skip to main content
research-article

A Convolutional Neural Network Model Using Weighted Loss Function to Detect Diabetic Retinopathy

Authors Info & Claims
Published:25 January 2022Publication History
Skip Abstract Section

Abstract

Nowadays, artificial intelligence (AI) provides tremendous prospects for driving future healthcare while empowering patients and service providers. The extensive use of digital healthcare produces a massive amount of multimedia healthcare data continuously (e.g., MRI, X-Ray, ultrasound images, etc.). Hence, it needs special data analytics techniques to provide a smart diagnosis to the patients. Recent advancements in artificial intelligence and machine learning techniques, particularly Deep learning (DL) methods, have demonstrated tremendous medical diagnosis progress and achievements. Diabetic Retinopathy (DR), cataract, macular degeneration, and glaucoma are the most common eye problems due to diabetes. Numerous models have been proposed using deep learning models to diagnose diabetic retinopathy, but no model is perfect for detecting DR diseases. This article presents a deep learning model to analyze diabetic retinopathy images to classify DR patients’ severity levels. The model applies a custom-weighted loss function in the model’s training and achieves 92.49% accuracy and a 0.945 Cohen Kappa score on test data. The model’s weighted average precision was 93%, recall 92%, and f1 score 93%. The model is compared with several state-of-the-art pre-trained models. We observe that the proposed model performs better in accuracy results and Cohen Kappa score.

