Retrieval of pathological retina images using Bag of Visual Words and pLSA model

Abstract Automated identification of pathological retina images is very important in retinopathy. Conventional methods of retrieval in the domain of retinopathy are based on the manual observation of different components of retina. However, manual observation becomes difficult due to the large diversity of images and the varying symptoms of diseases present in pathological images. For example, varying features such as color, shape and structure of lesions complicate the manual observations and subsequent assessment of the state of the disease. As a solution to these issues, this paper proposes an unsupervised technique known as probabilistic Latent Semantic Analysis (pLSA) along with Bag of Visual Words to discriminate diseased images from normal ones. The method was tested with images from publicly available standard retina fundus image databases and achieved better performance measures compared to the existing methods.

[1]  Jayanthi Sivaswamy,et al.  Visual saliency based bright lesion detection and discrimination in retinal images , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[2]  Arnau Oliver,et al.  Modeling and Classifying Breast Tissue Density in Mammograms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  Emmanouil Giouvanakis,et al.  Saliency map driven image retrieval combining the bag-of-words model and PLSA , 2014, 2014 19th International Conference on Digital Signal Processing.

[4]  Roberto Hornero,et al.  Automated detection of diabetic retinopathy in retinal images , 2016, Indian journal of ophthalmology.

[5]  Desire Sidibé,et al.  Discrimination of retinal images containing bright lesions using sparse coded features and SVM , 2015, Comput. Biol. Medicine.

[6]  Jayanthi Sivaswamy,et al.  A Bag of Words approach for discriminating between retinal images containing exudates or drusen , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[7]  Liming Chen,et al.  Encoding Local Binary Descriptors by Bag-of-Features with Hamming Distance for Visual Object Categorization , 2013, ECIR.

[8]  Jacques Wainer,et al.  Assessing the Need for Referral in Automatic Diabetic Retinopathy Detection , 2013, IEEE Transactions on Biomedical Engineering.

[9]  M. Raj,et al.  Retinal Abnormality Risk Prediction Model: A Hybrid Approach Based on Vessel Characteristics and Exudates , 2016 .

[10]  Dong-Ju Kim,et al.  Face Recognition via Local Directional Pattern , 2013 .

[11]  Emanuele Trucco,et al.  Leveraging Multiscale Hessian-Based Enhancement With a Novel Exudate Inpainting Technique for Retinal Vessel Segmentation , 2016, IEEE Journal of Biomedical and Health Informatics.

[12]  Dong Yue,et al.  Control Synthesis of Discrete-Time T–S Fuzzy Systems: Reducing the Conservatism Whilst Alleviating the Computational Burden , 2017, IEEE Transactions on Cybernetics.

[13]  Rainer Lienhart,et al.  Multilayer pLSA for multimodal image retrieval , 2009, CIVR '09.

[14]  Khosro Rezaee,et al.  Optimized clinical segmentation of retinal blood vessels by using combination of adaptive filtering, fuzzy entropy and skeletonization , 2017, Appl. Soft Comput..

[15]  Ibrahim Sadek,et al.  Automatic discrimination of color retinal images using the bag of words approach , 2015, Medical Imaging.

[16]  Oksam Chae,et al.  Gender Classification Using Local Directional Pattern (LDP) , 2010, 2010 20th International Conference on Pattern Recognition.

[17]  B. Nayak,et al.  Prevalence of diabetic retinopathy in India: The All India Ophthalmological Society Diabetic Retinopathy Eye Screening Study 2014 , 2016, Indian journal of ophthalmology.

[18]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[19]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[20]  Z. Habib,et al.  Texture Feature Analysis of Digital Fundus Images for Early Detection of Diabetic Retinopathy , 2014, 2014 11th International Conference on Computer Graphics, Imaging and Visualization.

[21]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[22]  Rajeev Srivastava,et al.  Retinal blood vessels segmentation by using Gumbel probability distribution function based matched filter , 2016, Comput. Methods Programs Biomed..

[23]  Zhiguo Jiang,et al.  Pathological Image Retrieval for Breast Cancer with pLSA Model , 2013, 2013 Seventh International Conference on Image and Graphics.

[24]  Oksam Chae,et al.  Local directional pattern variance (ldpv): a robust feature descriptor for facial expression recognition , 2012, Int. Arab J. Inf. Technol..

[25]  Thomas Hofmann,et al.  Unsupervised Learning by Probabilistic Latent Semantic Analysis , 2004, Machine Learning.