Deep Barcodes for Fast Retrieval of Histopathology Scans

TL;DR

This paper introduces deep barcodes, binary representations for histopathology images, enabling faster retrieval with comparable or better accuracy than traditional deep features, demonstrated on the Kimia Path24 dataset.

Contribution

The paper proposes two novel methods for generating deep barcodes to improve speed and efficiency in histopathology image retrieval.

Findings

Deep barcodes achieve 71.62% retrieval accuracy.

Deep barcodes are faster and more storage-efficient.

Performance surpasses traditional deep features.

Abstract

We investigate the concept of deep barcodes and propose two methods to generate them in order to expedite the process of classification and retrieval of histopathology images. Since binary search is computationally less expensive, in terms of both speed and storage, deep barcodes could be useful when dealing with big data retrieval. Our experiments use the dataset Kimia Path24 to test three pre-trained networks for image retrieval. The dataset consists of 27,055 training images in 24 different classes with large variability, and 1,325 test images for testing. Apart from the high-speed and efficiency, results show a surprising retrieval accuracy of 71.62% for deep barcodes, as compared to 68.91% for deep features and 68.53% for compressed deep features.