Stacked Autoencoders for Medical Image Search

Medical images can be a valuable resource for reliable information to support medical diagnosis. However, the large volume of medical images makes it challenging to retrieve relevant information given a particular scenario. To solve this challenge, content-based image retrieval (CBIR) attempts to characterize images (or image regions) with invariant content information in order to facilitate image search. This work presents a feature extraction technique for medical images using stacked autoencoders, which encode images to binary vectors. The technique is applied to the IRMA dataset, a collection of 14,410 x-ray images in order to demonstrate the ability of autoencoders to retrieve similar x-rays given test queries. Using IRMA dataset as a benchmark, it was found that stacked autoencoders gave excellent results with a retrieval error of 376 for 1,733 test images with a compression of 74.61%.

[1]  Marina Bosch,et al.  ImageCLEF, Experimental Evaluation in Visual Information Retrieval , 2010 .

[2]  H L Kundel,et al.  Visual scanning, pattern recognition and decision-making in pulmonary nodule detection. , 1978, Investigative radiology.

[3]  Razvan Pascanu,et al.  Theano: A CPU and GPU Math Compiler in Python , 2010, SciPy.

[4]  Yung-Kuan Chan,et al.  Image retrieval system based on color-complexity and color-spatial features , 2004, J. Syst. Softw..

[5]  Hayit Greenspan,et al.  Content-Based Image Retrieval in Radiology: Current Status and Future Directions , 2010, Journal of Digital Imaging.

[6]  Paul Clough,et al.  ImageCLEF: Experimental Evaluation in Visual Information Retrieval , 2010 .

[7]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[8]  Peter G. B. Enser,et al.  Progress in Documentation Pictorial Information Retrieval , 1995, J. Documentation.

[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]  Thomas Deselaers,et al.  A Content-Based Approach to Image Retrieval in Medical Applications , 2006 .

[11]  Peter G. B. Enser.  Pictorial information retrieval , 1995 .

[12]  K.Velmurugan,et al.  Content-Based Image Retrieval using SURF and Colour Moments , 2011 .

[13]  Naphtali Rishe,et al.  Content-based image retrieval , 1995, Multimedia Tools and Applications.

[14]  Chikkannan Eswaran,et al.  Using Autoencoders for Mammogram Compression , 2011, Journal of Medical Systems.

[15]  Razvan Pascanu,et al.  Theano: new features and speed improvements , 2012, ArXiv.

[16]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[17]  Michael Kohnen,et al.  The IRMA code for unique classification of medical images , 2003, SPIE Medical Imaging.

[18]  T V Kinsey,et al.  Interfacing the PACS and the HIS: results of a 5-year implementation. , 2000, Radiographics : a review publication of the Radiological Society of North America, Inc.