Analysis-synthesis model learning with shared features: A new framework for histopathological image classification

Abstract

Automated histopathological image analysis offers exciting opportunities for the early diagnosis of several medical conditions including cancer. There are however stiff practical challenges: 1.) discriminative features from such images for separating diseased vs. healthy classes are not readily apparent, and 2.) distinct classes, e.g. healthy vs. stages of disease continue to share several geometric features. We propose a novel Analysis-synthesis model Learning with Shared Features algorithm (ALSF) for classifying such images more effectively. In ALSF, a joint analysis and synthesis learning model is introduced to learn the classifier and the feature extractor at the same time. In this way, the computation load in patch-level based image classification can be much reduced. Crucially, we integrate into this framework the learning of a low rank shared dictionary and a shared analysis operator, which more accurately represents both similarities and differences in histopathological images from distinct classes. ALSF is evaluated on two challenging databases: (1) kidney tissue images provided by the Animal Diagnosis Lab (ADL) at the Pennsylvania State University and (2) brain tumor images from The Cancer Genome Atlas (TCGA) database. Experimental results confirm that ALSF can offer benefits over state of the art alternatives.

Improving Breast Cancer Detection and Diagnosis through Semantic Segmentation Using the Unet3+ Deep Learning Framework

“…This facilitates the flow of information between layers, thereby improving the accuracy of semantic segmentation. In addition, residual links are used to connect distant layers in the network to allow information propagation across multiple layers, further improving performance [ 30 , 31 ].…”

“…This facilitates the flow of information between layers, thereby improving the accuracy of semantic segmentation. In addition, residual links are used to connect distant layers in the network to allow information propagation across multiple layers, further improving performance [30,31]. Both Unet and Unet++ do not explore enough information from full scale, resulting in the inability to explicitly determine the position and boundary of an organ.…”