Research activity information

• Mar. 2026 Japan Human Brain Maaping Society, Early Career award, Resting-state functional connectivity reveals diagnostic signatures in mood disorders

  Suzuka Narukawa, Ayumu Yamashita

  共同研究・競争的資金等の業績IDIRI


• Sep. 2025 日本視覚学会, ベストプレゼンテーション賞, 判断指示のない条件下における形状・質感情報の利用傾向の検討

  大野 颯斗, 山下歩, 天野薫


• Jan. 2025 日本視覚学会, ベストプレゼンテーション, 網膜損傷患者における視覚野反応の起源に関するfMRI解析

  渡邊隆太郎, 山下歩, 増田 洋一郎, 天野 薫


• Apr. 2021 ATR, 優秀研究賞, うつ病を脳回路から見分ける先端人工知能技術を開発

  山下歩


• Oct. 2019 Japanese Meeting for Human Brain Imaging, Young Scientist Award, Two dominant brain states reflect optimal and suboptimal attention

  Ayumu Yamashita


• Apr. 2018 ATR, 奨励賞, ニューロフィードバック法による認知機能変容に関する優れた業績

  山下歩


• 2017 東北脳科学ウインタースクール, Best Poster Award, 脳機能画像法の施設間差を調べるための旅行被験者研究における優れた業績

  山下歩


• 2017 rtFIN2017, Travel Award, Sampling biases and measurement biases due to different sites in resting-state functional connectivity data comparable with effects of mental disorders

  Ayumu Yamashita


• 2014 東北脳科学ウインタースクール, Best Poster Award, ニューロフィードバック法の開発に関する優れた業績

  山下歩

• MAME: Multidimensional adaptive metamer exploration with human perceptual feedback.

  Mina Kamao, Hayato Ono, Ayumu Yamashita, Kaoru Amano, Masataka Sawayama

  Alignment between human brain networks and artificial models has become an active research area in vision science and machine learning. A widely adopted approach is identifying "metamers," stimuli that are physically different yet perceptually equivalent within a system. However, conventional methods lack a direct approach to searching for the human metameric space. Instead, researchers first develop biologically inspired models and then infer about human metamers indirectly by testing whether model metamers also appear as metamers to humans. Here, we propose the multidimensional adaptive metamer exploration (MAME) framework, enabling direct, high-dimensional exploration of human metameric spaces through online image generation guided by human perceptual feedback. MAME modulates reference images across multiple dimensions based on hierarchical neural network responses, adaptively updating generation parameters according to participants' perceptual discriminability. Using MAME, we successfully measured multidimensional human metameric spaces within a single psychophysical experiment. Experimental results using a biologically plausible convolutional neural network (CNN) model showed that human discrimination sensitivity was lower for metameric images based on Gram-matrix representations derived from low-level CNN features than for those derived from high-level CNN features. The finding suggests a relatively worse alignment between the metameric spaces of humans and the CNN model for low-level processing compared with high-level processing. Counterintuitively, given recent discussions on alignment at higher representational levels, our results highlight the importance of early visual computations in shaping biologically plausible models. Our MAME framework can serve as a future scientific tool for directly investigating the functional organization of human vision.

  Aug. 2026, Journal of vision, 26(8) (8), 1 - 1, English, International magazine

  [Refereed]

  Scientific journal


• Extraction of robust functional connectivity patterns across psychiatric disorders using principal component analysis-based feature selection

  Ayumu Yamashita, Takashi Itahashi, Yuki Sakai, Masahiro Takamura, Hiroki Togo, Yujiro Yoshihara, Tomohisa Okada, Hirotaka Yamagata, Kenichiro Harada, Haruto Takagishi, Koichi Hosomi, Naohiro Okada, Osamu Abe, Go Okada, Yasumasa Okamoto, Ryuichiro Hashimoto, Takashi Hanakawa, Toshiya Murai, Koji Matsuo, Hidehiko Takahashi, Kiyoto Kasai, Takuya Hayashi, Shinsuke Koike, Saori C. Tanaka, Mitsuo Kawato, Hiroshi Imamizu, Okito Yamashita

  Feb. 2026, Imaging Neuroscience

  [Refereed]

  Scientific journal


• Probing the content of semantic representations in body-selective regions.

  Ryuto Yashiro, Masataka Sawayama, Ayumu Yamashita, Kaoru Amano

  Recent advances in neural networks trained on natural language have revealed that category-selective regions encode complex semantics and contextual information of natural scenes in addition to object categories. However, the limited interpretability of embeddings derived from these models complicates the characterization of the aspects of natural scenes that contribute to such semantic representations. Here we addressed this question by developing an analysis of the relationship between object co-occurrence in large-scale natural scene captions and corresponding fMRI responses predicted by caption-based encoding models, inspired by the fact that the joint presence of multiple objects generally shapes the overall content of a scene. We performed this analysis on the extrastriate body area (EBA), which responds strongly to human body parts. We found that human bodies co-occurring with sports-related objects drive the strongest predicted responses in the EBA among all image categories, whereas those co-occurring with vehicles or accessories elicit strong but weaker predicted responses. The findings from the co-occurrence analysis helped identify three key body-related features that contribute to the semantic representation in the EBA and fusiform body area: human body motion speed implied in static images of natural scenes is a primary contributor, and the number of people and body size are secondary contributors. Our framework, integrating object co-occurrence with caption-based encoding models, offers an interpretable approach for understanding high-level visual representations underlying natural scene perception.

  2026, Imaging neuroscience (Cambridge, Mass.), 4, English, International magazine

  [Refereed]

  Scientific journal


• Generalizable stratification based on thalamo–somatomotor functional connectivity predicts responses to antidepressants in patients with depression

  Yuto Kashiwagi, Tomoki Tokuda, Yuji Takahara, Yukiko Masaki, Yuki Sakai, Junichiro Yoshimoto, Ayumu Yamashita, Toshinori Yoshioka, Koichi Ogawa, Go Okada, Yasumasa Okamoto, Mitsuo Kawato, Okito Yamashita

  Jan. 2026, Molecular Psychiatry

  [Refereed]

  Scientific journal


• Category-Specific Brain Structural Changes in Psychiatric Disorders and Conditions Using Well-Qualified Harmonization Dataset from Multiple Sites

  Shinsuke Koike, Norihide Maikusa, Lin Cai, Yinghan Zhu, Issei Ueda, Saori Tanaka, Ayumu Yamashita, Okito Yamashita, Yuko Nakamura, Shuhei Shibukawa, Kentaro Morita, Susumu Morita, Naohiro Okada, Noriaki Yahata, Hidenori Yamasue, Akira Kunimatsu, Osamu Abe, Shiori Honda, Masataka Wada, Nobuaki Hondo, Yoshihiro Noda, Daisuke Fujikane, Yujiro Yoshihara, Hidehiko Takahashi, Toshiharu Kamishikiryo, Eri Itai, Daiki Sasabayashi, Michio Suzuki, Takashi Itahashi, Takuya Hayashi, Mitsuo Kawato, Ryuichiro Hashimoto, Tsutomu Takahashi, Toshiya Murai, Go Okada, Kazutaka Ohi, Shinichiro Nakajima, Kiyoto Kasai

  Sep. 2025


• Internal State Estimation via Physiological Data and Its Modulation by Environmental Context during Social Activity

  Ayumu Yamashita, Hiroki Maeda, Jouh Yeong Chew, Kaoru Amano

  Aug. 2025, Journal of Cognitive Neuroscience

  [Refereed]

  Scientific journal


• 安静時fMRIを用いた精神疾患の客観的診断確立と層別化 安静時脳回路から探る自閉スペクトラム症の生物学的基盤とその展望

  板橋 貴史, 山下 歩, 高原 雄史, 八幡 憲明, 青木 悠太, 藤野 純也, 吉原 雄二郎, 中村 元昭, 青木 隆太, 沖村 宰, 太田 晴久, 酒井 雄希, 高村 真広, 市川 奈穂, 岡田 剛, 岡田 直大, 笠井 清登, 田中 沙織, 今水 寛, 加藤 進昌, 高橋 英彦, 川人 光男, 山下 宙人, 橋本 龍一郎

  (公社)日本精神神経学会, Jun. 2025, 精神神経学雑誌, (2025特別号) (2025特別号), S537 - S537, Japanese


• Unsupervised feature computation-based feature selection robustly extracted resting-state functional connectivity patterns related to mental disorders

  Ayumu Yamashita, Takashi Itahashi, Yuki Sakai, Masahiro Takamura, Hiroki Togo, Yujiro Yoshihara, Tomohisa Okada, Hirotaka Yamagata, Kenichiro Harada, Haruto Takagishi, Koichi Hosomi, Naohiro Okada, Osamu Abe, Go Okada, Yasumasa Okamoto, Ryuichiro Hashimoto, Takashi Hanakawa, Toshiya Murai, Koji Matsuo, Hidehiko Takahashi, Kiyoto Kasai, Takuya Hayashi, Shinsuke Koike, Saori C. Tanaka, Mitsuo Kawato, Hiroshi Imamizu, Okito Yamashita

  Apr. 2025, bioRxiv


• Prediction of Alpha Power Using Multiple Subjective Measures and Autonomic Responses.

