Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy
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, autom...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-93202-y |
| _version_ | 1818834642648694784 |
|---|---|
| author | 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 |
| author_facet | 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 |
| author_sort | Julia Gong |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-19T02:38:04Z |
| format | Article |
| id | doaj.art-8aaaf1d5cfdd43bc9f7aee8d04160169 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-19T02:38:04Z |
| publishDate | 2021-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-8aaaf1d5cfdd43bc9f7aee8d041601692022-12-21T20:39:17ZengNature PortfolioScientific Reports2045-23222021-07-0111111110.1038/s41598-021-93202-yUsing deep learning to identify the recurrent laryngeal nerve during thyroidectomyJulia Gong0F. Christopher Holsinger1Julia E. Noel2Sohei Mitani3Jeff Jopling4Nikita Bedi5Yoon Woo Koh6Lisa A. Orloff7Claudio R. Cernea8Serena Yeung9Department of Computer Science, Stanford UniversityDivision of Head and Neck Surgery, Department of Otolaryngology, Stanford UniversityDivision of Head and Neck Surgery, Department of Otolaryngology, Stanford UniversityDivision of Head and Neck Surgery, Department of Otolaryngology, Stanford UniversityDepartment of Surgery, Stanford UniversityDivision of Head and Neck Surgery, Department of Otolaryngology, Stanford UniversityDepartment of Head and Neck Surgery, Yonsei University School of MedicineDivision of Head and Neck Surgery, Department of Otolaryngology, Stanford UniversityDepartment of Surgery, University of São Paulo Medical SchoolDepartment of Computer Science, Stanford UniversityAbstract 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.https://doi.org/10.1038/s41598-021-93202-y |
| spellingShingle | 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 Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy Scientific Reports |
| title | Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy |
| title_full | Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy |
| title_fullStr | Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy |
| title_full_unstemmed | Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy |
| title_short | Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy |
| title_sort | using deep learning to identify the recurrent laryngeal nerve during thyroidectomy |
| url | https://doi.org/10.1038/s41598-021-93202-y |
| work_keys_str_mv | AT juliagong usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT fchristopherholsinger usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT juliaenoel usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT soheimitani usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT jeffjopling usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT nikitabedi usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT yoonwookoh usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT lisaaorloff usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT claudiorcernea usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy AT serenayeung usingdeeplearningtoidentifytherecurrentlaryngealnerveduringthyroidectomy |