Nishiya Yukio, Matsuura Kazuto, Ogane Tateo, Hayashi Kazuyuki, Kinebuchi Yumi, Tanaka Hirotaka, Okano Wataru, Tomioka Toshifumi, Shinozaki Takeshi, Hayashi Ryuichi
Department of Head and Neck Surgery National Cancer Center Hospital East Chiba Japan.
Department of Otolaryngology The Jikei University School of Medicine Tokyo Japan.
Laryngoscope Investig Otolaryngol. 2024 Dec 5;9(6):e70049. doi: 10.1002/lio2.70049. eCollection 2024 Dec.
We investigate the feasibility of using artificial intelligence (AI) to identify the recurrent laryngeal nerve (RLN) during endoscopic thyroid surgery and evaluated its accuracy.
In this retrospective study, we develop an AI model using a dataset of endoscopic thyroid surgery videos, including hemithyroidectomy procedures performed between April 2019 and September 2023 at the National Cancer Center Hospital East, Chiba, Japan. Semantic segmentation deep learning methods were applied to analyze the endoscopic thyroid surgery videos.
Forty endoscopic thyroid surgery videos, all in high definition or better quality, were analyzed. The Dice values were 0.351, 0.568, and 0.746 for the inferior thyroid artery, RLN, and trachea, respectively. Data augmentation was performed by cropping, standardizing, and resizing to reduce false positives and improve accuracy.
The AI model showed high recognition accuracy of the RLN and trachea. This method holds potential for assisting in future cervical gasless endoscopic surgeries.
我们研究了在内镜甲状腺手术中使用人工智能（AI）识别喉返神经（RLN）的可行性，并评估其准确性。
在这项回顾性研究中，我们使用内镜甲状腺手术视频数据集开发了一个AI模型，该数据集包括2019年4月至2023年9月在日本千叶国立癌症中心东医院进行的半甲状腺切除术。应用语义分割深度学习方法分析内镜甲状腺手术视频。
分析了40个内镜甲状腺手术视频，所有视频质量均为高清或更高。甲状腺下动脉、喉返神经和气管的Dice值分别为0.351、0.568和0.746。通过裁剪、标准化和调整大小进行数据增强，以减少假阳性并提高准确性。
AI模型对喉返神经和气管显示出较高的识别准确性。该方法在未来的颈部无气内镜手术中具有辅助潜力。
