Artículos de revistas
Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images
Registro en:
Plos One. Public Library Of Science, v. 9, n. 6, p. - , 2014.
19326203
10.1371/journal.pone.0096814
2-s2.0-84902336222
Autor
Pires R.
Jelinek H.F.
Wainer J.
Valle E.
Rocha A.
Institución
Resumen
Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semisoft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2±2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors. © 2014 Pires et al. 9 6
Sinthanayothin, C., Boyce, J.F., Williamson, T.H., Cook, H.L., Mensah, E., Lal, S., Usher, D., Automated detection of diabetic retinopathy on digital fundus images (2002) Diabetic Medicine, 19 (2), pp. 105-112. , DOI 10.1046/j.1464-5491.2002.00613.x Jelinek, H.F., Cree, M.J., Worsley, D., Luckie, A.P., Nixon, P., An automated microaneurysm detector as a tool for identification of diabetic retinopathy in rural optometric practice (2006) Clinical and Experimental Optometry, 89, pp. 299-305 Fleming, A.D., Philip, S., Goatman, K.A., Olson, J.A., Sharp, P.F., Automated microaneurysm detection using local contrast normalization and local vessel detection (2006) IEEE Transactions on Medical Imaging, 25 (9), pp. 1223-1232. , DOI 10.1109/TMI.2006.879953, 1677728 Niemeijer, M., Van Ginneken, B., Russell, S.R., Suttorp-Schulten, M.S.A., Abramoff, M.D., Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis (2007) Investigative Ophthalmology and Visual Science, 48 (5), pp. 2260-2267. , DOI 10.1167/iovs.06-0996 Giancardo, L., Mériaudeau, F., Karnowski, T.P., Tobin, K.W., Li, Y., Microaneurysms Detection with the Radon Cliff Operator in Retinal Fundus Images (2010) SPIE Medical Imaging, pp. 76230U-76230U. , International Society for Optics and Photonics Antal, B., Hajdu, A., An Ensemble-based System for Microaneurysm Detection and Diabetic Retinopathy Grading (2012) IEEE Transactions on Biomedical Engineering, 59 (6), pp. 1720-1726 Lazar, I., Hajdu, A., Retinal Microaneurysm Detection Through Local Rotating Cross-section Profile Analysis (2013) IEEE Transactions on Medical Imaging, 32 (2), pp. 400-407 Zhang, B., Wu, X., You, J., Li, Q., Karray, F., Hierarchical Detection of Red Lesions in Retinal Images by Multiscale Correlation Filtering (2009) SPIE Medical Imaging, pp. 72601L-72601L. , International Society for Optics and Photonics Sánchez, C.I., Hornero, R., Mayo, A., García, M., Mixture model-based clustering and logistic regression for automatic detection of microaneurysms in retinal images (2009) SPIE Medical Imaging, pp. 72601M-72601M. , International Society for Optics and Photonics Sánchez, C.I., García, M., Mayo, A., López, M.I., Hornero, R., Retinal image analysis based on mixture models to detect hard exudates (2009) Medical Image Analysis, 13 (4), pp. 650-658 Giancardo, L., Meriaudeau, F., Karnowski, T.P., Li, Y., Garg, S., Tobin, K.W., Chaum, E., Exudate-based diabetic macular edema detection in fundus images using publicly available datasets (2012) Medical Image Analysis, 16 (1), pp. 216-226 Fleming, A.D., Philip, S., Goatman, K.A., Williams, G.J., Olson, J.A., Sharp, P.F., Automated detection of exudates for diabetic retinopathy screening (2007) Physics in Medicine and Biology, 52 (24), pp. 7385-7396. , DOI 10.1088/0031-9155/52/24/012, PII S0031915507570430 Sopharak, A., Uyyanonvara, B., Barman, S., Williamson, T.H., Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods (2008) Computerized Medical Imaging and Graphics, 32, p. 8 Welfer, D., Scharcanski, J., Marinho, D.R., A coarse-to-fine strategy for automatically detecting exudates in color eye fundus images (2010) Computerized Medical Imaging and Graphics, 34, pp. 228-235 Boureau, Y., Bach, F., LeCun, Y., Ponce, J., Learning mid-level features for recognition (2010) IEEE Intl. Conference on Computer Vision and Pattern Recognition Rocha, A., Carvalho, T., Jelinek, H.F., Goldenstein, S., Wainer, J., Points of interest and visual dictionaries