  Yuting Xu, Ayumu Yamashita, Kyuto Uno, Tomoya Kawashima, Kaoru Amano

  Alpha oscillations are associated with various cognitive functions.However, the determinants of alpha power variation remain ambiguous,primarily due to its inconsistent associations with autonomic responsesand subjective states under different experimental conditions. Tothoroughly examine the correlations between alpha power variation andthese factors, we implemented a range of experimental conditions,encompassing attentional and emotional tasks, as well as a restingstate. In addition to the electroencephalogram data, we gathered a suiteof autonomic response measurements and subjective ratings. We employedmultivariate linear regression analysis, utilizing autonomic responsesand subjective reports as predictors of alpha power. We also subtractedthe aperiodic components for better estimation of the power of periodicalpha oscillations. Our results demonstrated that the combined use ofautonomic response measurements and subjective ratings effectivelypredicted the periodic alpha power variation across a range ofconditions. These predictions were supported byleave-one-participant-out cross-validation, confirming that multivariatelinear relationships can be generalized to new participants. This studydemonstrates the links of alpha power variations with autonomicresponses and subjective states, suggesting that during investigationsof the cognitive functions of alpha oscillations, it is important toconsider the potential influences of autonomic responses and subjectivestates on alpha oscillations.

  Lead, Authorea, Inc., Mar. 2025, Psychophysiology, 62(3) (3), e70028, English, International magazine

  [Refereed]

  Scientific journal


• Comprehensive evaluation of pipelines for classification of psychiatric disorders using multi-site resting-state fMRI datasets

  Yuji Takahara, Yuto Kashiwagi, Tomoki Tokuda, Junichiro Yoshimoto, Yuki Sakai, Ayumu Yamashita, Toshinori Yoshioka, Hidehiko Takahashi, Hiroto Mizuta, Kiyoto Kasai, Akira Kunimitsu, Naohiro Okada, Eri Itai, Hotaka Shinzato, Satoshi Yokoyama, Yoshikazu Masuda, Yuki Mitsuyama, Go Okada, Yasumasa Okamoto, Takashi Itahashi, Haruhisa Ohta, Ryu-ichiro Hashimoto, Kenichiro Harada, Hirotaka Yamagata, Toshio Matsubara, Koji Matsuo, Saori C. Tanaka, Hiroshi Imamizu, Koichi Ogawa, Sotaro Momosaki, Mitsuo Kawato, Okito Yamashita

  Elsevier BV, Feb. 2025, Neural Networks, 107335 - 107335

  [Refereed]

  Scientific journal


• BrainCodec: Neural fMRI codec for the decoding of cognitive brain states

  Yuto Nishimura, Masataka Sawayama, Ayumu Yamashita, Hideki Nakayama, Kaoru Amano

  Recently, leveraging big data in deep learning has led to significant performance improvements, as confirmed in applications like mental state decoding using fMRI data. However, fMRI datasets remain relatively small in scale, and the inherent issue of low signal-to-noise ratios (SNR) in fMRI data further exacerbates these challenges. To address this, we apply compression techniques as a preprocessing step for fMRI data. We propose BrainCodec, a novel fMRI codec inspired by the neural audio codec. We evaluated BrainCodec's compression capability in mental state decoding, demonstrating further improvements over previous methods. Furthermore, we analyzed the latent representations obtained through BrainCodec, elucidating the similarities and differences between task and resting state fMRI, highlighting the interpretability of BrainCodec. Additionally, we demonstrated that fMRI reconstructions using BrainCodec can enhance the visibility of brain activity by achieving higher SNR, suggesting its potential as a novel denoising method. Our study shows that BrainCodec not only enhances performance over previous methods but also offers new analytical possibilities for neuroscience. Our codes, dataset, and model weights are available at https://github.com/amano-k-lab/BrainCodec.

  Oct. 2024, English


• Generalizable and transportable resting-state neural signatures characterized by functional networks, neurotransmitters, and clinical symptoms in autism

  Ayumu Yamashita, Takashi Itahashi, Yuji Takahara, Noriaki Yahata, Yuta Y. Aoki, Junya Fujino, Yujiro Yoshihara, Motoaki Nakamura, Ryuta Aoki, Tsukasa Okimura, Haruhisa Ohta, Yuki Sakai, Masahiro Takamura, Naho Ichikawa, Go Okada, Naohiro Okada, Kiyoto Kasai, Saori C. Tanaka, Hiroshi Imamizu, Nobumasa Kato, Yasumasa Okamoto, Hidehiko Takahashi, Mitsuo Kawato, Okito Yamashita, Ryu-ichiro Hashimoto

  Lead, Springer Science and Business Media LLC, Sep. 2024, Molecular Psychiatry

  [Refereed]

  Scientific journal


• Probing unexplored areas in high-dimensional fMRI voxel space using an encoding model and image synthesis

  Ryuto Yashiro, Masataka Sawayama, Ayumu Yamashita, Kaoru Amano

  Association for Research in Vision and Ophthalmology (ARVO), Sep. 2024, Journal of Vision, 24(10) (10), 537 - 537

  Scientific journal


• The status of MRI databases across the world focused on psychiatric and neurological disorders.

  Saori C Tanaka, Kiyoto Kasai, Yasumasa Okamoto, Shinsuke Koike, Takuya Hayashi, Ayumu Yamashita, Okito Yamashita, Tom Johnstone, Franco Pestilli, Kenji Doya, Go Okada, Hotaka Shinzato, Eri Itai, Yuji Takahara, Akihiro Takamiya, Motoaki Nakamura, Takashi Itahashi, Ryuta Aoki, Yukiaki Koizumi, Masaaki Shimizu, Jun Miyata, Shuraku Son, Morio Aki, Naohiro Okada, Susumu Morita, Nobukatsu Sawamoto, Mitsunari Abe, Yuki Oi, Kazuaki Sajima, Koji Kamagata, Masakazu Hirose, Yohei Aoshima, Sayo Hamatani, Nobuhiro Nohara, Misako Funaba, Tomomi Noda, Kana Inoue, Jinichi Hirano, Masaru Mimura, Hidehiko Takahashi, Nobutaka Hattori, Atsushi Sekiguchi, Mitsuo Kawato, Takashi Hanakawa

  Neuroimaging databases for neuro-psychiatric disorders enable researchers to implement data-driven research approaches by providing access to rich data that can be used to study disease, build and validate machine learning models, and even redefine disease spectra. The importance of sharing large, multi-center, multi-disorder databases has gradually been recognized in order to truly translate brain imaging knowledge into real-world clinical practice. Here, we review MRI databases that share data globally to serve multiple psychiatric or neurological disorders. We found 42 datasets consisting of 23,293 samples from patients with psychiatry and neurological disorders and healthy controls; 1245 samples from mood disorders (major depressive disorder and bipolar disorder), 2015 samples from developmental disorders (autism spectrum disorder, attention-deficit hyperactivity disorder), 675 samples from schizophrenia, 1194 samples from Parkinson's disease, 5865 samples from dementia (including Alzheimer's disease), We recognize that large, multi-center databases should include governance processes that allow data to be shared across national boundaries. Addressing technical and regulatory issues of existing databases can lead to better design and implementation and improve data access for the research community. The current trend toward the development of shareable MRI databases will contribute to a better understanding of the pathophysiology, diagnosis and assessment, and development of early interventions for neuropsychiatric disorders.

  Aug. 2024, Psychiatry and clinical neurosciences, English, International magazine

  [Refereed]

  Scientific journal


• Prediction of antidepressant treatment response with thalamo-somatomotor functional connectivity revealed by generalizable stratification of depressed patients

  Yuto Kashiwagi, Tomoki Tokuda, Yuji Takahara, Yuki Sakai, Junichiro Yoshimoto, Ayumu Yamashita, Toshinori Yoshioka, Koichi Ogawa, Go Okada, Yasumasa Okamoto, Mitsuo Kawato, Okito Yamashita

  ABSTRACT Major depressive disorder (MDD) is diagnosed based on symptoms and signs without relying on physical, biological, or cognitive tests. MDD patients exhibit a wide range of complex symptoms, and it is assumed that there are diverse underlying neurobiological backgrounds, possibly composed of several subtypes with relatively homogeneous biological features. Initiatives, including the Research Domain Criteria, emphasize the importance of biologically stratifying MDD patients into homogeneous subtypes using a data-driven approach while utilizing genetic, neuroscience, and cognitive information. If biomarkers can stratify MDD patients into biologically homogeneous subtypes at the first episode of depression, personalized precision medicine may be within our scope. Some pioneering studies have used resting-state functional brain connectivity (rs-FC) for stratification and predicted differential responses to various treatments for different subtypes. However, to our knowledge, little research has demonstrated reproducibility (i.e., generalizability) of stratification markers in independent validation cohorts. This issue may be due to inherent measurement and sampling biases in multi-site fMRI data, or overfitting of machine learning algorithms to discovery cohorts with small sample sizes, i.e., a lack of appropriate machine learning algorithms for generalizable stratification. To address this problem, we have constructed a multi-site, multi-disorder fMRI database with prospectively and retrospectively harmonized data from thousands of samples and proposed a hierarchical supervised/unsupervised learning strategy. In line with this strategy, our previous research first developed generalizable MDD diagnostic biomarkers using this fMRI database of MDD patients via supervised learning. The MDD diagnostic biomarker determines the importance of thousands to tens of thousands of rs-FCs across the whole brain for MDD diagnosis. In this study, we constructed stratification markers for MDD patients using unsupervised learning (Multiple co-clustering) with a subset of top-ranked rs-FCs in the MDD diagnostic biomarker. We developed a method to evaluate the clustering stability between two independent datasets as a generalization metric of stratification biomarkers. To discover stratification biomarkers with high stability across datasets, we utilized two multi-site datasets with substantial differences in data acquisition facilities and fMRI measurement protocols (Dataset-1: a dataset of 138 depressed patients obtained with a unified measurement protocol across three facilities; Dataset-2: a dataset of 181 depressed patients obtained with non-unified measurement protocols across four facilities, distinct from Dataset-1). Starting from several diagnostic biomarkers, we constructed some stratification markers and identified the stratification biomarker with the highest clustering stability between the two datasets. This stratification biomarker was based on several rs-FCs between the thalamus and the postcentral gyrus, and the MDD subgroups stratified by this biomarker showed significantly different treatment responsiveness to a selective serotonin reuptake inhibitor (SSRI). By narrowing down whole-brain rs-FCs using MDD diagnostic biomarkers and further dividing the rs-FCs using multiple co-clustering, the feature dimension was significantly reduced, thereby avoiding overfitting to the training data and successfully constructing stratification biomarkers that are highly stable between independent datasets, i.e., have generalizability. Furthermore, the correlation between MDD subgroups and antidepressant treatment response was demonstrated, suggesting the potential for achieving personalized precision medicine for MDD.

