Intraoperative AI‐assisted early prediction of parathyroid and ischemia alert in endoscopic thyroid surgery
Head & Neck · 2024
DOI: 10.1002/hed.27629 ↗Kurz gefasst
Fachartikel in der Zeitschrift Head & Neck, 2024. Verfasst von Bo Wang und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thyroid Surgery, Fujian Medical University Union Hospital, Fuzhou, China. Hauptthemen laut MEDLINE: Thyroidectomy, Endoscopy, Parathyroid Glands. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: Innovation of Science and Technology, Fujian Province, Fujian Provincial Health Technology Project, Fujian Provincial Finance Project.
Abstract (Originalsprache)
Background
The 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.
Purpose
Our 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 methods Parathyroid 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.
Results
Utilizing 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).
Conclusion
The 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Thyroid Surgery, Fujian Medical University Union Hospital, Fuzhou, China.
- College of Computer and Data Science, Fuzhou University, Fuzhou, China.
- Department of Leading Cadre, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
- 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.
- Department of Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Clinical Research Center for Precision Management of Thyroid Cancer of Fujian Province, Fuzhou, China.
ORCID-Profile: Bo Wang, Jia-Fan Yu, Si-Ying Lin, Wen-Yu Huang, Shou-Yi Yan, Si-Si Wang, Li-Yong Zhang, Shao-Jun Cai, Si-Bin Wu, Meng-Yao Li, Ting-Yi Wang, Amr H Abdelhamid Ahmed, Gregory W Randolph, Wen-Xin Zhao
Förderung
- Innovation of Science and Technology, Fujian Province
- Fujian Provincial Health Technology Project
- Fujian Provincial Finance Project
- Clinical Research Center for Precision Management of Thyroid Cancer of Fujian Province
Zitieren
APA
Wang, B., Yu, J. F., Lin, S. Y., Li, Y. J., Huang, W. Y., Yan, S. Y., Wang, S. S., Zhang, L. Y., Cai, S. J., Wu, S. B., Li, M. Y., Wang, T. Y., Abdelhamid Ahmed, A. H., Randolph, G. W., Chen, F., & Zhao, W. X. (2024). Intraoperative AI‐assisted early prediction of parathyroid and ischemia alert in endoscopic thyroid surgery. Head & Neck. https://doi.org/10.1002/hed.27629
Vancouver
Wang B, Yu JF, Lin SY, Li YJ, Huang WY, Yan SY, et al. Intraoperative AI‐assisted early prediction of parathyroid and ischemia alert in endoscopic thyroid surgery. Head & Neck. 2024. doi:10.1002/hed.27629
BibTeX
@article{Wang2024,
author = {Wang, Bo and Yu, Jia-Fan and Lin, Si-Ying and Li, Yi-Jian and Huang, Wen-Yu and Yan, Shou-Yi and Wang, Si-Si and Zhang, Li-Yong and Cai, Shao-Jun and Wu, Si-Bin and Li, Meng-Yao and Wang, Ting-Yi and Abdelhamid Ahmed, Amr H and Randolph, Gregory W and Chen, Fei and Zhao, Wen-Xin},
title = {Intraoperative AI‐assisted early prediction of parathyroid and ischemia alert in endoscopic thyroid surgery},
journal = {Head & Neck},
year = {2024},
doi = {10.1002/hed.27629}
}
EUVIMED