Deep Interactive Learning-based ovarian cancer segmentation of H&E-stained whole slide images to study morphological patterns of BRCA mutation

TL;DR

This paper introduces a deep interactive learning approach that leverages pretrained models to efficiently segment ovarian cancer in histopathology images, enabling the study of BRCA mutation-related morphological patterns with reduced manual annotation effort.

Contribution

It proposes a novel interactive learning method using pretrained models to significantly cut down manual annotation time for cancer segmentation in whole slide images.

Findings

Achieved 0.74 IoU, 0.86 recall, 0.84 precision in ovarian cancer segmentation.

Reduced manual annotation time to 3.5 hours using pretrained models.

Provided publicly available segmentation model and code.

Abstract

Deep learning has been widely used to analyze digitized hematoxylin and eosin (H&E)-stained histopathology whole slide images. Automated cancer segmentation using deep learning can be used to diagnose malignancy and to find novel morphological patterns to predict molecular subtypes. To train pixel-wise cancer segmentation models, manual annotation from pathologists is generally a bottleneck due to its time-consuming nature. In this paper, we propose Deep Interactive Learning with a pretrained segmentation model from a different cancer type to reduce manual annotation time. Instead of annotating all pixels from cancer and non-cancer regions on giga-pixel whole slide images, an iterative process of annotating mislabeled regions from a segmentation model and training/finetuning the model with the additional annotation can reduce the time. Especially, employing a pretrained segmentation model can further reduce the time than starting annotation from scratch. We trained an accurate ovarian cancer segmentation model with a pretrained breast segmentation model by 3.5 hours of manual annotation which achieved intersection-over-union of 0.74, recall of 0.86, and precision of 0.84. With automatically extracted high-grade serous ovarian cancer patches, we attempted to train another deep learning model to predict BRCA mutation. The segmentation model and code have been released at https://github.com/MSKCC-Computational-Pathology/DMMN-ovary.