Summary of Foresee: Multimodal and Multi-view Representation Learning For Robust Prediction Of Cancer Survival, by Liangrui Pan et al.
FORESEE: Multimodal and Multi-view Representation Learning for Robust Prediction of Cancer Survival
by Liangrui Pan, Yijun Peng, Yan Li, Yiyi Liang, Liwen Xu, Qingchun Liang, Shaoliang Peng
First submitted to arxiv on: 13 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 new end-to-end framework called FORESEE for predicting patient survival by integrating multimodal data from cancer patients. The framework utilizes features at different scales, including cellular, tissue, and tumor heterogeneity levels, through a cross-scale feature fusion method. It also employs a hybrid attention encoder to capture contextual relationships and local details in molecular data. To address missing information within modalities, the paper introduces an asymmetrically masked triplet autoencoder for reconstructing lost data. Experimental results demonstrate the superiority of FORESEE over state-of-the-art methods on four benchmark datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps doctors predict how well cancer patients will do by using lots of different types of data about them. Usually, these methods don’t consider all the important details in the pictures and tests that doctors use to diagnose cancer. This new method, called FORESEE, is better because it looks at different parts of the pictures and tests, like tiny cells or bigger pieces of tissue, to get a better understanding of what’s going on. It also uses special tools to make sure that the information from all these different sources works well together. The results show that this new method is really good at predicting patient survival. |
Keywords
» Artificial intelligence » Attention » Autoencoder » Encoder