REFERENCES

  1. [1] Amin Javeria, Sharif Muhammad, and Yasmin Mussarat. 2016. A review on recent developments for detection of diabetic retinopathy. Scientifica 2016 (2016), 68389766838976. https://doi.org/10.1155/2016/6838976Google ScholarGoogle ScholarCross RefCross Ref
  2. [2] Amin Syed Umar et al. 2019. Cognitive smart healthcare for pathology detection and monitoring. IEEE Access 7 (2019), 1074510753. https://doi.org/10.1109/ACCESS.2019.2891390Google ScholarGoogle ScholarCross RefCross Ref
  3. [3] Bhaskaranand Malavika, Ramachandra Chaithanya, Bhat Sandeep, Cuadros Jorge, Nittala Muneeswar Gupta, Sadda SriniVas, and Solanki Kaushal. 2016. Automated diabetic retinopathy screening and monitoring using retinal fundus image analysis. Journal of Diabetes Science Technology 10, 2 (Feb. 2016), 254261. https://doi.org/10.1177/1932296816628546Google ScholarGoogle ScholarCross RefCross Ref
  4. [4] Byrd Jonathon and Lipton Zachary C.. 2018. Weighted risk minimization & deep learning. CoRR abs/1812.03372 (2018). arxiv:1812.03372 http://arxiv.org/abs/1812.03372.Google ScholarGoogle Scholar
  5. [5] Chernenko Sergey. [n.d.]. Gaussian Filter, or Gaussian Blur. Retrieved May 27, 2017, from http://www.librow.com/articles/article-9.Google ScholarGoogle Scholar
  6. [6] Choi Joon Yul, Yoo Tae Keun, Seo Jeong Gi, Kwak Jiyong, Um Terry Taewoong, and Rim Tyler Hyungtaek. 2017. Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database. PLOS ONE 12, 11 (2017), 116. https://doi.org/10.1371/journal.pone.0187336Google ScholarGoogle ScholarCross RefCross Ref
  7. [7] DeHoog Edward and Schwiegerling James. 2009. Fundus camera systems: A comparative analysis. Applied Options 48, 2 (Jan. 2009), 221228. https://doi.org/10.1364/AO.48.000221Google ScholarGoogle ScholarCross RefCross Ref
  8. [8] M. Shorfuzzaman, and M. S. Hossain. 2021. MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patients. Pattern Recognition 113 (2021), 107700. https://doi.org/10.1016/j.patcog.2020.107700Google ScholarGoogle Scholar
  9. [9] Hammes H. P., Lemmen Klaus Dieter, and Bertram Becky. 2014. Diabetic retinopathy and maculopathy. Experimental and Clinical Endocrinology & Diabetes Official Journal, German Society of Endocrinology [and] German Diabetes Association 122, 7 (2014), 387–90.Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Hermann B., Fernández E. J., Unterhuber A., Sattmann H., Fercher A. F., Drexler W., Prieto P. M., and Artal P.. 2004. Adaptive-optics ultrahigh-resolution optical coherence tomography. Optics Letters 29, 18 (Sep. 2004), 21422144. https://doi.org/10.1364/OL.29.002142Google ScholarGoogle ScholarCross RefCross Ref
  11. [11] Hossain M. S.. 2017. Cloud-supported cyber-physical localization framework for patients monitoring. IEEE Systems Journal 11, 1 (2017), 118127.Google ScholarGoogle ScholarCross RefCross Ref
  12. [12] Hossain M. S., Amin S. U., Alsulaiman G., and Muhammad M.. 2019. Applying deep learning for epilepsy seizure detection and brain mapping visualization. ACM Transactions on Multimedia Computing, Communications, and Applications 15, 1s (2019), 1–17. https://doi.org/10.1145/3241056 Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. [13] Huang Gao, Liu Zhuang, Maaten Laurens van der, and Weinberger Kilian Q.. 2017. Densely Connected Convolutional Networks. arxiv:1608.06993.Google ScholarGoogle Scholar
  14. [14] Mishra P. K., Sinha A., Teja K. R., Bhojwani N., Sahu S., and A. A. Kumar2014. A computational modeling for the detection of diabetic retinopathy severity. Bioinformation 10, 9 (2014), 556561.Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] kag 2019. APTOS 2019 Blindness Detection. Retrieved May 27, 2021, from https://www.kaggle.com/c/aptos2019-blindness-detection.Google ScholarGoogle Scholar
  16. [16] Kalyani G., Janakiramaiah B., Karuna A., and Prasad L. V. Narasimha. 2021. Diabetic retinopathy detection and classification using capsule networks. Complex & Intelligent Systems (2021), 1–14. https://doi.org/10.1007/s40747-021-00318-9Google ScholarGoogle ScholarCross RefCross Ref
  17. [17] Kandhasamy J. Pradeep, Balamurali Seifedine Kadry S., and Ramasamy Lakshmana Kumar. 2020. Diagnosis of diabetic retinopathy using multi level set segmentation algorithm with feature extraction using SVM with selective features. Multimedia Tools and Applications 79 (March 2020), 1058110596. https://doi.org/10.1007/s11042-019-7485-8Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. [18] Simonyan Andrew Zisserman and Karen. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arxiv:1409.1556.Google ScholarGoogle Scholar
