Summary of Omg-net: a Deep Learning Framework Deploying Segment Anything to Detect Pan-cancer Mitotic Figures From Haematoxylin and Eosin-stained Slides, by Zhuoyan Shen et al.
OMG-Net: A Deep Learning Framework Deploying Segment Anything to Detect Pan-Cancer Mitotic Figures from Haematoxylin and Eosin-Stained Slides
by Zhuoyan Shen, Mikael Simard, Douglas Brand, Vanghelita Andrei, Ali Al-Khader, Fatine Oumlil, Katherine Trevers, Thomas Butters, Simon Haefliger, Eleanna Kara, Fernanda Amary, Roberto Tirabosco, Paul Cool, Gary Royle, Maria A. Hawkins, Adrienne M. Flanagan, Charles-Antoine Collins Fekete
First submitted to arxiv on: 17 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed AI-aided approach detects mitotic figures (MFs) in digitized haematoxylin and eosin-stained whole slide images (WSIs), addressing the limitations of current manual methods. A two-stage framework, OMG-Net, combines the Segment Anything Model (SAM) for contouring MFs and an adapted ResNet18 for classification. The model achieves an F1-score of 0.84 on pan-cancer MF detection, outperforming previous state-of-the-art models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study uses AI to help doctors identify mitotic figures in cancer cells, which is important for grading different types of cancer. A big problem with current methods is that they’re time-consuming and prone to mistakes. To address this, researchers created a new AI model that can automatically detect mitotic figures in digital images of cancer cells. The model is more accurate than previous ones and can be used to help diagnose and treat different types of cancer. |
Keywords
» Artificial intelligence » Classification » F1 score » Sam
