Assessment of Breast Cancer Histology Using Densely Connected Convolutional Networks

Abstract

Breast cancer is the most frequently diagnosed cancer and leading cause of cancer-related death among females worldwide. In this article, we investigate the applicability of densely connected convolutional neural networks to the problems of histology image classification and whole slide image segmentation in the area of computer-aided diagnoses for breast cancer. To this end, we study various approaches for transfer learning and apply them to the data set from the 2018 grand challenge on breast cancer histology images (BACH).Keywords: digital pathology, breast cancer, deep learning 1. mitotic activity as a measure of cellular proliferation, 2. nuclear pleomorphism, i.e. how different the tumor cells are in comparison to normal cells, and 3. glandular and tubular differentiation, i.e. how well the tumor resembles normal structures.Current developments in the area of digital pathology are driven by the observation that genetic and phenotypic intra-tumor heterogeneity have a direct impact on both diagnosis and disease management [18] as well as the availability of effective machine learning techniques, such as deep convolutional neural networks. Particularly the segmentation of WSIs, i.e. the second part of the BACH challenge, plays an increasingly important role as it facilitates not only a standardized assessment of resection margins, but also novel scoring approaches, such as the ImmunoScore [11], and a better understanding of tumor heterogeneity and micro-environment, e.g. via phenotype-guided genetic readouts.

BACH: Grand challenge on breast cancer histology images

“…The resulting output map was then refined using a ResNet34 (He et al, 2016) to separate tissue regions from the background and regions with artifacts, reducing potential misclassifications due to ink and other artifacts in whole slide images. (Kohl et al, 2018) used an ImageNet pretrained DenseNet (Huang et al, 2017) to approach both parts of the challenge. For Part A, the 400 training images were downsampled by a factor 10 and normalized to zero mean and unit standard deviation.…”

Semi-automated analysis of digital whole slides from humanized lung-cancer xenograft models for checkpoint inhibitor response prediction

“…While digital pathology algorithms for lung-cancer WSIs are not deeply covered in literature, there is a variety of publications regarding breast cancer detection [9], grading [10, 11], and epithelial vs. stroma classification [12]. Besides the differences in organ, technical deviations exist, as [9] solves a binary classification problem (versus our eight-class problem) and [10, 11] work with ordinal data. Similar to our approach, [12] deploys a two-step processing involving deep learning feature generation and conventional classification.…”

Fine-Grained Multi-Instance Classification in Microscopy Through Deep Attention

“…Accuracy Methods Accuracy Vgg19 [10] 0.925 Inception-v3 [10] 0.913 DenseNet-161 [10] 0.940 Model Fusion [13] 0.925 AlexNet [12] 0.813 ResNet-152 [2] 0.830 RFSVM-All [2] 0.930 Ensemble [15] 0.825 Refined Ensemble [15] 0.875 Two-stage network [7] 0.850 Hybrid deep network [20] 0.913 Our method 0.970…”