TY - GEN
T1 - Generating binary tags for fast medical image retrieval based on convolutional nets and Radon Transform
AU - Liu, Xinran
AU - Tizhoosh, H. R.
AU - Kofman, J.
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/10/31
Y1 - 2016/10/31
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85007228588&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85007228588&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2016.7727562
DO - 10.1109/IJCNN.2016.7727562
M3 - Conference contribution
AN - SCOPUS:85007228588
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 2872
EP - 2878
BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 International Joint Conference on Neural Networks, IJCNN 2016
Y2 - 24 July 2016 through 29 July 2016
ER -