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

TL;DR

This paper introduces ALSF, a novel analysis-synthesis model with shared features for more effective histopathological image classification, reducing computational load and capturing class similarities and differences.

Contribution

The paper proposes a joint analysis-synthesis learning framework with shared low-rank dictionaries and analysis operators for improved histopathological image classification.

Findings

ALSF outperforms state-of-the-art methods on kidney tissue images.

ALSF effectively captures shared features among different classes.

Reduced computational complexity in patch-level 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.