SEARCH

Search Details

YAMASHITA Toshihiko
University Hospital / Otorhinolaryngology-Head and Neck Surgery
Assistant Professor

Research activity information

■ Paper
  • 岩城 忍, 四宮 弘隆, 山下 俊彦, 堀地 祐人, 丹生 健一
    日本音声言語医学会, Apr. 2026, 音声言語医学, 67(2) (2), 147 - 155, Japanese

  • Ryunosuke Ueno, Takeshi Fujita, Kazuhiro Matsui, Keita Atsuumi, Natsumi Uehara, Toshihiko Yamashita, Hiroaki Hirai, Toshikazu Kawai, Hisashi Suzuki, Atsushi Nishikawa
    BACKGROUND: Accurate automatic recognition of surgical instruments is important for enhancing the safety and efficiency of transcanal endoscopic ear surgery (TEES). Segment Anything Model 2 (SAM 2) is a state-of-the-art artificial intelligence (AI) model featuring "zero-shot segmentation", which allows it to identify objects without extensive training data. The purpose of this study was to be the first to apply SAM 2 to TEES videos to evaluate its performance in segmenting and classifying surgical instruments. METHODS: From videos of three clinical TEES cases (tympanoplasty), we created a 684-frame evaluation video that simulated the sequential use of four types of surgical instruments: cupped forceps, pick, alligator forceps, and circular knife. SAM 2 was instructed to identify the instruments using only 12 reference images. Performance was quantitatively evaluated using four metrics-Precision, Recall, dice similarity coefficient (DSC), and intersection over union (IoU)-as well as a confusion matrix to assess frame-level classification accuracy by comparing the model's output to manually created ground-truth annotations. RESULTS: For segmentation without classification, SAM 2 demonstrated excellent performance, with a mean Precision of 0.98, a mean Recall of 0.89, a mean DSC of 0.93, and a mean IoU of 0.87. When classifying the four specific instrument types, performance varied, with mean Precision ranging from 0.68 to 0.98, mean Recall from 0.79 to 0.86, mean DSC from 0.62 to 0.89, and mean IoU from 0.58 to 0.84. Notably, false-positive detections in non-instrument regions were extremely rare. A trend of lower classification accuracy was observed for articulating instruments with moving parts (cupped forceps and alligator forceps). CONCLUSIONS: This study demonstrated that SAM 2 can accurately identify surgical instruments in TEES videos without the need to prepare large, costly training datasets. This zero-shot segmentation characteristic significantly lowers the barrier to clinical implementation of AI, suggesting it is a promising foundational technology for future surgical navigation and robotic automation. Key future challenges include improving classification accuracy for articulating instruments and accelerating processing speed for practical, real-time use.
    Dec. 2025, Quantitative imaging in medicine and surgery, 15(12) (12), 12386 - 12397, English, International magazine
    Scientific journal

  • Toshihiko Yamashita, Hirotaka Shinomiya, Ken-ichi Nibu
    Aug. 2025, Auris Nasus Larynx
    Scientific journal

  • Takeshi Fujita, Kenta Yokoyama, Toshikazu Kawai, Natsumi Uehara, Toshihiko Yamashita, Takefumi Kamakura, Yu Matsumoto, Kunio Mizutari, Akinobu Kakigi, Ken-ichi Nibu, Hisashi Suzuki, Atsushi Nishikawa
    2025, ADVANCED BIOMEDICAL ENGINEERING, 14, 146 - 154, English
    Scientific journal

  • 横井 純, 藤田 岳, 山下 俊彦, 柿木 章伸, 丹生 健一
    (一社)日本めまい平衡医学会, Oct. 2024, Equilibrium Research, 83(5) (5), 396 - 396, Japanese

  • Influences of Orogastric and Nasogastric Tubes on Sucking Pressure during Bottle Feeding in Immature Infants.
    Takeshi Komatsu, Tatsuya Furukawa, Daisuke Kobayashi, Sota Iwatani, Seiji Yoshimoto, Toshihiko Yamashita, Yumi Endo, Sayaka Katsunuma, Masahide Otsu, Ken-Ichi Nibu
    Orogastric (OG) and nasogastric (NG) tubes have been reported to delay breastfeeding initiation and affect respiratory function. However, the effects of feeding tubes on sucking pressure have not been well studied. Fourteen preterm infants were enrolled in this study, and their sucking pressures during bottle feeding with an OG tube, NG tube, and without any tube were measured. Sucking pressure significantly increased after changing the OG tube to an NG tube (p = 0.044). However, sucking pressure showed no significant differences after changing the feeding method from an NG tube to oral intake. Thus, NG tubes are superior to OG tubes in terms of sucking pressure.
    May 2023, The Kobe journal of medical sciences, 69(1) (1), E25-E32, English, Domestic magazine
    Scientific journal

