OMG-Octo: Uniformised large scale database of mitotic cells
-
Shen, Zhuoyan
(Researcher)1
-
Simard, Mikaël
(Researcher)1
- Brand, Douglas1, 2
- Andrei, Vanghelita3, 1
- Al-Khader, Ali3, 1
- Oumlil, Fatine3
- Trevers, Katherine1, 3
- Butters, Thomas1, 3
- Haefliger, Simon4
- Kara, Eleanna5
- Amary, Fernanda3, 1
- Tirabosco, Roberto3, 1
- Cool, Paul6, 7
- Royle, Gary1
- Hawkins, Maria A.1, 2
- Flanagan, Adrienne M.1, 3
-
Collins Fekete, Charles-Antoine
(Project leader)1
-
1.
University College London
-
2.
University College London Hospitals NHS Foundation Trust
-
3.
Royal National Orthopaedic Hospital
-
4.
University Hospital of Basel
-
5.
Rutgers, The State University of New Jersey
-
6.
Robert Jones and Agnes Hunt Orthopaedic Hospital NHS Trust
-
7.
Keele University
Description
In this study, we established a large uniform database of pan-cancer mitotic figures (MFs) by deploying the Segment Anything Model (SAM), a foundation object detection model, in five open-source datasets (ICPR, TUPAC, CCMCT, CMC, MIDOG++) using a single nuclei mask format. Manual revision of the masks was performed to maximise database quality. Then, we contributed an in-house dataset of human soft tissue tumours (STT) MFs (N=8,400) (Soft-Tissue Mitotic Figures, STMF). Although STT represents a rare tumour group, they comprise over 100 subtypes exhibiting a wide variety of histological appearances and mimic other tumours including common cancers such as melanoma, carcinoma and lymphoma. STT harbours a variable number of MFs and aids in reaching a diagnosis and predicting disease behaviour. The STMF was initiated by staining WSIs with an anti-phosphorylated histone H3 (pHH3) antibody to target MFs which was expanded and improved by AI-assisted annotations made by pathologists.
Files
image_list.csv
Additional details
Identifiers
- arXiv
- arXiv:2407.12773
Funding
Software
- Repository URL
- https://github.com/SZY1234567/OMG-Net
- Development Status
- Active