Deep Learning Derived Histopathology Image Score for Increasing Phase 3 Clinical Trial Probability of Success

TL;DR

This study introduces a deep learning-based scoring method for histopathology images that improves early identification of responders in oncology trials, potentially increasing Phase 3 success rates and reducing costs.

Contribution

The paper presents a novel deep learning approach to derive digital pathology scores from immunohistochemistry images, outperforming traditional tumor proportion scores in predicting treatment response.

Findings

Deep learning score achieved 4% higher AUC-ROC than clinical benchmark.

Score showed 6% higher AUC-PR compared to tumor proportion score.

Responder rate was at least 25% higher in small independent test set.

Abstract

Failures in Phase 3 clinical trials contribute to expensive cost of drug development in oncology. To drastically reduce such cost, responders to an oncology treatment need to be identified early on in the drug development process with limited amount of patient data before the planning of Phase 3 clinical trials. Despite the challenge of small sample size, we pioneered the use of deep-learning derived digital pathology scores to identify responders based on the immunohistochemistry images of the target antigen expressed in tumor biopsy samples from a Phase 1 Non-small Cell Lung Cancer clinical trial. Based on repeated 10-fold cross validations, the deep-learning derived score on average achieved 4% higher AUC of ROC curve and 6% higher AUC of Precision-Recall curve comparing to the tumor proportion score (TPS) based clinical benchmark. In a small independent testing set of patients, we also demonstrated that the deep-learning derived score achieved numerically at least 25% higher responder rate in the enriched population than the TPS clinical benchmark.