  Cold Spring Harbor Laboratory, May 2024


• Computational Mechanisms of Neuroimaging Biomarkers Uncovered by Multicenter Resting-State fMRI Connectivity Variation Profile

  Okito Yamashita, Ayumu Yamashita, Yuji Takahara, Yuki Sakai, Yasumasa Okamoto, Go Okada, Masahiro Takamura, Motoaki Nakamura, Takashi Itahashi, Takashi Hanakawa, Hiroki Togo, Yujiro Yoshihara, Toshiya Murai, Tomohisa Okada, Jin Narumoto, Hidehiko Takahashi, Haruto Takagishi, Koichi Hosomi, Kiyoto Kasai, Naohiro Okada, Osamu Abe, Hiroshi Imamizu, Takuya Hayashi, Shinsuke Koike, Saori C. Tanaka, Mitsuo Kawato

  Resting-state functional connectivity (rsFC) is increasingly used to develop biomarkers for psychiatric disorders. Despite progress, development of the reliable and practical FC biomarker remains an unmet goal, particularly one that is clinically predictive at the individual level with generalizability, robustness, and accuracy. In this study, we propose a new approach to profile each connectivity from diverse perspective, encompassing not only disorder-related differences but also disorder-unrelated variations attributed to individual difference, within-subject across-runs, imaging protocol, and scanner factors. By leveraging over 1500 runs of 10-minute resting-state data from 84 traveling-subjects across 29 sites and 900 participants of the case-control study with three psychiatric disorders, the disorder-related and disorder-unrelated FC variations were estimated for each individual FC. Using the FC profile information, we evaluated the effects of the disorder-related and disorder-unrelated variations on the output of the multi-connectivity biomarker trained with ensemble sparse classifiers and generalizable to the multicenter data. Our analysis revealed hierarchical variations in individual functional connectivity, ranging from within-subject across-run variations, individual differences, disease effects, inter-scanner discrepancies, and protocol differences, which were drastically inverted by the sparse machine-learning algorithm. We found this inversion mainly attributed to suppression of both individual difference and within-subject across-runs variations relative to the disorder-related difference by weighted-averaging of the selected FCs and ensemble computing. This comprehensive approach will provide an analytical tool to delineate future directions for developing reliable individual-level biomarkers.

  Cold Spring Harbor Laboratory, Apr. 2024, Molecular psychiatry, 30(11) (11), 5463 - 5474, English, International magazine

  Scientific journal


• Comprehensive evaluation of pipelines for diagnostic biomarkers of major depressive disorder using multi-site resting-state fMRI datasets

  Yuji Takahara, Yuto Kashiwagi, Tomoki Tokuda, Junichiro Yoshiomoto, Yuki Sakai, Ayumu Yamashita, Toshinori Yoshioka, Hidehiko Takahashi, Hiroto Mizuta, Kiyoto Kasai, Akira Kunimitsu, Naohiro Okada, Eri Itai, Hotaka Shinzato, Satoshi Yokoyama, Yoshikazu Masuda, Yuki Mitsuyama, Go Okada, Yasumasa Okamoto, Takashi Itahashi, Haruhisa Ota, Ryu-ichiro Hashimoto, Kenichiro Harada, Hirotaka Yamagata, Toshio Matsubara, Koji Matsuo, Saor C. Tanaka, Hiroshi Imamizu, Koichi Ogawa, Sotaro Momosaki, Mitsuo Kawato, Okito Yamashita

  The objective diagnostic and stratification biomarkers developed with resting-state functional magnetic resonance imaging (rs-fMRI) data are expected to contribute to more effective treatment for mental disorders. Unfortunately, there are currently no widely accepted biomarkers, partially due to the large variety of analysis pipelines for developing them. In this study we comprehensively evaluated analysis pipelines using a large-scale, multi-site fMRI dataset for major depressive disorder (MDD) (1162 participants from eight imaging sites). We explored the combinations of options in four subprocesses of analysis pipelines: six types of brain parcellation, four types of estimations of functional connectivity (FC), three types of site difference harmonization, and five types of machine learning methods. 360 different MDD diagnostic biomarkers were constructed using the SRPBS dataset acquired with unified protocols (713 participants from four imaging sites) as a discovery dataset and evaluated with datasets from other projects acquired with heterogeneous protocols (449 participants from four imaging sites) for independent validation. To identify the optimal options regardless of the discovery dataset, we repeated the same procedure after swapping the roles of the two datasets. We found pipelines that included Glasser's parcellation, tangent-covariance, no harmonization, and non-sparse machine learning methods tended to result in high classification performance. The diagnosis results of the top 10 biomarkers showed high similarity, and weight similarity was also observed between eight of the biomarkers, except two that used both data-driven parcellation and FC computation. We applied the top 10 pipelines to the datasets of other mental disorders (autism spectral disorder: ASD and schizophrenia: SCZ) and eight of the ten biomarkers showed sufficient classification performances for both disorders, except two pipelines that included Pearson correlation, ComBat harmonization and random forest classifier combination.

  Mar. 2024, English


• Effects of Transcranial Direct-Current Stimulation on Hand Redirection

  Shogo Tachi, Keigo Matsumoto, Maki Ogawa, Ayumu Yamashita, Takuji Narumi, Kaoru Amano

  IEEE, Mar. 2024, 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), 1047 - 1048

  International conference proceedings


• Generalisable functional imaging classifiers of schizophrenia have multifunctionality as trait, state, and staging biomarkers

  Ayumu Yamashita, Takahiko Kawashima, Yujiro Yoshihara, Yuko Kobayashi, Naohiro Okada, Kiyoto Kasai, Ming-Chyi Huang, Akira Sawa, Junichiro Yoshimoto, Okito Yamashita, Toshiya Murai, Jun Miyata, Mitsuo Kawato, Hidehiko Takahashi

  Lead, Jan. 2024


• Distinctive alterations in the mesocorticolimbic circuits in various psychiatric disorders

  Yuko Nakamura, Takuya Ishida, Saori C. Tanaka, Yuki Mitsuyama, Satoshi Yokoyama, Hotaka Shinzato, Eri Itai, Go Okada, Yuko Kobayashi, Takahiko Kawashima, Jun Miyata, Yujiro Yoshihara, Hidehiko Takahashi, Ryuta Aoki, Motoaki Nakamura, Haruhisa Ota, Takashi Itahashi, Susumu Morita, Shintaro Kawakami, Osamu Abe, Naohiro Okada, Akira Kunimatsu, Ayumu Yamashita, Okito Yamashita, Hiroshi Imamizu, Jun Morimoto, Yasumasa Okamoto, Toshiya Murai, Ryu‐Ichiro Hashimoto, Kiyoto Kasai, Mitsuo Kawato, Shinsuke Koike

  AIM: Increasing evidence suggests that psychiatric disorders are linked to alterations in the mesocorticolimbic dopamine-related circuits. However, the common and disease-specific alterations remain to be examined in schizophrenia (SCZ), major depressive disorder (MDD), and autism spectrum disorder (ASD). Thus, this study aimed to examine common and disease-specific features related to mesocorticolimbic circuits. METHODS: This study included 555 participants from four institutes with five scanners: 140 individuals with SCZ (45.0% female), 127 individuals with MDD (44.9%), 119 individuals with ASD (15.1%), and 169 healthy controls (HC) (34.9%). All participants underwent resting-state functional magnetic resonance imaging. A parametric empirical Bayes approach was adopted to compare estimated effective connectivity among groups. Intrinsic effective connectivity focusing on the mesocorticolimbic dopamine-related circuits including the ventral tegmental area (VTA), shell and core parts of the nucleus accumbens (NAc), and medial prefrontal cortex (mPFC) were examined using a dynamic causal modeling analysis across these psychiatric disorders. RESULTS: The excitatory shell-to-core connectivity was greater in all patients than in the HC group. The inhibitory shell-to-VTA and shell-to-mPFC connectivities were greater in the ASD group than in the HC, MDD, and SCZ groups. Furthermore, the VTA-to-core and VTA-to-shell connectivities were excitatory in the ASD group, while those connections were inhibitory in the HC, MDD, and SCZ groups. CONCLUSION: Impaired signaling in the mesocorticolimbic dopamine-related circuits could be an underlying neuropathogenesis of various psychiatric disorders. These findings will improve the understanding of unique neural alternations of each disorder and will facilitate identification of effective therapeutic targets.

  Wiley, Mar. 2023, Psychiatry and Clinical Neurosciences, 77(6) (6), 345 - 354, English, International magazine

  [Refereed]

  Scientific journal


• Aberrant Large-Scale Network Interactions Across Psychiatric Disorders Revealed by Large-Sample Multi-Site Resting-State Functional Magnetic Resonance Imaging Datasets.

