Case-Based Histopathological Malignancy Diagnosis using Convolutional Neural Networks

Abstract

In practice, histopathological diagnosis of tumor malignancy often requires a human expert to scan through histopathological images at multiple magnification levels, after which a final diagnosis can be accurately determined. However, previous research on such classification tasks using convolutional neural networks primarily determine a diagnosis for a single magnification level. In this paper, we propose a case-based approach using deep residual neural networks for histopathological malignancy diagnosis, where a case is defined as a sequence of images from the patient at all available levels of magnification. Effectively, through mimicking what a human expert would actually do, our approach makes a diagnosis decision based on features learned in combination at multiple magnification levels. Our results show that the case-based approach achieves better performance than the state-of-the-art methods when evaluated on BreaKHis, a histopathological image dataset for breast tumors.

Cell Phenotype Classification Using Deep Residual Network and Its Variants

“…The introduction of residual connections into convolutional neural network makes ResNet currently the basis of many state-of-the-art CNN models. Similar to our previous work, 9 we also train an 18-layer ResNet model (ResNet-18) integrated with the latest design of residual unit, which is proposed to make the model easier to train and also has better performance. 6 The basic residual unit consists of six sequential components: Batch Normalization, ReLU, Convolution, Batch Normalization, ReLU and Convolution.…”