Gram Barcodes for Histopathology Tissue Texture Retrieval

TL;DR

This paper introduces Gram barcodes, a novel image feature extraction method based on high-order statistics from CNNs, to improve histopathology image retrieval efficiency and accuracy in large databases.

Contribution

The paper proposes Gram barcodes as a new texture descriptor for histopathology images, leveraging CNN feature correlations for better retrieval performance.

Findings

Achieved highly competitive retrieval results on three public datasets.

Demonstrated efficiency of Gram barcodes in handling gigapixel images.

Validated the approach using a pre-trained VGG19 network.

Abstract

Recent advances in digital pathology have led to the need for Histopathology Image Retrieval (HIR) systems that search through databases of biopsy images to find similar cases to a given query image. These HIR systems allow pathologists to effortlessly and efficiently access thousands of previously diagnosed cases in order to exploit the knowledge in the corresponding pathology reports. Since HIR systems may have to deal with millions of gigapixel images, the extraction of compact and expressive image features must be available to allow for efficient and accurate retrieval. In this paper, we propose the application of Gram barcodes as image features for HIR systems. Unlike most feature generation schemes, Gram barcodes are based on high-order statistics that describe tissue texture by summarizing the correlations between different feature maps in layers of convolutional neural networks. We run HIR experiments on three public datasets using a pre-trained VGG19 network for Gram barcode generation and showcase highly competitive results.