  Takuya Ishida, Yuko Nakamura, Saori C Tanaka, Yuki Mitsuyama, Satoshi Yokoyama, Hotaka Shinzato, Eri Itai, Go Okada, Yuko Kobayashi, Takahiko Kawashima, Jun Miyata, Yujiro Yoshihara, Hidehiko Takahashi, Susumu Morita, Shintaro Kawakami, Osamu Abe, Naohiro Okada, Akira Kunimatsu, Ayumu Yamashita, Okito Yamashita, Hiroshi Imamizu, Jun Morimoto, Yasumasa Okamoto, Toshiya Murai, Kiyoto Kasai, Mitsuo Kawato, Shinsuke Koike

  BACKGROUND AND HYPOTHESIS: Dynamics of the distributed sets of functionally synchronized brain regions, known as large-scale networks, are essential for the emotional state and cognitive processes. However, few studies were performed to elucidate the aberrant dynamics across the large-scale networks across multiple psychiatric disorders. In this paper, we aimed to investigate dynamic aspects of the aberrancy of the causal connections among the large-scale networks of the multiple psychiatric disorders. STUDY DESIGN: We applied dynamic causal modeling (DCM) to the large-sample multi-site dataset with 739 participants from 4 imaging sites including 4 different groups, healthy controls, schizophrenia (SCZ), major depressive disorder (MDD), and bipolar disorder (BD), to compare the causal relationships among the large-scale networks, including visual network, somatomotor network (SMN), dorsal attention network (DAN), salience network (SAN), limbic network (LIN), frontoparietal network, and default mode network. STUDY RESULTS: DCM showed that the decreased self-inhibitory connection of LIN was the common aberrant connection pattern across psychiatry disorders. Furthermore, increased causal connections from LIN to multiple networks, aberrant self-inhibitory connections of DAN and SMN, and increased self-inhibitory connection of SAN were disorder-specific patterns for SCZ, MDD, and BD, respectively. CONCLUSIONS: DCM revealed that LIN was the core abnormal network common to psychiatric disorders. Furthermore, DCM showed disorder-specific abnormal patterns of causal connections across the 7 networks. Our findings suggested that aberrant dynamics among the large-scale networks could be a key biomarker for these transdiagnostic psychiatric disorders.

  Mar. 2023, Schizophrenia bulletin, 49(4) (4), 933 - 943, English, International magazine

  [Refereed]

  Scientific journal


• Verification of the brain network marker of major depressive disorder: Test-retest reliability and anterograde generalization performance for newly acquired data.

  Go Okada, Toshinori Yoshioka, Ayumu Yamashita, Eri Itai, Satoshi Yokoyama, Toshiharu Kamishikiryo, Hotaka Shinzato, Yoshikazu Masuda, Yuki Mitsuyama, Shigeyuki Kan, Akiko Kurata, Masahiro Takamura, Atsuo Yoshino, Akio Mantani, Osamu Yamamoto, Norio Yokota, Tatsuji Tamura, Hiroaki Jitsuiki, Mitsuo Kawato, Okito Yamashita, Yuki Sakai, Yasumasa Okamoto

  BACKGROUND: Recently, we developed a generalizable brain network marker for the diagnosis of major depressive disorder (MDD) across multiple imaging sites using resting-state functional magnetic resonance imaging. Here, we applied this brain network marker to newly acquired data to verify its test-retest reliability and anterograde generalization performance for new patients. METHODS: We tested the sensitivity and specificity of our brain network marker of MDD using data acquired from 43 new patients with MDD as well as new data from 33 healthy controls (HCs) who participated in our previous study. To examine the test-retest reliability of our brain network marker, we evaluated the intraclass correlation coefficients (ICCs) between the brain network marker-based classifier's output (probability of MDD) in two sets of HC data obtained at an interval of approximately 1 year. RESULTS: Test-retest correlation between the two sets of the classifier's output (probability of MDD) from HCs exhibited moderate reliability with an ICC of 0.45 (95 % confidence interval,0.13-0.68). The classifier distinguished patients with MDD and HCs with an accuracy of 69.7 % (sensitivity, 72.1 %; specificity, 66.7 %). LIMITATIONS: The data of patients with MDD in this study were cross-sectional, and the clinical significance of the marker, such as whether it is a state or trait marker of MDD and its association with treatment responsiveness, remains unclear. CONCLUSIONS: The results of this study reaffirmed the test-retest reliability and generalization performance of our brain network marker for the diagnosis of MDD.

  Jan. 2023, Journal of affective disorders, English, International magazine

  [Refereed]

  Scientific journal


• Punishment and reward normalize error-related cognitive control in PTSD by modulating salience network activation and connectivity

  Travis C. Evans, Joseph DeGutis, David Rothlein, Audreyana Jagger-Rickels, Ayumu Yamashita, Catherine B. Fortier, Jennifer R. Fonda, William Milberg, Regina McGlinchey, Michael Esterman

  Elsevier {BV}, Dec. 2021, Cortex, 145, 295 - 314

  [Refereed]

  Scientific journal


• Effects of upgrading acquisition-techniques and harmonization methods: A multi-modal MRI study with implications for longitudinal designs

  Takashi Itahashi, Yuta Y. Aoki, Ayumu Yamashita, Takafumi Soda, Junya Fujino, Haruhisa Ohta, Ryuta Aoki, Motoaki Nakamura, Nobumasa Kato, Saori C. Tanaka, Daisuke Kokuryo, Ryu-ichiro Hashimoto

  Abstract A downside of upgrading MRI acquisition sequences is the discontinuity of technological homogeneity of the MRI data. It hampers combining new and old datasets, especially in a longitudinal design. Characterizing upgrading effects on multiple brain parameters and examining the efficacy of harmonization methods are essential. This study investigated the upgrading effects on three structural parameters, including cortical thickness (CT), surface area (SA), cortical volume (CV), and resting-state functional connectivity (rs-FC) collected from 64 healthy volunteers. We used two evaluation metrics, Cohen’s d and classification accuracy, to quantify the effects. In classification analyses, we built classifiers for differentiating the protocols from brain parameters. We investigated the efficacy of three harmonization methods, including traveling subject (TS), TS-ComBat, and ComBat methods, and the sufficient number of participants for eliminating the effects on the evaluation metrics. Finally, we performed age prediction as an example to confirm that harmonization methods retained biological information. The results without harmonization methods revealed small to large mean Cohen’s d values on brain parameters (CT:0.85, SA:0.66, CV:0.68, and rs-FC:0.24) with better classification accuracy (>92% accuracy). With harmonization methods, Cohen’s d values approached zero. Classification performance reached the chance level with TS-based techniques when data from less than 26 participants were used for estimating the effects, while the Combat method required more participants. Furthermore, harmonization methods improved age prediction performance, except for the ComBat method. These results suggest that acquiring TS data is essential to preserve the continuity of MRI data.

  Cold Spring Harbor Laboratory, Nov. 2021


• A multi-site, multi-disorder resting-state magnetic resonance image database.

  Saori C Tanaka, Ayumu Yamashita, Noriaki Yahata, Takashi Itahashi, Giuseppe Lisi, Takashi Yamada, Naho Ichikawa, Masahiro Takamura, Yujiro Yoshihara, Akira Kunimatsu, Naohiro Okada, Ryuichiro Hashimoto, Go Okada, Yuki Sakai, Jun Morimoto, Jin Narumoto, Yasuhiro Shimada, Hiroaki Mano, Wako Yoshida, Ben Seymour, Takeshi Shimizu, Koichi Hosomi, Youichi Saitoh, Kiyoto Kasai, Nobumasa Kato, Hidehiko Takahashi, Yasumasa Okamoto, Okito Yamashita, Mitsuo Kawato, Hiroshi Imamizu

  Machine learning classifiers for psychiatric disorders using resting-state functional magnetic resonance imaging (rs-fMRI) have recently attracted attention as a method for directly examining relationships between neural circuits and psychiatric disorders. To develop accurate and generalizable classifiers, we compiled a large-scale, multi-site, multi-disorder neuroimaging database. The database comprises resting-state fMRI and structural images of the brain from 993 patients and 1,421 healthy individuals, as well as demographic information such as age, sex, and clinical rating scales. To harmonize the multi-site data, nine healthy participants ("traveling subjects") visited the sites from which the above datasets were obtained and underwent neuroimaging with 12 scanners. All participants consented to having their data shared and analyzed at multiple medical and research institutions participating in the project, and 706 patients and 1,122 healthy individuals consented to having their data disclosed. Finally, we have published four datasets: 1) the SRPBS Multi-disorder Connectivity Dataset 2), the SRPBS Multi-disorder MRI Dataset (restricted), 3) the SRPBS Multi-disorder MRI Dataset (unrestricted), and 4) the SRPBS Traveling Subject MRI Dataset.

  Aug. 2021, Scientific data, 8(1) (1), 227 - 227, English, International magazine

  [Refereed]

  Scientific journal


• Comparison of traveling-subject and ComBat harmonization methods for assessing structural brain characteristics.

