Summary of Selector: Heterogeneous Graph Network with Convolutional Masked Autoencoder For Multimodal Robust Prediction Of Cancer Survival, by Liangrui Pan et al.
SELECTOR: Heterogeneous graph network with convolutional masked autoencoder for multimodal robust prediction of cancer survival
by Liangrui Pan, Yijun Peng, Yan Li, Xiang Wang, Wenjuan Liu, Liwen Xu, Qingchun Liang, Shaoliang Peng
First submitted to arxiv on: 14 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); 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 introduces SELECTOR, a novel heterogeneous graph-aware network for predicting cancer patient survival. The multimodal prediction approach addresses challenges in missing data and information interaction within modalities. SELECTOR comprises four modules: feature edge reconstruction, convolutional mask encoder, feature cross-fusion, and multimodal survival prediction. Initially, the meta-path method is used to reconstruct features from graph edges, followed by a convolutional masked autoencoder (CMAE) to process the heterogeneous graph. The feature cross-fusion module facilitates communication between modalities. Experiments on six cancer datasets demonstrate that SELECTOR outperforms state-of-the-art methods in both modality-missing and intra-modality information-confirmed cases. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to predict how well people with cancer will do after treatment. The current ways of predicting this are not very accurate, especially when there is missing data or different types of information. The new method, called SELECTOR, uses a special kind of computer program that can handle these problems. It looks at all the different pieces of information about each patient and combines them to make a more accurate prediction. In tests with real cancer patients’ data, SELECTOR was much better than other methods at predicting how well people would do. |
Keywords
* Artificial intelligence * Autoencoder * Encoder * Mask
