# Colorectal cancer survival prediction using deep distribution based multiple-instance learning

arXiv: https://arxiv.org/abs/2204.11294 · HTML: https://mlsanity.com/paper/2204.11294/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 24 Apr 2022.

## Builds on (most cited first, 14 of 14)

- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach](https://mlsanity.com/paper/1802.02212/) (2018)
- [Interpretable Survival Prediction for Colorectal Cancer using Deep Learning](https://mlsanity.com/paper/2011.08965/) (2020)
- [Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology](https://mlsanity.com/paper/1806.05083/) (2018)
- [Improving Feature Extraction from Histopathological Images Through A Fine-tuning ImageNet Model](https://mlsanity.com/paper/2201.00636/) (2022)
- [The Concordance Index decomposition: A measure for a deeper understanding of survival prediction models](https://mlsanity.com/paper/2203.00144/) (2022)
- [Colorectal Cancer Outcome Prediction from H&E Whole Slide Images using Machine Learning and Automatically Inferred Phenotype Profiles](https://mlsanity.com/paper/1902.03582/) (2019)
- [A Retrospective Analysis using Deep-Learning Models for Prediction of Survival Outcome and Benefit of Adjuvant Chemotherapy in Stage II/III Colorectal Cancer](https://mlsanity.com/paper/2111.03532/) (2021)
- [Automatic Discovery and Optimization of Parts for Image Classification](https://mlsanity.com/paper/1412.6598/) (2014)
- [EPIC-Survival: End-to-end Part Inferred Clustering for Survival Analysis, Featuring Prognostic Stratification Boosting](https://mlsanity.com/paper/2101.11085/) (2021)
- [Hierarchical Phenotyping and Graph Modeling of Spatial Architecture in Lymphoid Neoplasms](https://mlsanity.com/paper/2106.16174/) (2021)

## Built on by (most cited first, 1 of 1)

- [Time to Embrace Natural Language Processing (NLP)-based Digital Pathology: Benchmarking NLP- and Convolutional Neural Network-based Deep Learning Pipelines](https://mlsanity.com/paper/2302.10406/) (2023)

## Abstract (arXiv)

Several deep learning algorithms have been developed to predict survival of cancer patients using whole slide images (WSIs).However, identification of image phenotypes within the WSIs that are relevant to patient survival and disease progression is difficult for both clinicians, and deep learning algorithms. Most deep learning based Multiple Instance Learning (MIL) algorithms for survival prediction use either top instances (e.g., maxpooling) or top/bottom instances (e.g., MesoNet) to identify image phenotypes. In this study, we hypothesize that wholistic information of the distribution of the patch scores within a WSI can predict the cancer survival better. We developed a distribution based multiple-instance survival learning algorithm (DeepDisMISL) to validate this hypothesis. We designed and executed experiments using two large international colorectal cancer WSIs datasets - MCO CRC and TCGA COAD-READ. Our results suggest that the more information about the distribution of the patch scores for a WSI, the better is the prediction performance. Including multiple neighborhood instances around each selected distribution location (e.g., percentiles) could further improve the prediction. DeepDisMISL demonstrated superior predictive ability compared to other recently published, state-of-the-art algorithms. Furthermore, our algorithm is interpretable and could assist in understanding the relationship between cancer morphological phenotypes and patients cancer survival risk.