Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Data Efficient Image Classification for Retinal Disease Diagnosis

데이터 효율적 이미지 분류를 통한 안질환 진단

  • Honggu Kang (Dept. of AI Systems Engineering, Sungkyunkwan University) ;
  • Huigyu Yang (Convergence Research Institute, Sungkyunkwan University) ;
  • Moonseong Kim (Dept. of IT Convergence Software, Seoul Theological University) ;
  • Hyunseung Choo (Dept. of Electrical and Computer Engineering, Sungkyunkwan, University)
  • 강홍구 ;
  • 양희규 ;
  • 김문성 ;
  • 추현승
  • Received : 2024.03.28
  • Accepted : 2024.05.20
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

The worldwide aging population trend is causing an increase in the incidence of major retinal diseases that can lead to blindness, including glaucoma, cataract, and macular degeneration. In the field of ophthalmology, there is a focused interest in diagnosing diseases that are difficult to prevent in order to reduce the rate of blindness. This study proposes a deep learning approach to accurately diagnose ocular diseases in fundus photographs using less data than traditional methods. For this, Convolutional Neural Network (CNN) models capable of effective learning with limited data were selected to classify Conventional Fundus Images (CFI) from various ocular disease patients. The chosen CNN models demonstrated exceptional performance, achieving high Accuracy, Precision, Recall, and F1-score values. This approach reduces manual analysis by ophthalmologists, shortens consultation times, and provides consistent diagnostic results, making it an efficient and accurate diagnostic tool in the medical field.

전 세계적인 인구 고령화 현상으로, 녹내장, 백내장, 황반변성과 같은 실명을 초래할 수 있는 주요 안질환의 발병률이 상승하고 있다. 이에 안과 분야에서는 실명률을 줄이기 위해 예방이 어려운 질환의 진단에 관심이 집중되고 있다. 본 연구는 기존보다 적은 양의 데이터를 활용하여 안저 사진 내의 안질환을 정확하게 진단하는 딥러닝 방안을 제안한다. 이를 위해 적은 데이터로도 효과적인 학습이 가능한 Convolutional Neural Network (CNN) 모델을 선정하여 다양한 안질환 환자의 Conventional Fundus Image (CFI)를 분류 한다. 선정된 CNN 모델들은 Accuracy, Precision, Recall, F1-score에서 우수한 성능을 기록함으로써 CFI 내 안질환의 정확한 분류에 탁월한 성능을 보였다. 이러한 접근법은 안과 전문의들의 수작업 분석을 줄이고, 진료 시간을 단축하며, 리소스가 제한된 환경에서도 일관성 있는 진단 결과를 제공함으로써 의료 현장에 효율적이고 정확한 진단의 보조 도구로 기여할 수 있다.

Keywords

Acknowledgement

본 연구는 과학기술정보통신부 및 정보통신기획평가원의 ICT명품인재양성사업(IITP-2024-2020-0-01821, 70%)과 인공지능 혁신 허브 연구 개발(No.RS-2021-II212068, 30%)의 지원을 받아 수행된 연구임.