  Norihide Maikusa, Yinghan Zhu, Akiko Uematsu, Ayumu Yamashita, Kousaku Saotome, Naohiro Okada, Kiyoto Kasai, Kazuo Okanoya, Okito Yamashita, Saori C Tanaka, Shinsuke Koike

  Multisite magnetic resonance imaging (MRI) is increasingly used in clinical research and development. Measurement biases-caused by site differences in scanner/image-acquisition protocols-negatively influence the reliability and reproducibility of image-analysis methods. Harmonization can reduce bias and improve the reproducibility of multisite datasets. Herein, a traveling-subject (TS) dataset including 56 T1-weighted MRI scans of 20 healthy participants in three different MRI procedures-20, 19, and 17 subjects in Procedures 1, 2, and 3, respectively-was considered to compare the reproducibility of TS-GLM, ComBat, and TS-ComBat harmonization methods. The minimum participant count required for harmonization was determined, and the Cohen's d between different MRI procedures was evaluated as a measurement-bias indicator. The measurement-bias reduction realized with different methods was evaluated by comparing test-retest scans for 20 healthy participants. Moreover, the minimum subject count for harmonization was determined by comparing test-retest datasets. The results revealed that TS-GLM and TS-ComBat reduced measurement bias by up to 85 and 81.3%, respectively. Meanwhile, ComBat showed a reduction of only 59.0%. At least 6 TSs were required to harmonize data obtained from different MRI scanners, complying with the imaging protocol predetermined for multisite investigations and operated with similar scan parameters. The results indicate that TS-based harmonization outperforms ComBat for measurement-bias reduction and is optimal for MRI data in well-prepared multisite investigations. One drawback is the small sample size used, potentially limiting the applicability of ComBat. Investigation on the number of subjects needed for a large-scale study is an interesting future problem.

  Aug. 2021, Human brain mapping, 42(16) (16), 5278 - 5287, English, International magazine

  [Refereed]

  Scientific journal


• Brain state-based detection of attentional fluctuations and their modulation.

  Ayumu Yamashita, David Rothlein, Aaron Kucyi, Eve M Valera, Michael Esterman

  In the search for brain markers of optimal attentional focus, the mainstream approach has been to first define attentional states based on behavioral performance, and to subsequently investigate "neural correlates" associated with these performance variations. However, this approach constrains the range of contexts in which attentional states can be operationalized by relying on overt behavior, and assumes a one-to-one correspondence between behavior and brain state. Here, we reversed the logic of these previous studies and sought to identify behaviorally-relevant brain states based solely on brain activity, agnostic to behavioral performance. In four independent datasets, we found that the same two brain states were dominant during a sustained attention task. One state was behaviorally optimal, with higher accuracy and stability, but a greater tendency to mind wander (State1). The second state was behaviorally suboptimal, with lower accuracy and instability (State2). We further demonstrate how these brain states were impacted by motivation and attention-deficit/hyperactivity disorder (ADHD). Individuals with ADHD spent more time in suboptimal State2 and less time in optimal State1 than healthy controls. Motivation overcame the suboptimal behavior associated with State2. Our study provides compelling evidence for the existence of two attentional states from the sole viewpoint of brain activity.

  Elsevier {BV}, Aug. 2021, NeuroImage, 236, 118072 - 118072, English, International magazine

  [Refereed]

  Scientific journal


• Variable rather than extreme slow reaction times distinguish brain states during sustained attention.

  Ayumu Yamashita, David Rothlein, Aaron Kucyi, Eve M Valera, Laura Germine, Jeremy Wilmer, Joseph DeGutis, Michael Esterman

  A common behavioral marker of optimal attention focus is faster responses or reduced response variability. Our previous study found two dominant brain states during sustained attention, and these states differed in their behavioral accuracy and reaction time (RT) variability. However, RT distributions are often positively skewed with a long tail (i.e., reflecting occasional slow responses). Therefore, a larger RT variance could also be explained by this long tail rather than the variance around an assumed normal distribution (i.e., reflecting pervasive response instability based on both faster and slower responses). Resolving this ambiguity is important for better understanding mechanisms of sustained attention. Here, using a large dataset of over 20,000 participants who performed a sustained attention task, we first demonstrated the utility of the exGuassian distribution that can decompose RTs into a strategy factor, a variance factor, and a long tail factor. We then investigated which factor(s) differed between the two brain states using fMRI. Across two independent datasets, results indicate unambiguously that the variance factor differs between the two dominant brain states. These findings indicate that 'suboptimal' is different from 'slow' at the behavior and neural level, and have implications for theoretically and methodologically guiding future sustained attention research.

  Jul. 2021, Scientific reports, 11(1) (1), 14883 - 14883, English, International magazine

  [Refereed]

  Scientific journal


• Integration and segregation across large-scale intrinsic brain networks as a marker of sustained attention and task-unrelated thought.

  Agnieszka Zuberer, Aaron Kucyi, Ayumu Yamashita, Charley M Wu, Martin Walter, Eve M Valera, Michael Esterman

  Sustained attention is a fundamental cognitive process that can be decoupled from distinct external events, and instead emerges from ongoing intrinsic large-scale network interdependencies fluctuating over seconds to minutes. Lapses of sustained attention are commonly associated with the subjective experience of mind wandering and task-unrelated thoughts. Little is known about how fluctuations in information processing underpin sustained attention, nor how mind wandering undermines this information processing. To overcome this, we used fMRI to investigate brain activity during subjects' performance (n=29) of a cognitive task that was optimized to detect and isolate continuous fluctuations in both sustained attention (via motor responses) and task-unrelated thought (via subjective reports). We then investigated sustained attention with respect to global attributes of communication throughout the functional architecture, i.e., by the segregation and integration of information processing across large scale-networks. Further, we determined how task-unrelated thoughts related to these global information processing markers of sustained attention. The results show that optimal states of sustained attention favor both enhanced segregation and reduced integration of information processing in several task-related large-scale cortical systems with concurrent reduced segregation and enhanced integration in the auditory and sensorimotor systems. Higher degree of mind wandering was associated with losses of the favored segregation and integration of specific subsystems in our sustained attention model. Taken together, we demonstrate that intrinsic ongoing neural fluctuations are characterized by two converging communication modes throughout the global functional architecture, which give rise to optimal and suboptimal attention states. We discuss how these results might potentially serve as neural markers for clinically abnormal attention. SIGNIFICANCE STATEMENT: Most of our brain activity unfolds in an intrinsic manner, i.e., is unrelated to immediate external stimuli or tasks. Here we use a gradual continuous performance task to map this intrinsic brain activity to both fluctuations of sustained attention and mind wandering. We show that optimal sustained attention is associated with concurrent segregation and integration of information processing within many large-scale brain networks, while task-unrelated thought is related to sub-optimal information processing in specific subsystems of this sustained attention network model. These findings provide a novel information processing framework for investigating the neural basis of sustained attention, by mapping attentional fluctuations to genuinely global features of intra-brain communication.

  Elsevier {BV}, Apr. 2021, NeuroImage, 229, 117610 - 117610, English, International magazine

  [Refereed]

  Scientific journal


• Brain/MINDS beyond human brain MRI project: A protocol for multi-level harmonization across brain disorders throughout the lifespan.

  Ayumu Yamashita, Shinsuke Koike, Saori C Tanaka, Tomohisa Okada, Toshihiko Aso, Okito Yamashita, Michiko Asano, Norihide Maikusa, Kentaro Morita, Naohiro Okada, Masaki Fukunaga, Akiko Uematsu, Hiroki Togo, Atsushi Miyazaki, Katsutoshi Murata, Yuta Urushibata, Joonas Autio, Takayuki Ose, Junichiro Yoshimoto, Toshiyuki Araki, Matthew F Glasser, David C Van Essen, Megumi Maruyama, Norihiro Sadato, Mitsuo Kawato, Kiyoto Kasai, Yasumasa Okamoto, Takashi Hanakawa, Takuya Hayashi

  Psychiatric and neurological disorders are afflictions of the brain that can affect individuals throughout their lifespan. Many brain magnetic resonance imaging (MRI) studies have been conducted; however, imaging-based biomarkers are not yet well established for diagnostic and therapeutic use. This article describes an outline of the planned study, the Brain/MINDS Beyond human brain MRI project (BMB-HBM, FY2018 ~ FY2023), which aims to establish clinically-relevant imaging biomarkers with multi-site harmonization by collecting data from healthy traveling subjects (TS) at 13 research sites. Collection of data in psychiatric and neurological disorders across the lifespan is also scheduled at 13 sites, whereas designing measurement procedures, developing and analyzing neuroimaging protocols, and databasing are done at three research sites. A high-quality scanning protocol, Harmonization Protocol (HARP), was established for five high-quality 3 T scanners to obtain multimodal brain images including T1 and T2-weighted, resting-state and task functional and diffusion-weighted MRI. Data are preprocessed and analyzed using approaches developed by the Human Connectome Project. Preliminary results in 30 TS demonstrated cortical thickness, myelin, functional connectivity measures are comparable across 5 scanners, suggesting sensitivity to subject-specific connectome. A total of 75 TS and more than two thousand patients with various psychiatric and neurological disorders are scheduled to participate in the project, allowing a mixed model statistical harmonization. The HARP protocols are publicly available online, and all the imaging, demographic and clinical information, harmonizing database will also be made available by 2024. To the best of our knowledge, this is the first project to implement a prospective, multi-level harmonization protocol with multi-site TS data. It explores intractable brain disorders across the lifespan and may help to identify the disease-specific pathophysiology and imaging biomarkers for clinical practice.

  Lead, 2021, NeuroImage. Clinical, 30, 102600 - 102600, English, International magazine

  [Refereed]

  Scientific journal


• Common Brain Networks Between Major Depressive-Disorder Diagnosis and Symptoms of Depression That Are Validated for Independent Cohorts.

