Summary of Ressurv: Cancer Survival Analysis Prediction Model Based on Residual Networks, by Wankang Zhai
ResSurv: Cancer Survival Analysis Prediction Model Based on Residual Networks
by Wankang Zhai
First submitted to arxiv on: 11 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Applications (stat.AP)
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 ResSurv framework combines the Cox proportional hazards method with Deep Residual Learning to predict survival risk through TCGA genomics data. This approach addresses overfitting issues with deep learning models when dealing with high-throughput data by incorporating normalization layers in each ResNet Block. The model’s loss function is based on the semi-parametric partial likelihood model, and ablation experiments demonstrate its effectiveness in extracting high-dimensional features. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new framework called ResSurv predicts survival risk using TCGA genomics data. It combines ideas from Cox proportional hazards and Deep Residual Learning to overcome overfitting issues with deep learning models. The framework uses normalization layers to prevent gradient disappearance and explosion, and its loss function is based on the partial likelihood model. The result is a model that can extract high-dimensional features and reach state-of-the-art performance in survival prediction. |
Keywords
» Artificial intelligence » Deep learning » Likelihood » Loss function » Overfitting » Resnet
