Deep learning-based approach to reveal tumor mutational burden status from whole slide images across multiple cancer types

TL;DR

This study introduces a multi-scale deep learning framework that predicts tumor mutational burden from routine whole slide images across various cancers, achieving high accuracy and generalization, potentially aiding immunotherapy decisions in resource-limited settings.

Contribution

The paper presents a novel multi-scale deep learning model for TMB prediction from whole slide images, outperforming single-scale models and demonstrating cross-cohort robustness.

Findings

Achieved mean AUC of 0.818 in cross-validation

Outperformed single-scale models and other methods

Generalized well with AUC of 0.732 on external data

Abstract

Tumor mutational burden (TMB) is a potential genomic biomarker of immunotherapy. However, TMB detected through whole exome sequencing lacks clinical penetration in low-resource settings. In this study, we proposed a multi-scale deep learning framework to address the detection of TMB status from routinely used whole slide images for a multiple cancer TMB prediction model (MC- TMB). The MC-TMB achieved a mean area under the curve (AUC) of 0.818 (0.804-0.831) in the cross-validation cohort, which showed superior performance to each single-scale model. The improvements of MC-TMB over the single-tumor models were also confirmed by the ablation tests on x10 magnification, and the highly concerned regions typically correspond to dense lymphocytic infiltration and heteromorphic tumor cells. MC-TMB algorithm also exhibited good generalization on the external validation cohort with an AUC of 0.732 (0.683-0.761), and better performance when compared to other methods. In conclusion, we proposed a deep learning-based approach to reveal tumor mutational burden status from routinely used pathological slides across multiple cancer types.