for automatic retinal lesion detection (2012) IEEE Transactions on Biomedical Engineering, 59, pp. 2244-2253 Jelinek, H.F., Rocha, A., Carvalho, T., Goldenstein, S., Wainer, J., Machine learning and pattern classification in identification of indigenous retinal pathology (2011) Intl. Conference of the IEEE Engineering in Medicine and Biology Society, pp. 5951-5954 Jelinek, H.F., Pires, R., Padilha, R., Goldenstein, S., Wainer, J., Data fusion for multi-lesion diabetic retinopathy detection (2012) IEEE Intl. Computer-Based Medical Systems, pp. 1-4 Phillips, P.J., Visible manifestations of diabetic retinopathy (2012) Medicine Today, 5, p. 83 (2013) Diabetes Programme. Online, , http://www.who.int/diabetes/en, World Health Organization Available: Accessed 6 May 2014 Giancardo, L., Meriaudeau, F., Karnowski, T.P., Li, Y., Tobin, K., Microaneurysm detection with radon transform-based classification on retina images (2011) Intl. Conference of the IEEE Engineering in Medicine and Biology Society, pp. 5939-5942 Li, Y., Karnowski, T.P., Tobin, K.W., Giancardo, L., Morris, S., A health insurance portability and accountability act-compliant ocular telehealth network for the remote diagnosis and management of diabetic retinopathy (2011) Telemedicine and E-Health, 17, pp. 627-634 Cree, M.J., Gamble, E., Cornforth, D.J., Colour normalisation to reduce interpatient and intrapatient variability in microaneurysm detection in colour retinal images (2005) Workshop on Digital Image Computing, pp. 163-168 Soares, J.V.B., Leandro, J.J.G., Cesar Jr., R.M., Jelinek, H.F., Cree, M.J., Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification (2006) IEEE Transactions on Medical Imaging, 25 (9), pp. 1214-1222. , DOI 10.1109/TMI.2006.879967, 1677727 Acharya, U.R., Lim, C.M., Ng, E.Y.K., Chee, C., Tamura, T., Computer-based detection of diabetes retinopathy stages using digital fundus images (2009) Journal of Engineering in Medicine, 223, pp. 545-553 Gonzalez, R.C., Woods, R.E., (2006) Digital Image Processing, , Upper Saddle River, NJ, USA: PrenticeHall, Inc., 2nd edition Nayak, J., Bhat, P.S., Acharya, U.R., Lim, C.M., Kagathi, M., Automated identification of diabetic retinopathy stages using digital fundus images (2008) Journal of Medical Systems, 32, pp. 107-115 Jelinek, H.F., Al-Saedi, K., Backlund, L.B., Computer assisted 'top-down' assessment of diabetic retinopathy (2009) World Congress on Medical Physics and Biomedical Engineering, pp. 127-130 Yun, W.L., Rajendra, A.U., Venkatesh, Y.V., Chee, C., Min, L.C., Ng, E.Y.K., Identification of different stages of diabetic retinopathy using retinal optical images (2008) Information Sciences, 178 (1), pp. 106-121. , DOI 10.1016/j.ins.2007.07.020, PII S0020025507003635 Sivic, J., Zisserman, A., Video Google: A Text Retrieval Approach to Object Matching in Videos (2003) IEEE Intl. Conference on Computer Vision, pp. 1470-1477 Baeza-Yates, R., Neto, B.R., (1999) Modern Information Retrieval, 1. , Addison Wesley Precioso, F., Cord, M., Machine learning approaches for visual information retrieval (2012) Visual Indexing and Retrieval, pp. 21-40. , Springer New York, SpringerBriefs in Computer Science Avila, S., Thome, N., Cord, M., Valle, E., De A Arajo, A., Pooling in image representation: The visual codeword point of view (2013) Computer Vision and Image Understanding, 117, pp. 453-465 Van Gemert, J., Veenman, C.J., Smeulders, A.W.M., Geusebroek, J.M., Visual word ambiguity (2010) IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, pp. 1271-1283 Boureau, Y., Ponce, J., LeCun, Y., A theoretical analysis of feature pooling in visual recognition (2010) Intl. Conference on Machine Learning, pp. 111-118 Cortes, C., Vapnik, V., Support-vector networks (1995) Machine Learning, 20, pp. 273-297 Chang, C.C., Lin, C.J., (2001) LIBSVM: A Library for Support Vector Machines, , http://www.csie.ntu.edu.tw/~cjlin/libsvm, Available: Accessed: 6 May 2014 