TY - GEN
T1 - Barcodes for medical image retrieval using autoencoded Radon transform
AU - Tizhoosh, Hamid R.
AU - Mitcheltree, Christopher
AU - Zhu, Shujin
AU - Dutta, Shamak
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/1/1
Y1 - 2016/1/1
N2 - 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.
AB - 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.
KW - Autoencoder
KW - Image retrieval
KW - Medical imaging
KW - Neural networks
KW - Radon barcode
KW - Radon transform
UR - http://www.scopus.com/inward/record.url?scp=85019146972&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019146972&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2016.7900119
DO - 10.1109/ICPR.2016.7900119
M3 - Conference contribution
AN - SCOPUS:85019146972
T3 - Proceedings - International Conference on Pattern Recognition
SP - 3150
EP - 3155
BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd International Conference on Pattern Recognition, ICPR 2016
Y2 - 4 December 2016 through 8 December 2016
ER -