9 56

Cited 0 times in

Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy

Authors
 Julia Gong  ;  F Christopher Holsinger  ;  Julia E Noel  ;  Sohei Mitani  ;  Jeff Jopling  ;  Nikita Bedi  ;  Yoon Woo Koh  ;  Lisa A Orloff  ;  Claudio R Cernea  ;  Serena Yeung 
Citation
 SCIENTIFIC REPORTS, Vol.11(1) : 14306, 2021-07 
Journal Title
SCIENTIFIC REPORTS
Issue Date
2021-07
MeSH
Deep Learning* ; Humans ; Recurrent Laryngeal Nerve / pathology ; Recurrent Laryngeal Nerve / surgery* ; Thyroid Diseases / pathology ; Thyroid Diseases / surgery* ; Thyroid Gland / pathology ; Thyroid Gland / surgery ; Thyroidectomy / methods*
Abstract
Surgeons must visually distinguish soft-tissues, such as nerves, from surrounding anatomy to prevent complications and optimize patient outcomes. An accurate nerve segmentation and analysis tool could provide useful insight for surgical decision-making. Here, we present an end-to-end, automatic deep learning computer vision algorithm to segment and measure nerves. Unlike traditional medical imaging, our unconstrained setup with accessible handheld digital cameras, along with the unstructured open surgery scene, makes this task uniquely challenging. We investigate one common procedure, thyroidectomy, during which surgeons must avoid damaging the recurrent laryngeal nerve (RLN), which is responsible for human speech. We evaluate our segmentation algorithm on a diverse dataset across varied and challenging settings of operating room image capture, and show strong segmentation performance in the optimal image capture condition. This work lays the foundation for future research in real-time tissue discrimination and integration of accessible, intelligent tools into open surgery to provide actionable insights.
Files in This Item:
T202126086.pdf Download
DOI
10.1038/s41598-021-93202-y
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Otorhinolaryngology (이비인후과학교실) > 1. Journal Papers
Yonsei Authors
Koh, Yoon Woo(고윤우)
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/190458
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links