  19. [19] Krishnan Mookiah Muthu Rama, Min Chua Chua Kuang, Ng Lim Choo, Laude E. Y. K., and Augustinus. 2013. Computer aided diagnosis of diabetic retinopathy using multi-resolution analysis and feature ranking frame work. Journal of Medical Imaging and Health Informatics 3, 4 (Dec. 2013), 598606. https://doi.org/10.1166/jmihi.2013.1210 Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. [20] Krizhevsky Alex, Sutskever Ilya, and Hinton Geoffrey E.. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM 60, 6 (May 2017), 8490. https://doi.org/10.1145/3065386 Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Lecun Y., Bottou L., Bengio Y., and Haffner P.. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 11 (1998), 22782324.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Li B. and Li H. K.. 2013. Automated analysis of diabetic retinopathy images: Principles, recent developments, and emerging trends. Current Diabetes Reports 13, 4 (Aug 2013), 453459.Google ScholarGoogle ScholarCross RefCross Ref
  23. [23] M. Shorfuzzaman et al. 2021. Towards the sustainable development of smart cities through mass video surveillance: A response to the COVID-19 pandemic. Sustainable Cities and Society 64 (2021), 102582. https://doi.org/10.1016/j.scs.2020.102582Google ScholarGoogle Scholar
  24. [24] Manivannan A., Kirkpatrick J. N. P., Sharp P. F., and Forrester J. V.. 1998. Novel approach towards colour imaging using scanning laser ophthalmoscope. British Journal of Ophthalmology 82, 4 (Feb. 1998), 342345. https://doi.org/10.1136/bjo.82.4.342Google ScholarGoogle ScholarCross RefCross Ref
  25. [25] Miao Yu, Dong Haiwei, Jaam Jihad Mohamad Al, and Saddik Abdulmotaleb El. 2019. A deep learning system for recognizing facial expression in real-time. ACM Transactions on Multimedia Computing, Communications, and Applications 15, 2 (2019), 20 pages. https://doi.org/10.1145/3311747 Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Mookiah Muthu Rama Krishnan, Acharya Rajendra, Chuaa Chua Kuang, Lim Choo Min, Ng E. Y. K., and Laude Augustinus. 2013. Computer-aided diagnosis of diabetic retinopathy: A review. Computers in Biology and Medicine 43, 11 (Dec. 2013), 21362155. https://doi.org/10.1016/j.compbiomed.2013.10.007 Google ScholarGoogle ScholarDigital LibraryDigital Library
  27. [27] Hossain M. S. and Muhammad G.. 2019. Emotion recognition using deep learning approach from audio-visual emotional big data. Information Fusion 49 (2019), 6978. https://doi.org/10.1016/j.inffus.2018.09.008Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. [28] Hossain M. S., Muhammad G., and Alamri A.. 2019. A smart healthcare monitoring: A voice pathology detection paradigm for smart cities. Multimedia Systems 25 (2019), 565575.Google ScholarGoogle ScholarCross RefCross Ref
  29. [29] Muhammad G. et al. 2020. EEG-based pathology detection for home health monitoring. IEEE Journal on Selected Areas in Communications 39, 2 (2020), 603–610.Google ScholarGoogle Scholar
  30. [30] Murray V., Agurto C., Barriga S., Pattichis M. S., and Soliz P.. 2012. Real-time diabetic retinopathy patient screening using multiscale AM-FM methods. In 2012 19th IEEE International Conference on Image Processing. 525528.Google ScholarGoogle ScholarCross RefCross Ref
  31. [31] Niemeijer M., Ginneken B. Van, Russell S. R., Suttorp-Schulten M. S., and Abràmoff M. D.. 2007. Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis. Investigative Ophthalmology and Visual Science 48, 5 (May 2007), 22602267.Google ScholarGoogle ScholarCross RefCross Ref
  32. [32] Prakash Nattanmai Balasubramanian, Selvathi D., and Hemalakshmi Giri Rajanbabu. 2014. Development of algorithm for dual stage classification to estimate severity level of diabetic retinopathy in retinal images using soft computing techniques. International Journal on Electrical Engineering and Informatics 6, 4 (Dec. 2014), 598606.Google ScholarGoogle ScholarCross RefCross Ref
  33. [33] Ruder Sebastian. 2021. An Overview of Gradient Descent Optimization Algorithms. Retrieved May 29, 2021, from https://ruder.io/optimizing-gradient-descent/.Google ScholarGoogle Scholar
  34. [34] Russakovsky Olga, Deng Jia, Su Hao, Krause Jonathan, Satheesh Sanjeev, Ma Sean, Huang Zhiheng, Karpathy Andrej, Khosla Aditya, Bernstein Michael, Berg Alexander C., and Fei-Fei Li. 2015. ImageNet large scale visual recognition challenge. International Journal of Computer Vision 115, 3 (Dec. 2015), 211252. https://doi.org/10.1007/s11263-015-0816-y Google ScholarGoogle ScholarDigital LibraryDigital Library