Pires, R., Jelinek, H.F., Wainer, J., Rocha, A., Retinal image quality analysis for automatic diabetic retinopathy detection (2012) Intl. Conference on Graphics, Patterns and Images Bay, H., Ess, A., Tuytelaars, T., Gool, L.V., Speeded-up robust features (SURF) (2008) Computer Vision and Image Understanding, 110, pp. 346-359 Lowe, D.G., Distinctive image features from scale-invariant keypoints (2004) Intl Journal of Computer Vision, 60, pp. 91-110 Decencière, E., Cazuguel, G., Zhang, X., Thibault, G., Klein, J.C., (2013) TeleOphta: Machine Learning and Image Processing Methods for Teleophthalmology, , Ingénierie et Recherche Biomédicale Barriga, E.S., Murray, V., Agurto, C., Pattichis, M., Bauman, W., Automatic System for Diabetic Retinopathy Screening Based on AM-FM, Partial Least Squares, and Support Vector Machines (2010) IEEE Intl. Symposium on Biomedical Imaging: From Nano to Macro, pp. 1349-1352 Deepak, K.S., Sivaswamy, J., Automatic Assessment of Macular Edema from Color Retinal Images (2012) IEEE Transactions on Medical Imaging, 31 (3), pp. 766-776 Pires, R., Jelinek, H.F., Wainer, J., Goldenstein, S., Valle, E., Assessing the Need for Referral in Automatic Diabetic Retinopathy Detection (2013) IEEE Transactions on Biomedical Engineering, 60 (12), pp. 3391-3398 Dietterich, T.G., Approximate statistical tests for comparing supervised classification learning algorithms (1998) Neural Computation, 10, pp. 1895-1923 Friedman, M., The use of ranks to avoid the assumption of normality implicit in the analysis of variance (1937) Journal of the American Statistical Association, 32 (200), pp. 675-701 Nemenyi, P., (1963) Distribution-free Multiple Comparisons, , Doctoral dissertation, Princeton University Klein, R., Klein, B.E.K., Moss, S.E., Davis, M.D., DeMets, D.L., The Wisconsin Epidemiologic Study of Diabetic Retinopathy. IX. Four-year incidence and progression of diabetic retinopathy when age at diagnosis is less than 30 years (1989) Archives of Ophthalmology, 107 (2), pp. 237-243 Grading diabetic retinopathy from stereoscopic color fundus photographs - An extension of the modified Airlie House Classification. ETDRS Report Number 10 (1991) Ophthalmology, 98, pp. 786-806. , ETDRS Research Group Mitchell, P., Foran, S., Wong, T.Y., Chua, B., Patel, I., (2008) Guidelines for the Management of Diabetic Retinopathy, , http://www.nhmrc.gov.au/_files_nhmrc/file/publications/synopses/di15.pdf, Available: Accessed: 6 May 2014 Chew, E.Y., A simplified diabetic retinopathy scale (2003) Ophthalmology, 110 (9), pp. 1675-1676. , Sep Abramoff, M.D., Niemeijer, M., Suttorp-Schulten, M.S.A., Viergever, M.A., Russell, S.R., Van Ginneken, B., Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes (2008) Diabetes Care, 31 (2), pp. 193-198. , http://care.diabetesjournals.org/cgi/reprint/31/2/193, DOI 10.2337/dc07-1312 Fleming, A.D., Goatman, K.A., Philip, S., Williams, G.J., Prescott, G.J., The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy (2010) British Journal of Ophthalmology, 94 (6), pp. 706-711 Abramoff, M.D., Folk, J.C., Han, D.P., Walker, J.D., Williams, D.F., Automated analysis of retinal images for detection of referable diabetic retinopathy (2013) JAMA Ophthalmol, 131 (3), pp. 351-357 Ahmed, J., Ward, T.P., Bursell, S.-E., Aiello, L.M., Cavallerano, J.D., Vigersky, R.A., The sensitivity and specificity of nonmydriatic digital stereoscopic retinal imaging in detecting diabetic retinopathy (2006) Diabetes Care, 29 (10), pp. 2205-2209. , http://care.diabetesjournals.org/cgi/reprint/29/10/2205.pdf, DOI 10.2337/dc06-0295 Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A., The devil is in the details: An evaluation of recent feature encoding methods (2011) British Machine Vision Conference (BMVC), pp. 1-12 Perronnin, F., Akata, Z., Harchaoui, Z., Schmid, C., Towards good practice in large-scale learning for image classification (2012) Intl. Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-8