Learning autoencoded radon projections

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 ≈ 82% accuracy) outperforming state-of-the-art works on retrieval from IRMA dataset using autoencoders.

[1]  Hamid R. Tizhoosh,et al.  Medical Image Classification via SVM Using LBP Features from Saliency-Based Folded Data , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[2]  Hamid R. Tizhoosh,et al.  Stacked Autoencoders for Medical Image Search , 2016, ISVC.

[3]  Li Deng,et al.  A tutorial survey of architectures, algorithms, and applications for deep learning , 2014, APSIPA Transactions on Signal and Information Processing.

[4]  Hayit Greenspan,et al.  Addressing the ImageClef 2009 Challenge Using a Patch-based Visual Words Representation , 2009, CLEF.

[5]  Paul Benjamin,et al.  Object Recognition Using Deep Neural Networks: A Survey , 2014, ArXiv.

[6]  Sarah Eichmann,et al.  The Radon Transform And Some Of Its Applications , 2016 .

[7]  Hamid R. Tizhoosh,et al.  Radon features and barcodes for medical image retrieval via SVM , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[8]  Nico Karssemeijer,et al.  Computer-Aided Diagnosis in Medical Imaging , 2001, IEEE Trans. Medical Imaging.

[9]  Hamid R. Tizhoosh,et al.  Autoencoding the retrieval relevance of medical images , 2015, 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA).

[10]  Hamid R. Tizhoosh,et al.  Barcodes for medical image retrieval using autoencoded Radon transform , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[11]  Barbara Caputo,et al.  Overview of the CLEF 2009 Medical Image Annotation Track , 2009, CLEF.

[12]  Jorge L. C. Sanz,et al.  Radon and Projection Transform-Based Computer Vision: Algorithms, A Pipeline Architecture, and Industrial Applications , 1988 .

[13]  Kunio Doi,et al.  Computer-aided diagnosis in medical imaging: Historical review, current status and future potential , 2007, Comput. Medical Imaging Graph..

[14]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[15]  Geoffrey E. Hinton,et al.  Using very deep autoencoders for content-based image retrieval , 2011, ESANN.

[16]  Hamid R. Tizhoosh,et al.  Barcode annotations for medical image retrieval: A preliminary investigation , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[17]  Hamid R. Tizhoosh,et al.  MinMax Radon Barcodes for Medical Image Retrieval , 2016, ISVC.

[18]  Andrew K. C. Wong,et al.  Binary codes for tagging x-ray images via deep de-noising autoencoders , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).