3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

Abstract

Automated grading systems using deep convolution neural networks (DCNNs) have proven their capability and potential to distinguish between different breast cancer grades using digitized histopathological images. In digital breast pathology, it is vital to measure how confident a DCNN is in grading using a machine-confidence metric, especially with the presence of major computer vision challenging problems such as the high visual variability of the images. Such a quantitative metric can be employed not only to improve the robustness of automated systems, but also to assist medical professionals in identifying complex cases. In this paper, we propose Entropy-based Elastic Ensemble of DCNN models (3E-Net) for grading invasive breast carcinoma microscopy images which provides an initial stage of explainability (using an uncertainty-aware mechanism adopting entropy). Our proposed model has been designed in a way to (1) exclude images that are less sensitive and highly uncertain to our ensemble model and (2) dynamically grade the non-excluded images using the certain models in the ensemble architecture. We evaluated two variations of 3E-Net on an invasive breast carcinoma dataset and we achieved grading accuracy of 96.15% and 99.50%.

Uncertainty-informed deep learning models enable high-confidence predictions for digital histopathology

“…In general, high uncertainty is associated with misclassification or poorer quality segmentation, a phenomenon potentially exploitable for isolating a subset of highconfidence predictions. However, consistent with previous observations in the broader machine learning literature 22,23,39,40 , uncertainty estimates were susceptible to domain shift when applied to external datasets 36,37 , raising concerns about generalizability.…”

“…The utility of these UQ methods has been explored for various applications in digital histopathology, including segmentation [1][2][3]6,32 , classification [32][33][34][35][36][37][38] , and dataset curation 32,38 . In general, high uncertainty is associated with misclassification or poorer quality segmentation, a phenomenon potentially exploitable for isolating a subset of highconfidence predictions.…”

“…A limitation in the above studies is the method of assessing the reliability of uncertainty estimates in the face of observed domain shift. Several groups explored UQ thresholds to enable highconfidence predictions on low-uncertainty data, abstaining from predictions for high-uncertainty data [33][34][35]37 . In each of these approaches, however, thresholds were manually determined when the distribution of uncertainty in validation data was known, constituting a form of data leakage.…”

BM-Net: CNN-Based MobileNet-V3 and Bilinear Structure for Breast Cancer Detection in Whole Slide Images

“…An essential step in managing breast cancer is WSI diagnosis, which provides guidelines for treatment [ 2 ]. Traditionally, pathologists evaluate hematoxylin and eosin (H&E) staining slides to generate a diagnosis and breast cancer grading result [ 3 , 4 ]. Due to the high spatial resolution, pathologists spend more time evaluating a whole slide image (WSI) than other medical images.…”

“…In the end, this method achieved an accuracy of 98.5%. Senousy et al [ 4 ] utilized an entropy-based elastic ensemble of deep convolutional neural networks to divide breast cancer into three invasiveness grades, achieving a grading accuracy of 96.15%. In summary, many deep learning engineers utilize patches as research objects.…”