Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent

TLDR

Whole‑slide imaging has enabled rapid digitization of pathology slides, prompting development of automated algorithms to detect breast cancer extent, yet manual delineation remains critical but laborious and variable, requiring robust methods across diverse data sources. This study aimed to assess the accuracy and robustness of a deep‑learning approach for automatically delineating invasive tumor extent on digitized breast cancer slides. The authors trained a convolutional neural network on nearly 400 annotated cases from multiple sites and scanners and independently validated it on almost 200 TCGA cases. The method achieved a 75.86 % Dice coefficient, 71.62 % positive predictive value, and 96.77 % negative predictive value in pixel‑wise comparison to manual annotations of invasive ductal carcinoma.

Abstract

With the increasing ability to routinely and rapidly digitize whole slide images with slide scanners, there has been interest in developing computerized image analysis algorithms for automated detection of disease extent from digital pathology images. The manual identification of presence and extent of breast cancer by a pathologist is critical for patient management for tumor staging and assessing treatment response. However, this process is tedious and subject to inter- and intra-reader variability. For computerized methods to be useful as decision support tools, they need to be resilient to data acquired from different sources, different staining and cutting protocols and different scanners. The objective of this study was to evaluate the accuracy and robustness of a deep learning-based method to automatically identify the extent of invasive tumor on digitized images. Here, we present a new method that employs a convolutional neural network for detecting presence of invasive tumor on whole slide images. Our approach involves training the classifier on nearly 400 exemplars from multiple different sites, and scanners, and then independently validating on almost 200 cases from The Cancer Genome Atlas. Our approach yielded a Dice coefficient of 75.86%, a positive predictive value of 71.62% and a negative predictive value of 96.77% in terms of pixel-by-pixel evaluation compared to manually annotated regions of invasive ductal carcinoma.