Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule Summary
Background: Real-time review of frozen sections underpins the quality of Mohs surgery. There is an unmet need for low-cost techniques that can improve Mohs surgery by reliably corroborating cancerous regions of interest and surgical margin proximity. Objective: To test that deep learning models can...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | JAAD International |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666328723001669 |
| _version_ | 1827347912351285248 |
|---|---|
| author | Eugene Tan, MBChB Sophie Lim, MBBS Duncan Lamont, MMed Richard Epstein, MBBS, PhD David Lim, MBChB Frank P.Y. Lin, MBChB, PhD |
| author_facet | Eugene Tan, MBChB Sophie Lim, MBBS Duncan Lamont, MMed Richard Epstein, MBBS, PhD David Lim, MBChB Frank P.Y. Lin, MBChB, PhD |
| author_sort | Eugene Tan, MBChB |
| collection | DOAJ |
| description | Background: Real-time review of frozen sections underpins the quality of Mohs surgery. There is an unmet need for low-cost techniques that can improve Mohs surgery by reliably corroborating cancerous regions of interest and surgical margin proximity. Objective: To test that deep learning models can identify nonmelanoma skin cancer regions in Mohs frozen section specimens. Methods: Deep learning models were developed on archival images of focused microscopic views (FMVs) containing regions of annotated, invasive nonmelanoma skin cancer between 2015 and 2018, then validated on prospectively collected images in a temporal cohort (2019-2021). Results: The tile-based classification models were derived using 1423 focused microscopic view images from 154 patients and tested on 374 images from 66 patients. The best models detected basal cell carcinomas with a median average precision of 0.966 and median area under the receiver operating curve of 0.889 at 100x magnification (0.943 and 0.922 at 40x magnification). For invasive squamous cell carcinomas, high median average precision of 0.904 was achieved at 100x magnification. Limitations: Single institution study with limited cases of squamous cell carcinoma and rare nonmelanoma skin cancer. Conclusion: Deep learning appears highly accurate for detecting skin cancers in Mohs frozen sections, supporting its potential for enhancing surgical margin control and increasing operational efficiency. |
| first_indexed | 2024-03-07T23:59:51Z |
| format | Article |
| id | doaj.art-82d8bbdb7bf54b45974cf48eaf3497b9 |
| institution | Directory Open Access Journal |
| issn | 2666-3287 |
| language | English |
| last_indexed | 2024-03-07T23:59:51Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | JAAD International |
| spelling | doaj.art-82d8bbdb7bf54b45974cf48eaf3497b92024-02-18T04:44:25ZengElsevierJAAD International2666-32872024-03-01143947Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule SummaryEugene Tan, MBChB0Sophie Lim, MBBS1Duncan Lamont, MMed2Richard Epstein, MBBS, PhD3David Lim, MBChB4Frank P.Y. Lin, MBChB, PhD5Western Skin Institute, Melbourne, Australia; Skintel, Auckland, New Zealand; Alfred Health, Melbourne, Australia; Correspondence to: Eugene Tan, MBChB, Department of Dermatology, Skintel, 11 Apollo Dr, Rosedale, Auckland, 0632, New Zealand.Alfred Health, Melbourne, AustraliaDepartment of Pathology, Waikato Hospital, Hamilton, New ZealandSchool of Medicine, University of New South Wales, Sydney, AustraliaSkintel, Auckland, New ZealandSchool of Medicine, University of New South Wales, Sydney, Australia; Kinghorn Centre for Clinical Genomics, Garvan Institute of Medical Research, Sydney, Australia; NHMRC Clinical Trials Centre, University of Sydney, Camperdown, NSW, AustraliaBackground: Real-time review of frozen sections underpins the quality of Mohs surgery. There is an unmet need for low-cost techniques that can improve Mohs surgery by reliably corroborating cancerous regions of interest and surgical margin proximity. Objective: To test that deep learning models can identify nonmelanoma skin cancer regions in Mohs frozen section specimens. Methods: Deep learning models were developed on archival images of focused microscopic views (FMVs) containing regions of annotated, invasive nonmelanoma skin cancer between 2015 and 2018, then validated on prospectively collected images in a temporal cohort (2019-2021). Results: The tile-based classification models were derived using 1423 focused microscopic view images from 154 patients and tested on 374 images from 66 patients. The best models detected basal cell carcinomas with a median average precision of 0.966 and median area under the receiver operating curve of 0.889 at 100x magnification (0.943 and 0.922 at 40x magnification). For invasive squamous cell carcinomas, high median average precision of 0.904 was achieved at 100x magnification. Limitations: Single institution study with limited cases of squamous cell carcinoma and rare nonmelanoma skin cancer. Conclusion: Deep learning appears highly accurate for detecting skin cancers in Mohs frozen sections, supporting its potential for enhancing surgical margin control and increasing operational efficiency.http://www.sciencedirect.com/science/article/pii/S2666328723001669artificial intelligencebasal cell carcinomadeep learningdigital pathologyMohs micrographic surgerysquamous cell carcinoma |
| spellingShingle | Eugene Tan, MBChB Sophie Lim, MBBS Duncan Lamont, MMed Richard Epstein, MBBS, PhD David Lim, MBChB Frank P.Y. Lin, MBChB, PhD Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule Summary JAAD International artificial intelligence basal cell carcinoma deep learning digital pathology Mohs micrographic surgery squamous cell carcinoma |
| title | Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule Summary |
| title_full | Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule Summary |
| title_fullStr | Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule Summary |
| title_full_unstemmed | Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule Summary |
| title_short | Development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with Mohs micrographic surgeryCapsule Summary |
| title_sort | development and validation of a deep learning model for improving detection of nonmelanoma skin cancers treated with mohs micrographic surgerycapsule summary |
| topic | artificial intelligence basal cell carcinoma deep learning digital pathology Mohs micrographic surgery squamous cell carcinoma |
| url | http://www.sciencedirect.com/science/article/pii/S2666328723001669 |
| work_keys_str_mv | AT eugenetanmbchb developmentandvalidationofadeeplearningmodelforimprovingdetectionofnonmelanomaskincancerstreatedwithmohsmicrographicsurgerycapsulesummary AT sophielimmbbs developmentandvalidationofadeeplearningmodelforimprovingdetectionofnonmelanomaskincancerstreatedwithmohsmicrographicsurgerycapsulesummary AT duncanlamontmmed developmentandvalidationofadeeplearningmodelforimprovingdetectionofnonmelanomaskincancerstreatedwithmohsmicrographicsurgerycapsulesummary AT richardepsteinmbbsphd developmentandvalidationofadeeplearningmodelforimprovingdetectionofnonmelanomaskincancerstreatedwithmohsmicrographicsurgerycapsulesummary AT davidlimmbchb developmentandvalidationofadeeplearningmodelforimprovingdetectionofnonmelanomaskincancerstreatedwithmohsmicrographicsurgerycapsulesummary AT frankpylinmbchbphd developmentandvalidationofadeeplearningmodelforimprovingdetectionofnonmelanomaskincancerstreatedwithmohsmicrographicsurgerycapsulesummary |