A data mining framework for the classification of retinopathy images based on a new multistage prediction algorithm

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Medical image processing, analysis and classification is a rapidly expanding field providing possible solutions for health care providers including ophthalmologists and optometrists. To be of value, image analysis and classification requires high accuracy and fast processing. Early detection of diabetic retinopathy can lead to better treatment outcomes, especially in rural and remote areas where there is a lack of specialists. In the current work we propose a highly accurate prediction model based on optic disc color characteristics. We propose a data mining algorithm based on a top-down processing framework. The framework involves a new Multistage Prediction algorithm (MSP1) consisting of segmentation of the optic disc, dilation, and color normalization, color histogram determination, and calculating the predicted classification score of each image. The final step carries out the process of classification of all images based on the Group Method of Data Handling(GMDH) application. One hundred and fifty seven images were available for classification. The results indicate that the proposed Multistage Prediction algorithm combined with the GMDH classification framework improved on previous results with an overall accuracy of 96.8%, and sensitivity of 95% and an F-measure for the classification performance of96%. MSP1 is easy to implement on any laptop and therefore provides a robust option for tele-ophthalmology diagnostics of retinopathy.

     


     

  • Keywords


    Method of Data Handling; GMDH; Diabetic Retinopathy; Optic Disc; Medical Image processing; Data Mining.

  • References


      [1] KantardzicM.,“Data Mining: Concepts, Models, Methods, and Algorithms”. 2nd Edition, Hardcover, 552 pages, Wiley-IEEE Press, ISBN: 978-0-470-89045-5. 2011.https://doi.org/10.1002/9781118029145.

      [2] Han J., KamberM, and Pei J., "Data Mining Concepts and Techniques". Third edition, Morgan Kaufmann publishers as anreprint by Elsevier, USA, 2012.

      [3] GMDH website, "GMDH algorithms and the algorithms of GMDH type". http://www.gmdh.net/GMDH_typ.htm. 2018.

      [4] Mingzhu Z., Changzheng H., and Panos L., “A D-GMDH Model for Time Series Forecasting”. Expert Systems with Applications Journal,Vol. 39, Issue 5. (April 2012), 5711-5716. DOI=http: // dx.doi.org /10.1016 / j.eswa. 2011.11.100. 2012.

      [5] GMDH website, “GMDH Shell Documentation”,http://d.gmdhshell.com/docs/concepts. 2018.

      [6] Abdul Aziz A.andRehman A., “Detection of Cardiac Disease using Data Mining Classification Techniques”. International Journal of Advanced Computer Science and Applications, Vol. 8, Issue 7, Pages 256-259. 2017.

      [7] Kavakiotis I., Tsave O., Salifoglou A., Maglaveras N., Vlahavas I., ChouvardaI.,“Machine Learning and Data Mining Methods in Diabetes Research”. Computational and Structural Biotechnology Journal. 15:104-116. doi:10.1016/j.csbj.2016.12.005.2017.

      [8] KamilR., Al-Saedi K. H., Al-Azawi R., "An Accurate System for Measure the Diabetic Retinopathy by Using SVM Classifier".Ciência e TécnicaVitivinícola Journal, 2018. Vol. 33, Issue 1, Pages 135-139. 2018.

      [9] Gulshan V, Peng L, Coram M, et al.,“Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs”. JAMA,Vol. 316, Issue 22, Pages 2402–2410.https://doi.org/10.1001/jama.2016.17216.

      [10] Mahendran G., Dhanasekaran R., “Investigation of the Severity Level of Diabetic Retinopathy using Supervised Classifier Algorithms”. Computers & Electrical Engineering Journal, Vol. 45, Pages 312-323, https://doi.org/10.1016/j.compeleceng.2015.01.013.

      [11] KamilR, Al-Saedi K. H., Al-Azawi R., "A Novel Approach for Optic Disc Detection in RGB Retinal Fundus Images". International Journal of Science and Research, Vol. 6, Issue 8, Pages 1263 – 1268, http://www.ijsrpublications.com/ijsr.net/archive/v6i8/v6i8.php, 2017.

      [12] Almazroa A., Burman R., Raahemifar K., Lakshminarayanan V., “Optic Disc and Optic Cup Segmentation Methodologies for Glaucoma Image Detection: A Survey”. Journal of Ophthalmology, Vol. 2015, Article ID 180972, Pages 1-28.

      [13] Alghamdi, H., Tang H., Waheeb, S., and Tunde, P, “Automatic Optic Disc Abnormality Detection in Fundus Images: A Deep Learning Approach”. In Proceedings of the Ophthalmic Medical Image Analysis Third International Workshop, Vol: 3, Pages 17-24, Athens, Greece.

      [14] Sathiyamoorthy C. A. and Kulanthaivel, G., “Design and Develop a Computer Aided Design for Automatic Exudates Detection for Diabetic Retinopathy Screening”. Journal of Engineering Science and Technology Vol. 11, Issue 4, Pages 605 – 618, 2016.

      [15] Verma, K.; Deep, P.; Ramakrishnan, A. G., "Detection and Classification of Diabetic Retinopathy using Retinal Images". India Conference (INDICON), 2011 Annual IEEE, Vol., Pages 1-6, 16-18 Dec. 2011, URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6139346&isnumber=6139311https://doi.org/10.1109/INDCON.2011.6139346.

      [16] Welfer D., Scharcanski J., Cleyson M. K., Dal Pizzol M., LudwigW.B., Marinho R., “Segmentation of the Optic Disk in Color Eye Fundus Images using an Adaptive Morphological Approach”. Computers in Biology and Medicine Journal, Volume 40, Issue 2, Pages 124-137.

      [17] DaiB. Xiangqian Wu, Wei Bu, “Optic Disc Segmentation Based on VariationalModel with Multiple Energies”. Pattern Recognition Journal, Volume 64, Pages 226-235.

      [18] Mitchell P., Foran, S.Australian Diabetes Society, National Health, and Medical Research Council, “Guidelines for the management of diabetic retinopathy”, publisher National Health and Medical Research Council” ISBN 1741866723- 1741866715, https://nla.gov.au/nla.cat-vn4470187, 2008.

      [18]JelinekH.F, Al-SaediK. H. and BäcklundL.B. "Computer Assisted “Top-Down‟ Assessment of Diabetic Retinopathy". World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany, IFMBE Proceedings Springer Berlin Heidelberg, ISSN 1680-0737, Vol. 25, Issue 11, Pages 127-130. 2009.

      [19] Kumar SB and Vipula S., “Automatic Detection of Diabetic Retinopathy in Non-dilated RGB Retinal Fundus Images”. International Journal of Computer Applications, Vol. 47, Issue 19, Pages 26–32, 2012.

      [20] Thammastitkul A. and UyyanonvaraB, “Diabetic Retinopathy Stages Identification Using Retinal Images”. Annual Internatoinal Conference on Intelligent Computing, Computer Science & Information Systems, April 28-29 (2016), Pattaya, Thailand Pages 20–23, 2016.


 

View

Download

Article ID: 21243
 
DOI: 10.14419/ijet.v7i4.21243




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.