Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.12773 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910899348963328 |
|---|---|
| author | Shen, Zhuoyan Simard, Mikael Brand, Douglas Andrei, Vanghelita Al-Khader, Ali Oumlil, Fatine Trevers, Katherine Butters, Thomas Haefliger, Simon Kara, Eleanna Amary, Fernanda Tirabosco, Roberto Cool, Paul Royle, Gary Hawkins, Maria A. Flanagan, Adrienne M. Fekete, Charles-Antoine Collins |
| author_facet | Shen, Zhuoyan Simard, Mikael Brand, Douglas Andrei, Vanghelita Al-Khader, Ali Oumlil, Fatine Trevers, Katherine Butters, Thomas Haefliger, Simon Kara, Eleanna Amary, Fernanda Tirabosco, Roberto Cool, Paul Royle, Gary Hawkins, Maria A. Flanagan, Adrienne M. Fekete, Charles-Antoine Collins |
| contents | Mitotic activity is an important feature for grading several cancer types. Counting mitotic figures (MFs) is a time-consuming, laborious task prone to inter-observer variation. Inaccurate recognition of MFs can lead to incorrect grading and hence potential suboptimal treatment. In this study, we propose an artificial intelligence (AI)-aided approach to detect MFs in digitised haematoxylin and eosin-stained whole slide images (WSIs). Advances in this area are hampered by the limited number and types of cancer datasets of MFs. Here we establish the largest pan-cancer dataset of mitotic figures by combining an in-house dataset of soft tissue tumours (STMF) with five open-source mitotic datasets comprising multiple human cancers and canine specimens (ICPR, TUPAC, CCMCT, CMC and MIDOG++). This new dataset identifies 74,620 MFs and 105,538 mitotic-like figures. We then employed a two-stage framework (the Optimised Mitoses Generator Network (OMG-Net) to classify MFs. The framework first deploys the Segment Anything Model (SAM) to automate the contouring of MFs and surrounding objects. An adapted ResNet18 is subsequently trained to classify MFs. OMG-Net reaches an F1-score of 0.84 on pan-cancer MF detection (breast carcinoma, neuroendocrine tumour and melanoma), largely outperforming the previous state-of-the-art MIDOG++ benchmark model on its hold-out testing set (e.g. +16% F1-score on breast cancer detection, p<0.001) thereby providing superior accuracy in detecting MFs on various types of tumours obtained with different scanners. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12773 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OMG-Net: A Deep Learning Framework Deploying Segment Anything to Detect Pan-Cancer Mitotic Figures from Haematoxylin and Eosin-Stained Slides Shen, Zhuoyan Simard, Mikael Brand, Douglas Andrei, Vanghelita Al-Khader, Ali Oumlil, Fatine Trevers, Katherine Butters, Thomas Haefliger, Simon Kara, Eleanna Amary, Fernanda Tirabosco, Roberto Cool, Paul Royle, Gary Hawkins, Maria A. Flanagan, Adrienne M. Fekete, Charles-Antoine Collins Computer Vision and Pattern Recognition Artificial Intelligence Mitotic activity is an important feature for grading several cancer types. Counting mitotic figures (MFs) is a time-consuming, laborious task prone to inter-observer variation. Inaccurate recognition of MFs can lead to incorrect grading and hence potential suboptimal treatment. In this study, we propose an artificial intelligence (AI)-aided approach to detect MFs in digitised haematoxylin and eosin-stained whole slide images (WSIs). Advances in this area are hampered by the limited number and types of cancer datasets of MFs. Here we establish the largest pan-cancer dataset of mitotic figures by combining an in-house dataset of soft tissue tumours (STMF) with five open-source mitotic datasets comprising multiple human cancers and canine specimens (ICPR, TUPAC, CCMCT, CMC and MIDOG++). This new dataset identifies 74,620 MFs and 105,538 mitotic-like figures. We then employed a two-stage framework (the Optimised Mitoses Generator Network (OMG-Net) to classify MFs. The framework first deploys the Segment Anything Model (SAM) to automate the contouring of MFs and surrounding objects. An adapted ResNet18 is subsequently trained to classify MFs. OMG-Net reaches an F1-score of 0.84 on pan-cancer MF detection (breast carcinoma, neuroendocrine tumour and melanoma), largely outperforming the previous state-of-the-art MIDOG++ benchmark model on its hold-out testing set (e.g. +16% F1-score on breast cancer detection, p<0.001) thereby providing superior accuracy in detecting MFs on various types of tumours obtained with different scanners. |
| title | OMG-Net: A Deep Learning Framework Deploying Segment Anything to Detect Pan-Cancer Mitotic Figures from Haematoxylin and Eosin-Stained Slides |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.12773 |