  Ayumu Yamashita, Yuki Sakai, Takashi Yamada, Noriaki Yahata, Akira Kunimatsu, Naohiro Okada, Takashi Itahashi, Ryuichiro Hashimoto, Hiroto Mizuta, Naho Ichikawa, Masahiro Takamura, Go Okada, Hirotaka Yamagata, Kenichiro Harada, Koji Matsuo, Saori C Tanaka, Mitsuo Kawato, Kiyoto Kasai, Nobumasa Kato, Hidehiko Takahashi, Yasumasa Okamoto, Okito Yamashita, Hiroshi Imamizu

  Large-scale neuroimaging data acquired and shared by multiple institutions are essential to advance neuroscientific understanding of pathophysiological mechanisms in psychiatric disorders, such as major depressive disorder (MDD). About 75% of studies that have applied machine learning technique to neuroimaging have been based on diagnoses by clinicians. However, an increasing number of studies have highlighted the difficulty in finding a clear association between existing clinical diagnostic categories and neurobiological abnormalities. Here, using resting-state functional magnetic resonance imaging, we determined and validated resting-state functional connectivity related to depression symptoms that were thought to be directly related to neurobiological abnormalities. We then compared the resting-state functional connectivity related to depression symptoms with that related to depression diagnosis that we recently identified. In particular, for the discovery dataset with 477 participants from 4 imaging sites, we removed site differences using our recently developed harmonization method and developed a brain network prediction model of depression symptoms (Beck Depression Inventory-II [BDI] score). The prediction model significantly predicted BDI score for an independent validation dataset with 439 participants from 4 different imaging sites. Finally, we found 3 common functional connections between those related to depression symptoms and those related to MDD diagnosis. These findings contribute to a deeper understanding of the neural circuitry of depressive symptoms in MDD, a hetero-symptomatic population, revealing the neural basis of MDD.

  2021, Frontiers in psychiatry, 12, 667881 - 667881, English, International magazine

  [Refereed]

  Scientific journal


• Generalizable brain network markers of major depressive disorder across multiple imaging sites.

  Ayumu Yamashita, Yuki Sakai, Takashi Yamada, Noriaki Yahata, Akira Kunimatsu, Naohiro Okada, Takashi Itahashi, Ryuichiro Hashimoto, Hiroto Mizuta, Naho Ichikawa, Masahiro Takamura, Go Okada, Hirotaka Yamagata, Kenichiro Harada, Koji Matsuo, Saori C Tanaka, Mitsuo Kawato, Kiyoto Kasai, Nobumasa Kato, Hidehiko Takahashi, Yasumasa Okamoto, Okito Yamashita, Hiroshi Imamizu

  Many studies have highlighted the difficulty inherent to the clinical application of fundamental neuroscience knowledge based on machine learning techniques. It is difficult to generalize machine learning brain markers to the data acquired from independent imaging sites, mainly due to large site differences in functional magnetic resonance imaging. We address the difficulty of finding a generalizable marker of major depressive disorder (MDD) that would distinguish patients from healthy controls based on resting-state functional connectivity patterns. For the discovery dataset with 713 participants from 4 imaging sites, we removed site differences using our recently developed harmonization method and developed a machine learning MDD classifier. The classifier achieved an approximately 70% generalization accuracy for an independent validation dataset with 521 participants from 5 different imaging sites. The successful generalization to a perfectly independent dataset acquired from multiple imaging sites is novel and ensures scientific reproducibility and clinical applicability.

  Dec. 2020, PLOS biology, 18(12) (12), e3000966, English, International magazine

  [Refereed]

  Scientific journal


• 安静時脳機能結合に基づいた施設間安定性を有するうつ病層別化マーカーの開発

  柏木 雄人, 徳田 智磯, 高原 雄史, 酒井 雄希, 吉本 潤一郎, 山下 歩, 吉岡 利福, 小川 公一, 川人 光男, 山下 宙人

  日本神経精神薬理学会・日本生物学的精神医学会・日本精神薬学会, Aug. 2020, 日本神経精神薬理学会年会・日本生物学的精神医学会年会・日本精神薬学会総会・学術集会合同年会プログラム・抄録集, 50回・42回・4回, 216 - 216, Japanese


• Harmonization of resting-state functional MRI data across multiple imaging sites via the separation of site differences into sampling bias and measurement bias.

  Ayumu Yamashita, Noriaki Yahata, Takashi Itahashi, Giuseppe Lisi, Takashi Yamada, Naho Ichikawa, Masahiro Takamura, Yujiro Yoshihara, Akira Kunimatsu, Naohiro Okada, Hirotaka Yamagata, Koji Matsuo, Ryuichiro Hashimoto, Go Okada, Yuki Sakai, Jun Morimoto, Jin Narumoto, Yasuhiro Shimada, Kiyoto Kasai, Nobumasa Kato, Hidehiko Takahashi, Yasumasa Okamoto, Saori C Tanaka, Mitsuo Kawato, Okito Yamashita, Hiroshi Imamizu

  When collecting large amounts of neuroimaging data associated with psychiatric disorders, images must be acquired from multiple sites because of the limited capacity of a single site. However, site differences represent a barrier when acquiring multisite neuroimaging data. We utilized a traveling-subject dataset in conjunction with a multisite, multidisorder dataset to demonstrate that site differences are composed of biological sampling bias and engineering measurement bias. The effects on resting-state functional MRI connectivity based on pairwise correlations because of both bias types were greater than or equal to psychiatric disorder differences. Furthermore, our findings indicated that each site can sample only from a subpopulation of participants. This result suggests that it is essential to collect large amounts of neuroimaging data from as many sites as possible to appropriately estimate the distribution of the grand population. Finally, we developed a novel harmonization method that removed only the measurement bias by using a traveling-subject dataset and achieved the reduction of the measurement bias by 29% and improvement of the signal-to-noise ratios by 40%. Our results provide fundamental knowledge regarding site effects, which is important for future research using multisite, multidisorder resting-state functional MRI data.

  Apr. 2019, PLOS biology, 17(4) (4), e3000042, English, International magazine

  [Refereed]

  Scientific journal


• Connectivity Neurofeedback Training Can Differentially Change Functional Connectivity and Cognitive Performance.

  Ayumu Yamashita, Shunsuke Hayasaka, Mitsuo Kawato, Hiroshi Imamizu

  Advances in functional magnetic resonance imaging have made it possible to provide real-time feedback on brain activity. Neurofeedback has been applied to therapeutic interventions for psychiatric disorders. Since many studies have shown that most psychiatric disorders exhibit abnormal brain networks, a novel experimental paradigm named connectivity neurofeedback, which can directly modulate a brain network, has emerged as a promising approach to treat psychiatric disorders. Here, we investigated the hypothesis that connectivity neurofeedback can induce the aimed direction of change in functional connectivity, and the differential change in cognitive performance according to the direction of change in connectivity. We selected the connectivity between the left primary motor cortex and the left lateral parietal cortex as the target. Subjects were divided into 2 groups, in which only the direction of change (an increase or a decrease in correlation) in the experimentally manipulated connectivity differed between the groups. As a result, subjects successfully induced the expected connectivity changes in either of the 2 directions. Furthermore, cognitive performance significantly and differentially changed from preneurofeedback to postneurofeedback training between the 2 groups. These findings indicate that connectivity neurofeedback can induce the aimed direction of change in connectivity and also a differential change in cognitive performance.

  Lead, Oct. 2017, Cerebral cortex (New York, N.Y. : 1991), 27(10) (10), 4960 - 4970, English, International magazine

  [Refereed]

  Scientific journal


• Functional MRI neurofeedback training on connectivity between two regions induces long-lasting changes in intrinsic functional network.

  Fukuda Megumi, Ayumu Yamashita, Mitsuo Kawato, Hiroshi Imamizu

  Motor or perceptual learning is known to influence functional connectivity between brain regions and induce short-term changes in the intrinsic functional networks revealed as correlations in slow blood-oxygen-level dependent (BOLD) signal fluctuations. However, no cause-and-effect relationship has been elucidated between a specific change in connectivity and a long-term change in global networks. Here, we examine the hypothesis that functional connectivity (i.e., temporal correlation between two regions) is increased and preserved for a long time when two regions are simultaneously activated or deactivated. Using the connectivity-neurofeedback training paradigm, subjects successfully learned to increase the correlation of activity between the lateral parietal and primary motor areas, regions that belong to different intrinsic networks and negatively correlated before training under the resting conditions. Furthermore, whole-brain hypothesis-free analysis as well as functional network analyses demonstrated that the correlation in the resting state between these areas as well as the correlation between the intrinsic networks that include the areas increased for at least 2 months. These findings indicate that the connectivity-neurofeedback training can cause long-term changes in intrinsic connectivity and that intrinsic networks can be shaped by experience-driven modulation of regional correlation.