  35. [35] Sakaguchi Aiki, Wu Renjie, and Kamata Sei-ichiro. 2019. Fundus image classification for diabetic retinopathy using disease severity grading. Association for Computing Machinery, New York, NY. https://doi.org/10.1145/3326172.3326198 Google ScholarGoogle ScholarDigital LibraryDigital Library
  36. [36] Saleh Emran, Baszczyski Jerzy, Moreno Antonio, Valls Aida, Romero-Aroca Pedro, Riva-Fernndez Sofia de la, and Sowiski Roman. 2018. Learning ensemble classifiers for diabetic retinopathy assessment. Artificial Intelligence in Medicine 85, C (April 2018), 5063. https://doi.org/10.1016/j.artmed.2017.09.006 Google ScholarGoogle ScholarDigital LibraryDigital Library
  37. [37] Shankar K., Sait Abdul Rahaman Wahab, Gupta Deepak, Lakshmanaprabu S. K., Khanna Ashish, and Pandey Hari Mohan. 2020. Automated detection and classification of fundus diabetic retinopathy images using synergic deep learning model. Pattern Recognition Letters 133 (2020), 210216. https://doi.org/10.1016/j.patrec.2020.02.026Google ScholarGoogle ScholarCross RefCross Ref
  38. [38] Sikder Niloy, Masud Mehedi, Bairagi Anupam Kumar, Arif Abu Shamim Mohammad, Nahid Abdullah-Al, and Alhumyani Hesham A.. 2021. Severity classification of diabetic retinopathy using an ensemble learning algorithm through analyzing retinal images. Symmetry 13, 4 (2021), 1–26. https://www.mdpi.com/2073-8994/13/4/670,DOI=10.3390/sym13040670.Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Simó Rafael and Hernández Cristina. 2009. Advances in the medical treatment of diabetic retinopathy. Diabetes Care 32, 8 (2009), 15561562. https://doi.org/10.2337/dc09-0565 arXiv: https://care.diabetesjournals.org/content/32/8/1556.full.pdf.Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Tajbakhsh N., Shin J. Y., Gurudu S. R., Hurst R. T., Kendall C. B., Gotway M. B., and Liang J.. 2016. Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE Transactions on Medical Imaging 35, 5 (2016), 12991312.Google ScholarGoogle ScholarCross RefCross Ref
  41. [41] Trivino Maria Camila Alvarez, Despraz Jérémie, Sotelo Jesús Alfonso López, and Peña Carlos Andrés. 2018. Deep learning on retina images as screening tool for diagnostic decision support. CoRR abs/1807.09232 (2018). arxiv:1807.09232 http://arxiv.org/abs/1807.09232.Google ScholarGoogle Scholar
  42. [42] Maaten Laurens van der and Hinton Geoffrey. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 25792605. http://jmlr.org/papers/v9/vandermaaten08a.html.Google ScholarGoogle Scholar
  43. [43] Yun W. L., Acharya U. R., Venkatesh Y. V., Chee C., Min L. C., and Ng E. Y. K.. 2008. Identification of different stages of diabetic retinopathy using retinal optical images. Information Sciences 178, 1 (Jan. 2008), 106121. https://doi.org/10.1016/j.ins.2007.07.020 Google ScholarGoogle ScholarDigital LibraryDigital Library
  44. [44] Yang X., Zhang T., Xu C., Yan S., Hossain M. S., and Ghoneim A.. 2016. Deep relative attributes. IEEE Transactions on Multimedia 18, 9 (2016), 18321842. Google ScholarGoogle ScholarDigital LibraryDigital Library
  45. [45] Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (May 2015), 436444. https://doi.org/10.1038/nature14539Google ScholarGoogle ScholarCross RefCross Ref
  46. [46] Zhou Y., Dong H., and Saddik A. El. 2020. Deep learning in next-frame prediction: A benchmark review. IEEE Access 8 (2020), 6927369283. https://doi.org/10.1109/ACCESS.2020.2987281Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. A Convolutional Neural Network Model Using Weighted Loss Function to Detect Diabetic Retinopathy

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image ACM Transactions on Multimedia Computing, Communications, and Applications
        ACM Transactions on Multimedia Computing, Communications, and Applications  Volume 18, Issue 1s
        February 2022
        352 pages
        ISSN:1551-6857
        EISSN:1551-6865
        DOI:10.1145/3505206
        Issue’s Table of Contents

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 25 January 2022
        • Revised: 1 June 2021
        • Accepted: 1 June 2021
        • Received: 1 November 2020
        Published in tomm Volume 18, Issue 1s

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
        • Refereed

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      View Full Text

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!