Globally-Aware Multiple Instance Classifier for Breast Cancer Screening

Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.

2D Electrophoresis Gel Image and Diagnosis of a Disease

The process of diagnosing a disease from the 2D gel electrophoresis image is a challenging problem. This is due to technical difficulties of generating reproducible images with a normalized form and the effect of negative stain. In this paper, we will discuss a new concept of interpreting the 2D images and overcoming the aforementioned technical difficulties using mathematical transformation. The method makes use of 2D gel images of proteins in serums and we explain a way of representing the images into vectors in order to apply machine-learning methods, such as the support vector machine.