  Frontiers Media SA, 2015, Frontiers in human neuroscience, 9, 160 - 160, English, International magazine

  [Refereed]

  Scientific journal

• Neural Basis of Methamphetamine from Frameworks of Psychosis and Addiction: fMRI, Machine Learning

  山本祐輝, 杉原玄一, 清水正彬, 河島孝彦, 山下歩, 山下歩, 竹内秀暁, 竹内秀暁, 鶴身孝介, 吉原雄二郎, 吉本潤一郎, 吉本潤一郎, 宮田淳, 宮田淳, 村井俊哉, 川人光男, HUANG Ming-Chyi, HUANG Ming-Chyi, 高橋英彦, 高橋英彦

  2025, 日本ヒト脳機能マッピング学会プログラム・抄録集, 27th (CD-ROM)


• Supporting depression diagnosis through machine learning

  Mar. 2023, Nature portfolio


• Longitudinal reliability of Brain Network Marker for Major Depressive Disorder and its association with clinical status

  新里輔鷹, 新里輔鷹, 岡田剛, 吉岡利福, 吉岡利福, 山下歩, 板井江梨, 上敷領俊晴, 横山仁史, 光山祐生, 増田慶一, 川人光男, 川人光男, 山下宙人, 酒井雄希, 酒井雄希, 岡本泰昌

  2023, 日本生物学的精神医学会(Web), 45th


• Hierarchical supervised/unsupervised approach for subtype and redefine psychiatric disorders using a harmonized multi-site multi-disorder resting state functional magnetic resonance imaging

  山下歩, 山下歩, SAKAI Yuki, SAKAI Yuki, YAMADA Takashi, YAMADA Takashi, YAHATA Noriaki, YAHATA Noriaki, YAHATA Noriaki, YAHATA Noriaki, KUNIMATSU Akira, KUNIMATSU Akira, OKADA Naohiro, OKADA Naohiro, ITAHASHI Takashi, HASHIMOTO Ryuichiro, HASHIMOTO Ryuichiro, HASHIMOTO Ryuichiro, MIZUTA Hiroto, ICHIKAWA Naho, TAKAMURA Masahiro, OKADA Go, YAMAGATA Hirotaka, HARADA Kenichiro, MATSUO Koji, TANAKA Saori C, TANAKA Saori C, KAWATO Mitsuo, KAWATO Mitsuo, KASAI Kiyoto, KASAI Kiyoto, KASAI Kiyoto, KATO Nobumasa, TAKAHASHI Hidehiko, TAKAHASHI Hidehiko, OKAMOTO Yasumasa, YAMAHSHITA Okito, IMAMIZU Hiroshi

  2022, 日本生物学的精神医学会(Web), 44th


• 個人に合わせたデフォルトモードネットワークの機能的結合は持続的注意の能力を反映する

  板橋貴史, 山下歩, 青木悠太, 青木隆太, 青木隆太, 太田晴久, 中村元昭, 加藤進昌, 橋本龍一郎, 橋本龍一郎

  2022, 日本神経科学会大会抄録集(Web), 65th


• 6 Recommended Articles from PLOS Biology Senior Editor Gabriel Gasque

  Jun. 2021, PLOS Biologue


• 他施設汎化可能なうつ病診断イメージングマーカー構築手法の網羅的な探索

  高原 雄史, 柏木 雄人, 徳田 智磯, 小川 公一, 吉本 潤一郎, 酒井 雄希, 山下 歩, 吉岡 利福, 川人 光男, 山下 宙人

  日本神経精神薬理学会・日本生物学的精神医学会・日本精神薬学会, Aug. 2020, 日本神経精神薬理学会年会・日本生物学的精神医学会年会・日本精神薬学会総会・学術集会合同年会プログラム・抄録集, 50回・42回・4回, 216 - 216, Japanese


• うつ病と抑うつ気分に共通する機能的結合

  山下歩, 山下歩, 早坂俊亮, 早坂俊亮, LISI Giuseppe, 市川奈穂, 高村真広, 岡田剛, 森本淳, 八幡憲明, 八幡憲明, 岡本泰昌, 川人光男, 今水寛, 今水寛

  日本生物学的精神医学会・日本神経精神薬理学会, Sep. 2015, 日本神経精神薬理学会プログラム・抄録集, 37回・45回, 166 - 166, Japanese


• Functional MRI neurofeedback training for changing both connectivity between intrinsic functional networks and cognitive performance

  YAMASHITA Ayumu, KAWATO Mitsuo, IMAMIZU Hiroshi

  本研究は,functional Magnetic Resonance Imaging(fMRI)による結合ニューロフィードバックトレーニングを用いて,安静時機能的結合を変化させることにより,安静時機能的結合と認知機能の因果関係を探るとともに認知機能の改善につなげるための基礎研究である.現在までに,様々なニューロフィードバックトレーニングの方法が提案されているが,安静時機能的結合を操作的に変化させるための結合ニューロフィードバックトレーニングの方法はいまだ確立されていない.さらに,結合ニューロフィードバックトレーニングでは相関値を扱うため,オンラインでノイズを除去する方法に関してさらに改善する必要がある.本研究は,安静時機能的結合を操作的に変化させるための結合ニューロフィードバックトレーニングの方法として,ネットワークを用いた結合ニューロフィードバックトレーニングの提案し,オンラインでノイズを除去する方法について検討を行った.実験の結果,オンラインでノイズを除去する必要があること,セッション内だけのデータを用いたノイズ除去の方法よりも一つ前のセッションのデータも用いたオンラインでのノイズ除去の方法が優れていることがわかった.

  The Institute of Electronics, Information and Communication Engineers, 17 Mar. 2014, IEICE technical report. Neurocomputing, 113(500) (500), 215 - 220, Japanese

• MEG・EEG入門 ―脳磁図と脳波の原理から解析・解釈まで―

  山下歩

  Joint translation, 9章：アーチファクト，22章：一歩引いて前を見る：人間の脳の理解に向けて, 朝倉書店, Jun. 2026, ISBN: 9784254103090


• 高次脳機能研究最前線 : 基盤技術から脳のデジタル化まで

  エヌ・ティー・エス

  Contributor, 第3編 脳機能DX化と脳研究倫理、第3章 脳のモデル化、1 節 精神疾患MRIデータによる脳回路機能解明と臨床デジタル脳の開発, エヌ・ティー・エス, Jan. 2026, Japanese, ISBN: 9784860439118


• 高次脳機能研究最前線 : 基盤技術から脳のデジタル化まで

  エヌ・ティー・エス

  Contributor, 第3編 脳機能DX化と脳研究倫理、第1章 データ統合による情報の可視化・定量化、3 節 脳活動と生体情報計測に基づく集中状態の定量化, エヌ・ティー・エス, Jan. 2026, Japanese, ISBN: 9784860439118


• うつ病の生物学的基盤と最新治療

  山下歩

  Contributor, Q78.ニューロフィードバックを利用したうつ病治療の研究結果をまとめてください。, 星和書店, Oct. 2025

• 脳活動から状態を読み解く：集中力の神経メカニズムに関する統一的理解を目指して

  山下歩

  生理研研究会「インタラクションとレジリエンスの神経ダイナミクス」, Aug. 2025

  [Invited]

  Invited oral presentation


• 脳はかく語りき～脳に直接聞いてみた～

  山下歩

  第51回「音楽と脳」研究会, 2025

  [Invited]


• Resting State Functional Connectivity Related to Major Depressive Disorder

  Ayumu Yamashita

  Society for Neuroscience 2023 Press conference on AI/Machine Learning, Nov. 2023, English

  [Invited]

  Media report


• 脳活動から集中力を科学する

  Ayumu Yamashita

  JSPS日本人研究者交流会冬, Mar. 2021, Japanese

  [Invited]

  Invited oral presentation


• Two dominant brain states reflect optimal and suboptimal attention

  Ayumu Yamashita

  2nd Mind Wandering Symposium, Mar. 2020, English

  [Invited]

  Nominated symposium


• Harmonization of resting‐state functional MRI data across multiple imaging sites via the separation of site differences into sampling bias and measurement bias

  Ayumu Yamashita

  3rd Japanese Meeting for Human Brain Imaging, Sep. 2019, English

  [Invited]

  Nominated symposium

• 記憶機能に関する全脳ダイナミクス・バイオマーカの開発とニューロフィードバック訓練の基盤構築

  今水寛, 浅井智久, 山下歩, 髙橋英彦

  国立研究開発法人日本医療研究開発機構, 脳神経科学統合プログラム（個別重点研究課題）, 株式会社国際電気通信基礎技術研究所, Apr. 2025 - Mar. 2030, Coinvestigator


• デジタル世代のインターネット依存・ADHDにおける縦断的脳ダイナミクスデータとスマホログデータを用いた発症・治療効果予測モデルの構築

  高橋英彦, 高岸治人, 今水寛, 山下歩

  国立研究開発法人日本医療研究開発機構, 脳神経科学統合プログラム（個別重点研究課題）, 東京大学, Apr. 2025 - Mar. 2030, Coinvestigator


• 抑うつ症状と認知機能障害が生じる皮質−皮質下脳ダイナミクスのヒト多次元縦断データを用いた解明と霊長類モデルでの検証

  岡田剛, 酒井雄希, 南本敬史, 山下歩

  国立研究開発法人日本医療研究開発機構, 脳神経科学統合プログラム（個別重点課題）, 株式会社国際電気通信基礎技術研究所 脳情報通信総合研究所, Apr. 2024 - Mar. 2030, Coinvestigator


• Elucidating the neural mechanisms of pre-performance routines and developing efficient training methods

  山下 歩

  Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Early-Career Scientists, The University of Tokyo, 01 Apr. 2023 - 31 Mar. 2026


• 脳活動を活用した注意対象の定量化に基づくADHDの持続的注意能力障害の神経メカニズムの解明

  板橋貴史, 太田晴久, 天野薫

  文部科学省, 昭和大学 文理融合型の共同研究, 東京大学, Sep. 2022 - Mar. 2026, Principal investigator


• 簡便な脳活動・生体情報計測に基づく集中状態の視覚化

  山下 歩

  日本学術振興会, 科学研究費助成事業, 研究活動スタート支援, 東京大学, 31 Aug. 2022 - 31 Mar. 2024

  本研究の目的は，情報学と認知神経科学に基づいて集中状態を可視化・定量化する技術を開発し，あらゆるヒトの生活の質を向上させることである。この目的を達成するために，脳活動のみから定義した集中状態と自律神経系の活動の相互関係を明らかにし，ウェアラブルデバイスで計測した生体情報から集中状態を視覚化する基礎技術を開発する。 令和4年度は，核磁気共鳴機能画像法よりも簡便に脳活動を計測できるEEG脳波計を用いて持続的注意課題を行っている際の脳活動及び複数の自律神経系の生体情報を同時に計測し，脳活動と生体情報の関連を調査した。持続的注意課題はgradual onset continuous performance task（gradCPT）を用いた。この課題は、反応時間の時間的変動によって注意状態を定義することができる認知課題である。生体情報は，視線計測，瞳孔径，心拍，皮膚電位活動，呼吸の計測を行った。gradCPT中のEEG脳波活動に対してenergy landscape analysisを適用することで安定的な脳状態を推定し、行動課題成績や生体情報との関係を検討した。その結果，安定的な脳状態は脳波の一過性のパターン化された準安定状態であるマイクロステートに類似していることがわかった。マイクロステートは、その空間的なパターンからマイクロステートA～Dと呼ばれ、それぞれ左右の後頭部、後頭葉、頭頂部の活動によって特徴づけられる。本研究では，実験協力者がマイクロステートDに近い脳状態にあるとき、反応時間の分散はより大きく、視覚感度はより低くなった。また、この状態では瞳孔の変動が大きくなっており，一般的な注意状態を表していると考えられる。本研究では，脳活動のみから行動課題成績や生体情報と関連する状態を推定できることが示され，生体情報のみを用いて注意状態を推定可能であることが示された。


