Intraoperative AI‐assisted early prediction of parathyroid and ischemia alert in endoscopic thyroid surgery

Author:

Wang Bo1ORCID,Yu Jia‐Fan1ORCID,Lin Si‐Ying1ORCID,Li Yi‐Jian2,Huang Wen‐Yu1ORCID,Yan Shou‐Yi1ORCID,Wang Si‐Si1ORCID,Zhang Li‐Yong1ORCID,Cai Shao‐Jun1ORCID,Wu Si‐Bin1ORCID,Li Meng‐Yao1ORCID,Wang Ting‐Yi3ORCID,Abdelhamid Ahmed Amr H.4ORCID,Randolph Gregory W.45ORCID,Chen Fei2,Zhao Wen‐Xin16ORCID

Affiliation:

1. Department of Thyroid Surgery Fujian Medical University Union Hospital Fuzhou China

2. College of Computer and Data Science Fuzhou University Fuzhou China

3. Department of Leading Cadre The First Affiliated Hospital of Fujian Medical University Fuzhou China

4. Division of Thyroid and Parathyroid Endocrine Surgery, Department of Otolaryngology – Head and Neck Surgery, Massachusetts Eye and Ear Infirmary Harvard Medical School Boston Massachusetts USA

5. Department of Surgery, Massachusetts General Hospital Harvard Medical School Boston Massachusetts USA

6. Clinical Research Center for Precision Management of Thyroid Cancer of Fujian Province Fuzhou China

Abstract

AbstractBackgroundThe preservation of parathyroid glands is crucial in endoscopic thyroid surgery to prevent hypocalcemia and related complications. However, current methods for identifying and protecting these glands have limitations. We propose a novel technique that has the potential to improve the safety and efficacy of endoscopic thyroid surgery.PurposeOur study aims to develop a deep learning model called PTAIR 2.0 (Parathyroid gland Artificial Intelligence Recognition) to enhance parathyroid gland recognition during endoscopic thyroidectomy. We compare its performance against traditional surgeon‐based identification methods.Materials and methodsParathyroid tissues were annotated in 32 428 images extracted from 838 endoscopic thyroidectomy videos, forming the internal training cohort. An external validation cohort comprised 54 full‐length videos. Six candidate algorithms were evaluated to select the optimal one. We assessed the model's performance in terms of initial recognition time, identification duration, and recognition rate and compared it with the performance of surgeons.ResultsUtilizing the YOLOX algorithm, we developed PTAIR 2.0, which demonstrated superior performance with an AP50 score of 92.1%. The YOLOX algorithm achieved a frame rate of 25.14 Hz, meeting real‐time requirements. In the internal training cohort, PTAIR 2.0 achieved AP50 values of 94.1%, 98.9%, and 92.1% for parathyroid gland early prediction, identification, and ischemia alert, respectively. Additionally, in the external validation cohort, PTAIR outperformed both junior and senior surgeons in identifying and tracking parathyroid glands (p < 0.001).ConclusionThe AI‐driven PTAIR 2.0 model significantly outperforms both senior and junior surgeons in parathyroid gland identification and ischemia alert during endoscopic thyroid surgery, offering potential for enhanced surgical precision and patient outcomes.

Funder

Fujian Provincial Health Technology Project

Publisher

Wiley

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3