Multimodal brain tumor classification

TL;DR

This paper presents a deep learning approach that combines histopathological slides and MRI images for brain tumor classification, demonstrating high accuracy on a challenging unbalanced dataset.

Contribution

It introduces a modular, generic architecture for multimodal tumor classification and provides an off-the-shelf Docker implementation for reproducibility.

Findings

Achieved balanced accuracy of 0.913 in cross-validation

Reported high F1 score of 0.951 on validation

Provided accessible Docker models for research use

Abstract

Cancer is a complex disease that provides various types of information depending on the scale of observation. While most tumor diagnostics are performed by observing histopathological slides, radiology images should yield additional knowledge towards the efficacy of cancer diagnostics. This work investigates a deep learning method combining whole slide images and magnetic resonance images to classify tumors. In particular, our solution comprises a powerful, generic and modular architecture for whole slide image classification. Experiments are prospectively conducted on the 2020 Computational Precision Medicine challenge, in a 3-classes unbalanced classification task. We report cross-validation (resp. validation) balanced-accuracy, kappa and f1 of 0.913, 0.897 and 0.951 (resp. 0.91, 0.90 and 0.94). For research purposes, including reproducibility and direct performance comparisons, our finale submitted models are usable off-the-shelf in a Docker image available at https://hub.docker.com/repository/docker/marvinler/cpm_2020_marvinler.