Generating Binary Tags For Fast Medical Image Retrieval Based On Convolutional Nets And Radon Transform

Abstract

Content-based image retrieval (CBIR) in large medical image archives is a challenging and necessary task. Generally, different feature extraction methods are used to assign expressive and invariant features to each image such that the search for similar images comes down to feature classification and/or matching. The present work introduces a new image retrieval method for medical applications that employs a convolutional neural network (CNN) with recently introduced Radon barcodes. We combine neural codes for global classification with Radon barcodes for the final retrieval. We also examine image search based on regions of interest (ROI) matching after image retrieval. The IRMA dataset with more than 14,000 x-rays images is used to evaluate the performance of our method. Experimental results show that our approach is superior to many published works.

Stats

• citations42
• S2 citations—
• github stars0
• HF likes0
• heat score12.25
• arxiv keyliu2016generating

Related papers

• Barcodes For Medical Image Retrieval Using Autoencoded Radon Transform (2016)8.60
• Minmax Radon Barcodes For Medical Image Retrieval (2016)9.92
• Combining Real-valued And Binary Gabor-radon Features For Classification And Search In Medical Imaging Archives (2017)4.52
• Radon-gabor Barcodes For Medical Image Retrieval (2016)6.34
• Medical Image Retrieval Using Deep Convolutional Neural Network (2017)19.35
• CBIDR: A Novel Method For Information Retrieval Combining Image And Data By Means Of TOPSIS Applied To Medical Diagnosis (2024)0.00
• Gabor Barcodes For Medical Image Retrieval (2016)5.84
• Retrieving Similar X-ray Images From Big Image Data Using Radon Barcodes With Single Projections (2017)8.35