Summary of Survmamba: State Space Model with Multi-grained Multi-modal Interaction For Survival Prediction, by Ying Chen et al.
SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival Prediction
by Ying Chen, Jiajing Xie, Yuxiang Lin, Yuhang Song, Wenxian Yang, Rongshan Yu
First submitted to arxiv on: 11 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
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 This paper proposes a novel method called SurvMamba for survival prediction by combining pathological images with genomic data. Existing approaches have not fully utilized the hierarchical structure within both whole slide images (WSIs) and transcriptomic data, which can lead to better representations and integration. The study introduces Mamba, a structured state space model that performs well in modeling long sequences with low complexity. SurvMamba is implemented with two modules: Hierarchical Interaction Mamba (HIM), which captures local features and global representations, and Interaction Fusion Mamba (IFM), which fuses inter-modal features for survival prediction. The authors conduct comprehensive evaluations on five TCGA datasets, demonstrating that SurvMamba outperforms existing methods in terms of performance and computational cost. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using special computer models to help doctors predict how well patients with cancer will do over time. They’re combining images of the cancer tissue with genetic information to make more accurate predictions. The current approaches aren’t taking full advantage of the different levels of detail in these two types of data, which can lead to better results. The researchers introduce a new model called SurvMamba that does this better. It has two parts: one that looks at local details and global patterns in the images, and another that combines the genetic information with the image-based predictions. They tested their method on several datasets and found it works better than other approaches. |