References

  1. J. Banks, "Looking Disease in the Eye," IEEE pulse, Vol. 12, No. 6, pp. 10-13, 2021. https://doi.org/10.1109/MPULS.2021.3128976
  2. Poplin, R., Varadarajan, A.V., Blumer, K. et al. "Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning," Nature Biomedical Engineering Vol. 2, pp. 158-164, 2018. https://doi.org/10.1038/s41551-018-0195-0
  3. Schuster AK, Erb C, Hoffmann EM, Dietlein T, and Pfeiffer N, "The Diagnosis and Treatment of Glaucoma," Deutsches Arzteblatt International, Vol. 117, No. 13, pp. 225-234, 2020. https://doi.org/10.3238/arztebl.2020.0225
  4. Norah Asiri, Muhammad Hussain, Fadwa Al Adel, Nazih Alzaidi, "Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey," Artificial Intelligence in Medicine, Vol. 99, 2019. https://doi.org/10.1016/j.artmed.2019.07.009
  5. Keel S, Wu J, Lee PY, Scheetz J, and He M, "Visualizing Deep Learning Models for the Detection of Referable Diabetic Retinopathy and Glaucoma," JAMA Ophthalmology, Vol. 137, No. 3, pp. 288-292, 2019. https://doi.org/10.1001/jamaophthalmol.2018.6035
  6. V. -N. Pham, D. -T. Le, J. Bum, E. J. Lee, J. C. Han and H. Choo, "Attention-Aided Generative Learning for Multi-Scale Multi-Modal Fundus Image Translation," IEEE Access, Vol. 11, pp. 51701-51711, 2023. https://doi.org/10.1109/ACCESS.2023.3278596
  7. D. Romo-Bucheli, U. S. Erfurth and H. Bogunovic, "End-to-End Deep Learning Model for Predicting Treatment Requirements in Neovascular AMD From Longitudinal Retinal OCT Imaging," IEEE Journal of Biomedical and Health Informatics, Vol. 24, No. 12, pp. 3456-3465, 2020. https://doi.org/10.1109/JBHI.2020.3000136
  8. T. Guergueb and M. A. Akhloufi, "Ocular Diseases Detection using Recent Deep Learning Techniques," 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Mexico, pp. 3336-3339, 2021. https://doi.org/10.1109/EMBC46164.2021.9629763
  9. Puneet, Kumar, R. and Gupta, M., "Optical coherence tomography image based eye disease detection using deep convolutional neural network," Health Inf Sci Syst, Vol. 10, No. 13, 2022. https://doi.org/10.1007/s13755-022-00182-y
  10. Cen, L. P., Ji, J., Lin, J. W., Ju, S. T., Lin, H. J., Li, T. P., ... and Zhang, M., "Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks," Nature Communications, Vol. 12, No. 1, p. 4828, 2021. https://doi.org/10.1038/s41467-021-25138-w
  11. Li, Z., Guo, C., Nie, D., Lin, D., Cui, T., Zhu, Y., ... and Lin, H., "Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning," Eye, Vol. 36, No. 8, pp. 1681-1686, 2022. https://doi.org/10.1038/s41433-021-01715-7
  12. Sahlsten, J., Jaskari, J., Kivinen, J., Turunen, L., Jaanio, E., Hietala, K., and Kaski, K., "Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading," Scientific Reports, Vol. 9, No. 1, p. 10750, 2019. https://doi.org/10.1038/s41598-019-47181-w
  13. Abu Kowshir Bitto and Imran Mahmud, "Multi categorical of common eye disease detect using convolutional neural network: a transfer learning approach," Bulletin of Electrical Engineering and Informatics, Vol. 11, No. 4, pp. 2378-2387, 2022. https://doi.org/10.11591/eei.v11i4.3834
  14. M. S. Junayed, M. B. Islam, A. Sadeghzadeh and S. Rahman, "CataractNet: An Automated Cataract Detection System Using Deep Learning for Fundus Images," IEEE Access, Vol. 9, pp. 128799-128808, 2021. https://doi.org/10.1109/ACCESS.2021.3112938
  15. Karthikeyan, S., Sanjay, K. P., Madhusudan, R. J., Sundaramoorthy, S. K., and Krishnan Namboori, P. K., "Detection of multi-class retinal diseases using artificial intelligence: An expeditious learning using deep CNN with minimal data," Biomedical & Pharmacology Journal, Vol. 12, No. 3, pp. 1577-1586, 2019. https://doi.org/10.13005/bpj/1788
  16. S. Ko, H. Yang, M. Kim, and H. Choo, "3D Medical Image Data Augmentation for CT Image Segmentation," Journal of Internet Computing and Services, Vol. 24, No. 4, pp. 85-92, 2023. https://doi.org/10.7472/jksii.2023.24.4.85
  17. He, K., Zhang, X., Ren, S., and Sun, J., "Deep residual learning for image recognition," Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016. https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html
  18. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q., "Densely connected convolutional networks," Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700- 4708, 2017. https://openaccess.thecvf.com/content_cvpr_2017/html/Huang_Densely_Connected_Convolutional_CVPR_2017_ paper.html
  19. Tan, Mingxing, and Quoc Le., "Efficientnet: Rethinking model scaling for convolutional neural networks," International conference on machine learning, pp. 6105-6114, 2019. https://proceedings.mlr.press/v97/tan19a.html