• 縦断的MRIデータに基づく成人期気分障害と関連疾患の神経回路の解明

  岡田剛, 橋本亮太, 清水栄司

  国立研究開発法人日本医療研究開発機構, 戦略的国際脳科学研究推進プログラム, Apr. 2022 - Mar. 2024, Coinvestigator


• 精神疾患の次世代治療法に繋がるｆＭＲＩニューロフィードバックトレーニングの開発

  山下 歩

  日本学術振興会, 科学研究費助成事業 特別研究員奨励費, 特別研究員奨励費, 京都大学, 24 Apr. 2015 - 31 Mar. 2017

  本研究の目的は，精神疾患の次世代治療法に繋がるfMRIニューロフィードバックトレーニングの開発である．目的達成に向けて，今年度は「fMRI結合ニューロフィードバックトレーニング（結合NFB）の手法開発」及び「安静時脳機能画像データから施設が与える影響を減少させる手法を開発する研究」を行った． 「fMRI結合NFBの手法開発」では、結合NFBによる脳機能結合の変化と認知機能の変化を調査した．結合NFB実験の施行自体による副次的な影響の可能性を除外するため，脳領域間の活動の時間相関（脳機能結合）を上げる群と下げる群の2群を用意し，群間でトレーニング効果を比較した．認知機能としては持続的注意能力や抑制能力を対象とした．実験の結果，相関を上げる群と下げる群の両群において，結合NFBトレーニングにより脳機能結合が所望の方向に有意に変化した．さらに、結合NFBトレーニング前後での認知機能の変化を群間で比較したところ，認知機能の変化する方向が有意に異なっていた．すなわち、脳機能結合を操作した方向に応じて認知機能が変化したということである． 「安静時脳機能画像データから施設が与える影響を減少させる手法開発」では、実験協力者9名が12施設（東京大学病院や広島大学病院など）に出向きデータを取得するTraveling subject designで安静時脳機能画像データを取得した．このデータを用いることで、施設間で選択バイアスが統制でき純粋な測定バイアスのみを推定することが可能となる．さらに、階層ベイズに自動関連度決定事前分布を用いて測定バイアスをスパースに推定した．そして、従来の施設間の違いを補正する方法に比べて、上記で推定した測定バイアスを用いて施設間の違いを補正する方法を用いることで安静時脳機能画像に基づくうつ病バイオマーカーの精度が向上することを確認した．

• 脳回路マーカ訓練装置、脳回路マーカ訓練プログラム、脳回路マーカ訓練方法、脳回路解析サーバ、脳回路解析サービス方法、及び脳回路解析システム

  山下歩, 鳴川紗, 酒井 雄希, 川人光男, 山下宙人

  特願2025-152680, 2025

  Patent right


• 脳機能結合相関値のクラスタリング装置、脳機能結合相関値のクラスタリングシステム、脳機能結合相関値のクラスタリング方法、脳機能結合相関値の分類器プログラム、脳活動マーカー分類システムおよび脳機能結合相関値のクラスタリング分類器モデル

  柏木 雄人, 徳田 智磯, 高原 雄史, 川人 光男, 山下 歩, 山下 宙人, 酒井 雄希, 吉本 潤一郎

  特願JP2021014254, 02 Apr. 2021, 特許7365496

  Patent right


• 「統合失調スペクトラム障害に関する情報を提供するための診断支援システム、診断支援装置、診断支援方法、 及び支援プログラム」

  河島孝彦、宮田淳、村井俊哉、山下歩、川人光男、髙橋英彦

  特願2024-003782, 特開2024-003782

  Patent right


• 「脳機能結合相関値の調整方法、脳機能結合相関値の調整システム、脳活動分類器のハーモナイズ方法、脳活動分類器のハーモナイズシステム、および脳活動バイオマーカシステム」

  山下歩, 川人光男, 今水寛, 山下宙人

  特願2019-034887, 特開2020-062369, 特許6812022

  Patent right


• 「脳活動分類器のハーモナイズシステム、及び脳活動分類器プログラム」

  山下歩, 川人光男, 今水寛, 山下宙人

  特願2020-204081, 特開2021-037397, 特許7247159

  Patent right


• 「脳機能結合相関値のクラスタリング装置、脳機能結合相関値のクラスタリングシステム、脳機能結合相関値のクラスタリング方法、脳機能結合相関値の分類器プログラムおよび脳機能マーカー分類システム」

  柏木雄人, 徳田智磯, 高原雄史, 川人光男, 山下歩, 山下宙人, 酒井, 雄希, 吉本潤一郎, 岡田剛

  特願2020-123208, 特許7737099

  Patent right

• 「ＡＩが「うつ病」を高精度診断、脳の血流解析で罹患見逃さず…広島大など成功」

  Other than myself, 読売新聞オンライン, Feb. 2023, https://www.yomiuri.co.jp/science/20230213-OYT1T50098/

  Internet


• 「MRIを使ったAIうつ病診断支援法、数年内に現場に登場か」

  Other than myself, 日経メディカル, Feb. 2023, https://medical.nikkeibp.co.jp/leaf/mem/pub/report/t285/202302/578540.html

  Internet


• 「心の病も可視化 新たな治療に可能性」

  Other than myself, 毎日新聞, Jun. 2022

  Paper


• 「うつ病診断に新支援技術 脳の活動をAIで解析」

  Other than myself, 毎日新聞, Aug. 2021

  Paper


• New Study Brings Biomarkers For Depression Closer To The Clinic

  Other than myself, Forbes, Dec. 2020, https://www.forbes.com/sites/jackierocheleau/2020/12/08/new-study-brings-biomarkers-for-depression-closer-to-the-clinic/?sh=4514013836a8

  Internet


• 「うつ病を脳画像から判別、精度7割 ATRなど技術開発」

  Other than myself, 34. 日本経済新聞, Dec. 2020, https://www.nikkei.com/article/DGXZQOGG072MZ0X01C20A2000000/

  Paper


• 「ＡＴＲ、うつ病をＡＩ診断 脳回路の状態数値化」

  Other than myself, 日刊工業新聞, Dec. 2020, https://www.nikkan.co.jp/articles/view/00581014

  Paper


• 「うつ病の脳の特徴、AIで見分ける 診断の補助に」

  Other than myself, 朝日新聞, Dec. 2020, https://www.asahi.com/articles/ASND73TBHND2PLBJ002.html

  Paper


• ＭＲＩ＋ＡＩでうつ病診断 広島大など研究チーム」

  中国新聞, Dec. 2020

  Paper


• ATR×広島大 うつ病を脳画像から見分ける技術とは

  Other than myself, テレビ大阪 やさしいニュース, Dec. 2020

  Media report


• Machine Learning Identifies Brain Signature of Depression

  Other than myself, Technology Networks, Dec. 2020, https://www.technologynetworks.com/tn/news/machine-learning-identifies-brain-signature-of-depression-343725

  Internet


• Brain Imaging Could Be Used to Personalize Treatment for Major Depression

  Other than myself, Diagnostic Imaging, Dec. 2020, https://www.diagnosticimaging.com/view/brain-imaging-could-be-used-to-personalize-treatment-for-major-depression

  Internet


• うつ病を脳回路から見分ける人工知能技術を開発－ATRほか

  Myself, 医療News QLifePro, Dec. 2020, http://www.qlifepro.com/news/20201209/ai-autistic-adults.html

  Internet


• 「うつ病を脳回路から見分ける人工知能技術を開発－ATRほか」

  Other than myself, QlifePro, Sep. 2020, https://www.qlifepro.com/news/20201209/ai-autistic-adults.html

  Internet


• 「脳画像 複数施設で統一解析」

  Other than myself, 京都新聞, Apr. 2019

  Paper


• Study: Brain ‘Signatures’ of major depression may help diagnosis, treatment

  Other than myself, UPI, https://www.upi.com/Health_News/2020/12/07/Study-Brain-signatures-of-major-depression-may-help-diagnosis-treatment/9191607367747/

  Internet


• Machine Learning Identifies New Brain Network Signature of Major Depression

  Other than myself, Neuroscience News.com, https://neurosciencenews.com/depression-machine-learning-17375/

  Internet


• うつ病の脳の特徴、AIで見分ける 診断の補助に

  Other than myself, 朝日新聞アピタル, https://www.asahi.com/articles/ASND73TBHND2PLBJ002.html

  Internet


• AIでうつ病の「脳回路マーカー」を開発 判定精度70% 保険適用視野に臨床応用へ

  Other than myself, MED IT Tech, https://medit.tech/brain-network-marker-for-depression-disease-2020/

  Internet