Deep learning for magnification independent breast cancer histopathology image classification

Abstract

Microscopic analysis of breast tissues is necessary for a definitive diagnosis of breast cancer which is the most common cancer among women. Pathology examination requires time consuming scanning through tissue images under different magnification levels to find clinical assessment clues to produce correct diagnoses. Advances in digital imaging techniques offers assessment of pathology images using computer vision and machine learning methods which could automate some of the tasks in the diagnostic pathology workflow. Such automation could be beneficial to obtain fast and precise quantification, reduce observer variability, and increase objectivity. In this work, we propose to classify breast cancer histopathology images independent of their magnifications using convolutional neural networks (CNNs). We propose two different architectures; single task CNN is used to predict malignancy and multi-task CNN is used to predict both malignancy and image magnification level simultaneously. Evaluations and comparisons with previous results are carried out on BreaKHis dataset. Experimental results show that our magnification independent CNN approach improved the performance of magnification specific model. Our results in this limited set of training data are comparable with previous state-of-the-art results obtained by hand-crafted features. However, unlike previous methods, our approach has potential to directly benefit from additional training data, and such additional data could be captured with same or different magnification levels than previous data.

Case-Based Histopathological Malignancy Diagnosis using Convolutional Neural Networks

“…As we are the first to use case-level and diagnosis-level accuracies, we can't compare the results for these metrics to previous results. However, based on patient-level accuracy, our case-based approach (86.36%) outperforms the multi-task CNN method (82.13%, average of four magnifications) [1] and the magnification independent single-task CNN method (83.25%, average of four magnifications) [1], and achieves a comparable performance to the best results obtained from the [20]. We further investigate the misclassified patients in terms of malignancy diagnosis for all five folds, and summarize the results as confusion matrices in Figure 4.…”

“…However, one disadvantage of this paper [20], is that four CNN classifiers have to be trained, with one classifier specialized for each of the four magnifications. Seeking to find a better solution to this problem, Bayramoglu et al [1] propose a magnification independent approach with both single-task (malignancy) and multi-task (malignancy and magnification) classification, where they ignore magnification information of the image and train a unique CNN classifier for all magnifications. Although the performance is slightly impaired, it indeed improves the efficiency.…”

Breast Cancer Histopathological Image Classification: A Deep Learning Approach

“…We combined different magnification including 40X, 100X, 200X and 400X to generate comprehensive, independent and scalable system while a large number of previous studies employed single magnification level ( [7], [30]). Several other studies ( [7], [25], [48], [4]) also investigated multiple magnifications of medical images. However, these approaches examined different classifiers for each magnification level and also had medical laboratory limitations to capture required multiple magnification to gather image training samples.…”

Deep Learning Based Analysis of Histopathological Images of Breast Cancer

“…Bayramoglu et al (2016) proposed to classify breast cancer histopathological images independently of their magnifications using CNN (convolutional neural networks). They proposed two different architectures: the single task CNN used to predict malignancy, and the multi-task CNN used to predict both malignancy and image magnification level simultaneously.…”