Automated Scoring of Nuclear Pleomorphism Spectrum with Pathologist-level Performance in Breast Cancer
This work addresses the challenge of consistent and accurate nuclear pleomorphism scoring in breast cancer grading, which is a critical component for prognosis and treatment decisions, for pathologists.
This paper developed a deep neural network to automatically score nuclear pleomorphism in breast cancer, achieving pathologist-level performance. The model was trained on diverse tumor regions and, in some experiments, utilized normal epithelium as a baseline, matching the performance of ten pathologists on regions of interest and four pathologists on whole slide images.
Nuclear pleomorphism, defined herein as the extent of abnormalities in the overall appearance of tumor nuclei, is one of the components of the three-tiered breast cancer grading. Given that nuclear pleomorphism reflects a continuous spectrum of variation, we trained a deep neural network on a large variety of tumor regions from the collective knowledge of several pathologists, without constraining the network to the traditional three-category classification. We also motivate an additional approach in which we discuss the additional benefit of normal epithelium as baseline, following the routine clinical practice where pathologists are trained to score nuclear pleomorphism in tumor, having the normal breast epithelium for comparison. In multiple experiments, our fully-automated approach could achieve top pathologist-level performance in select regions of interest as well as at whole slide images, compared to ten and four pathologists, respectively.