  • 藤田 岳, 上原 奈津美, 山下 俊彦, 西川 敦, 河合 俊和, 鈴木 寿, 横井 純, 柿木 章伸, 丹生 健一
    頭頸部外科領域にロボット手術が保険適応となり, 耳鼻咽喉科医にとってもロボット手術は身近な存在となってきた. しかし泌尿器・消化器領域で発展してきた手術ロボットを, そのまま耳や鼻の手術に応用することはまだ難しい. 私達は経外耳道的内視鏡下耳科手術 (Trans-canal Endoscopic Ear Surgery : TEES) を支援するロボットの研究・開発を複数の大学の工学部と共同で行っている. 手術ロボットの研究を通して, 自分たちの手術の特徴や問題点を改めて見直す機会が得られている. 本稿では, これまでの耳科手術用ロボットや内視鏡保持ロボットについて概略を述べ, 現在研究中の TEES 支援ロボットのコンセプトと試作機について述べる. また, 将来ロボット自身が自律的に手術を行うことを目標とした, ロボットの自律レベル向上に向けた研究についても紹介する.
    一般社団法人 日本耳鼻咽喉科頭頸部外科学会, Mar. 2023, 日本耳鼻咽喉科頭頸部外科学会会報, 126(3) (3), 181 - 184, Japanese
    Scientific journal

  • 山下 俊彦, 橋本 大, 藤原 肇, 茂木 千聡
    (一社)日本耳鼻咽喉科頭頸部外科学会, Aug. 2021, 日本耳鼻咽喉科頭頸部外科学会会報, 124(8) (8), 1202 - 1207, Japanese

  • 山下 俊彦, 梶本 康幸, 四宮 瞳, 大月 直樹, 丹生 健一
    (株)医学書院, May 2020, 耳鼻咽喉科・頭頸部外科, 92(6) (6), 469 - 473, Japanese

  • 山下 俊彦, 梶本 康幸, 四宮 瞳, 大月 直樹, 丹生 健一
    (株)医学書院, May 2020, 耳鼻咽喉科・頭頸部外科, 92(6) (6), 469 - 473, Japanese

■ MISC
  • 横井 純, 藤田 岳, 山下 俊彦, 上原 奈津美, 丹生 健一
    (一社)日本めまい平衡医学会, Oct. 2025, Equilibrium Research, 84(5) (5), 466 - 466, Japanese

  • 宮内 麻衣, 上原 奈津美, 横井 純, 山下 俊彦, 藤田 岳, 丹生 健一
    (一社)日本めまい平衡医学会, Oct. 2025, Equilibrium Research, 84(5) (5), 472 - 472, Japanese

  • 皮弁再建を要した口腔がん患者における舌圧と嚥下機能の関連
    高橋 美貴, 四宮 弘隆, 鷲見 麻里, 岩城 忍, 山下 俊彦, 堀地 祐人, 丹生 健一
    日本音声言語医学会, Oct. 2025, 日本音声言語医学会総会・学術講演会プログラム・抄録集, 70回, 104 - 104, Japanese

  • 日本語版CAPE-Vによる嗄声評価の信頼性に関する検討
    山下 俊彦, 堀地 祐人, 岩城 忍, 四宮 弘隆, 丹生 健一
    日本音声言語医学会, Oct. 2025, 日本音声言語医学会総会・学術講演会プログラム・抄録集, 70回, 100 - 100, Japanese

  • 担癌患者の一側性声帯麻痺に対する音声改善手術についての臨床的検討
    堀地 祐人, 山下 俊彦, 岩城 忍, 四宮 弘隆, 丹生 健一
    日本音声言語医学会, Oct. 2025, 日本音声言語医学会総会・学術講演会プログラム・抄録集, 70回, 112 - 112, Japanese

  • 頸部体表からの非侵襲な喉頭挙上距離計測についての検討
    山下俊彦, 古川竜也, 丹生健一
    2025, 日本嚥下医学会抄録(Web), 48th

  • 上岡 美和, 古川 竜也, 山下 俊彦, 高橋 美貴, 西岡 仁美, 吉川 麻里, 藤目 仁美, 丹生 健一
    (一社)日本摂食嚥下リハビリテーション学会, Dec. 2024, 日本摂食・嚥下リハビリテーション学会雑誌, 28(3) (3), S182 - S183, Japanese

  • 人工内耳症例の音楽知覚と語音聴取成績についての検討
    鷲見 麻里, 岩城 忍, 山下 俊彦, 柿木 章伸, 丹生 健一
    日本音声言語医学会, Oct. 2024, 日本音声言語医学会総会・学術講演会プログラム・抄録集, 69回, 100 - 100, Japanese

TOP