Barcodes for Medical Image Retrieval Using Autoencoded Radon Transform

TL;DR

This paper introduces autoencoded Radon barcodes, which use autoencoders to generate more efficient binary descriptors for medical image retrieval, outperforming previous methods like RBCs, SURF, and BRISK.

Contribution

The paper proposes a novel autoencoding approach to generate Radon-based binary codes, enhancing image retrieval accuracy by reducing redundancy and capturing richer features.

Findings

Autoencoded Radon barcodes outperform RBCs, SURF, and BRISK in retrieval accuracy.

Autoencoders reduce redundancy in Radon projections, leading to more effective image descriptors.

Experimental validation on the IRMA dataset demonstrates improved first-hit retrieval accuracy.

Abstract

Using content-based binary codes to tag digital images has emerged as a promising retrieval technology. Recently, Radon barcodes (RBCs) have been introduced as a new binary descriptor for image search. RBCs are generated by binarization of Radon projections and by assembling them into a vector, namely the barcode. A simple local thresholding has been suggested for binarization. In this paper, we put forward the idea of "autoencoded Radon barcodes". Using images in a training dataset, we autoencode Radon projections to perform binarization on outputs of hidden layers. We employed the mini-batch stochastic gradient descent approach for the training. Each hidden layer of the autoencoder can produce a barcode using a threshold determined based on the range of the logistic function used. The compressing capability of autoencoders apparently reduces the redundancies inherent in Radon projections leading to more accurate retrieval results. The IRMA dataset with 14,410 x-ray images is used to validate the performance of the proposed method. The experimental results, containing comparison with RBCs, SURF and BRISK, show that autoencoded Radon barcode (ARBC) has the capacity to capture important information and to learn richer representations resulting in lower retrieval errors for image retrieval measured with the accuracy of the first hit only.