Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility study

Abstract Background We investigate the feasibility of using artificial intelligence (AI) to identify the recurrent laryngeal nerve (RLN) during endoscopic thyroid surgery and evaluated its accuracy. Methods In this retrospective study, we develop an AI model using a dataset of endoscopic thyroid sur...

Full description

Saved in:
Bibliographic Details
Main Authors: Yukio Nishiya, Kazuto Matsuura, Tateo Ogane, Kazuyuki Hayashi, Yumi Kinebuchi, Hirotaka Tanaka, Wataru Okano, Toshifumi Tomioka, Takeshi Shinozaki, Ryuichi Hayashi
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Laryngoscope Investigative Otolaryngology
Subjects:
Online Access:https://doi.org/10.1002/lio2.70049
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134911887867904
author Yukio Nishiya
Kazuto Matsuura
Tateo Ogane
Kazuyuki Hayashi
Yumi Kinebuchi
Hirotaka Tanaka
Wataru Okano
Toshifumi Tomioka
Takeshi Shinozaki
Ryuichi Hayashi
author_facet Yukio Nishiya
Kazuto Matsuura
Tateo Ogane
Kazuyuki Hayashi
Yumi Kinebuchi
Hirotaka Tanaka
Wataru Okano
Toshifumi Tomioka
Takeshi Shinozaki
Ryuichi Hayashi
author_sort Yukio Nishiya
collection DOAJ
description Abstract Background We investigate the feasibility of using artificial intelligence (AI) to identify the recurrent laryngeal nerve (RLN) during endoscopic thyroid surgery and evaluated its accuracy. Methods 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. Results 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. Conclusions The AI model showed high recognition accuracy of the RLN and trachea. This method holds potential for assisting in future cervical gasless endoscopic surgeries.
format Article
id doaj-art-9780275e5bf24b6bb71304b40ceb232e
institution OA Journals
issn 2378-8038
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Laryngoscope Investigative Otolaryngology
spelling doaj-art-9780275e5bf24b6bb71304b40ceb232e2025-08-20T02:31:36ZengWileyLaryngoscope Investigative Otolaryngology2378-80382024-12-0196n/an/a10.1002/lio2.70049Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility studyYukio Nishiya0Kazuto Matsuura1Tateo Ogane2Kazuyuki Hayashi3Yumi Kinebuchi4Hirotaka Tanaka5Wataru Okano6Toshifumi Tomioka7Takeshi Shinozaki8Ryuichi Hayashi9Department of Head and Neck Surgery National Cancer Center Hospital East Chiba JapanDepartment of Head and Neck Surgery National Cancer Center Hospital East Chiba JapanDepartment of Medical Device Innovation National Cancer Center Hospital East Chiba JapanDepartment of Medical Device Innovation National Cancer Center Hospital East Chiba JapanDepartment of Medical Device Innovation National Cancer Center Hospital East Chiba JapanCenter for Promotion of Translational Research, National Cancer Center Tokyo JapanDepartment of Head and Neck Surgery National Cancer Center Hospital East Chiba JapanDepartment of Head and Neck Surgery National Cancer Center Hospital East Chiba JapanDepartment of Head and Neck Surgery National Cancer Center Hospital East Chiba JapanDepartment of Head and Neck Surgery National Cancer Center Hospital East Chiba JapanAbstract Background We investigate the feasibility of using artificial intelligence (AI) to identify the recurrent laryngeal nerve (RLN) during endoscopic thyroid surgery and evaluated its accuracy. Methods 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. Results 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. Conclusions The AI model showed high recognition accuracy of the RLN and trachea. This method holds potential for assisting in future cervical gasless endoscopic surgeries.https://doi.org/10.1002/lio2.70049artificial intelligencedeep learningendoscopic thyroid surgeryrecurrent laryngeal nervethyroidectomy
spellingShingle Yukio Nishiya
Kazuto Matsuura
Tateo Ogane
Kazuyuki Hayashi
Yumi Kinebuchi
Hirotaka Tanaka
Wataru Okano
Toshifumi Tomioka
Takeshi Shinozaki
Ryuichi Hayashi
Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility study
Laryngoscope Investigative Otolaryngology
artificial intelligence
deep learning
endoscopic thyroid surgery
recurrent laryngeal nerve
thyroidectomy
title Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility study
title_full Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility study
title_fullStr Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility study
title_full_unstemmed Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility study
title_short Anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery: A single‐center feasibility study
title_sort anatomical recognition artificial intelligence for identifying the recurrent laryngeal nerve during endoscopic thyroid surgery a single center feasibility study
topic artificial intelligence
deep learning
endoscopic thyroid surgery
recurrent laryngeal nerve
thyroidectomy
url https://doi.org/10.1002/lio2.70049
work_keys_str_mv AT yukionishiya anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT kazutomatsuura anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT tateoogane anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT kazuyukihayashi anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT yumikinebuchi anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT hirotakatanaka anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT wataruokano anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT toshifumitomioka anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT takeshishinozaki anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy
AT ryuichihayashi anatomicalrecognitionartificialintelligenceforidentifyingtherecurrentlaryngealnerveduringendoscopicthyroidsurgeryasinglecenterfeasibilitystudy