Deep learning models for histologic grading of breast cancer and association with disease prognosis

Abstract

Histologic grading of breast cancer involves review and scoring of three well-established morphologic features: mitotic count, nuclear pleomorphism, and tubule formation. Taken together, these features form the basis of the Nottingham Grading System which is used to inform breast cancer characterization and prognosis. In this study, we develop deep learning models to perform histologic scoring of all three components using digitized hematoxylin and eosin-stained slides containing invasive breast carcinoma. We first evaluate model performance using pathologist-based reference standards for each component. To complement this typical approach to evaluation, we further evaluate the deep learning models via prognostic analyses. The individual component models perform at or above published benchmarks for algorithm-based grading approaches, achieving high concordance rates with pathologist grading. Further, prognostic performance using deep learning-based grading is on par with that of pathologists performing review of matched slides. By providing scores for each component feature, the deep-learning based approach also provides the potential to identify the grading components contributing most to prognostic value. This may enable optimized prognostic models, opportunities to improve access to consistent grading, and approaches to better understand the links between histologic features and clinical outcomes in breast cancer.

Development and prognostic validation of a three-level NHG-like deep learning-based model for histological grading of breast cancer

“…An alternative approach to the modelling problem would be to attempt to reduce label noise, which could be achieved by e.g. utilising consensus labels assigned by a set of assessors as performed in (12). However, such attempts remain challenging due to the number of resources required and the shortage of pathologists available in most parts of the world.…”

“…Previously models for the classification of grades 1 and 2 (together) vs. grade 3 have been implemented for breast cancer (10,11). Jaroensri et al implemented a model that classified the sub-components, and the sub-component score, for breast cancer histological grading and the prognostic performance was compared against routine classification (12). Wang et al developed a model based on histological grade morphology in breast cancer that was applied to improve risk stratification of intermediate-risk patients (histological grade 2) (13).…”

Deep Learning Allows Assessment of Risk of Metastatic Relapse from Invasive Breast Cancer Histological Slides

“…Contrary to other digital pathology approaches predicting morphological features, such as histological grade or KI67 index that are ultimately indirectly linked to prognosis (36),(37),(38),(39), we trained our AI model to directly predict the MFS. Not only did we not require local annotations to train the algorithm, which takes as input the entire WSI, but our prediction task was directly addressing our clinical question, i.e.…”

Latent transcriptional programs reveal histology-encoded tumor features spanning tissue origins

“…Recent studies have shown that machine learning methods can use tumor histology to predict key disease characteristics, including grade [36][37][38] , immune infiltration [39][40][41] , HPV status 42 , mutation status 19,[43][44][45] , expression of individual genes 20,46,47 , and established multi-omic features 41 , but have not attempted to predict de novo learned, complex transcriptional features, such as our CLFs. To assess whether and how each CLF was histologically encoded, we trained a deep learning network to predict binarized CLF status (high or low) from tumor histology images (Fig.…”