Learning Autoencoded Radon Projections

Abstract

Autoencoders have been recently used for encoding medical images. In this study, we design and validate a new framework for retrieving medical images by classifying Radon projections, compressed in the deepest layer of an autoencoder. As the autoencoder reduces the dimensionality, a multilayer perceptron (MLP) can be employed to classify the images. The integration of MLP promotes a rather shallow learning architecture which makes the training faster. We conducted a comparative study to examine the capabilities of autoencoders for different inputs such as raw images, Histogram of Oriented Gradients (HOG) and normalized Radon projections. Our framework is benchmarked on IRMA dataset containing \(14,410\) x-ray images distributed across \(57\) different classes. Experiments show an IRMA error of \(313\) (equivalent to \(\approx 82%\) accuracy) outperforming state-of-the-art works on retrieval from IRMA dataset using autoencoders.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keysriram2017learning

Related papers

• Barcodes For Medical Image Retrieval Using Autoencoded Radon Transform (2016)8.60
• Stacked Autoencoders For Medical Image Search (2016)10.48
• Binary Codes For Tagging X-ray Images Via Deep De-noising Autoencoders (2016)7.81
• Generating Binary Tags For Fast Medical Image Retrieval Based On Convolutional Nets And Radon Transform (2016)12.25
• Local Radon Descriptors For Image Search (2017)8.60
• Minmax Radon Barcodes For Medical Image Retrieval (2016)9.92
• Sparse Autoencoders For Interpretable Medical Image Representation Learning (2026)0.78
• Retrieving Similar X-ray Images From Big Image Data Using Radon Barcodes With Single Projections (2017)8.35