Summary of Scmil: Sparse Context-aware Multiple Instance Learning For Predicting Cancer Survival Probability Distribution in Whole Slide Images, by Zekang Yang and Hong Liu and Xiangdong Wang
SCMIL: Sparse Context-aware Multiple Instance Learning for Predicting Cancer Survival Probability Distribution in Whole Slide Images
by Zekang Yang, Hong Liu, Xiangdong Wang
First submitted to arxiv on: 30 Jun 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 paper proposes a Sparse Context-aware Multiple Instance Learning (SCMIL) framework for predicting cancer survival probability distributions from Whole Slide Image (WSI). The method innovatively segments patches into clusters based on morphological features and spatial location information, using sparse self-attention to discern relationships between patches. A learnable patch filtering module called SoftFilter ensures that only task-relevant interactions are considered. To enhance clinical relevance, the paper proposes a register-based mixture density network for forecasting individual patient survival probability distributions. The authors evaluate SCMIL on two public WSI datasets from TCGA and demonstrate improved performance over current state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses computer vision to help doctors predict how well cancer patients will do after treatment. It looks at very small parts of a tumor, called patches, and tries to figure out which ones are important for making predictions. The method is better than others at doing this and can also give more helpful information about why the predictions were made. |
Keywords
» Artificial intelligence » Probability » Self attention
