İki göz hastalığı veri seti üzerinde transfer öğrenme tabanlı derin öğrenme modeli ile fundus görüntülerinden katarakt hastalığı sınıflandırması

Yıl 2023, Cilt: 13 Sayı: 2, 258 - 269, 15.04.2023

Halit Çetiner

https://doi.org/10.17714/gumusfenbil.1168842

Cited By: 5

Öz

Katarakt, tedavi edilmediği takdirde kör edebilen en ciddi göz hastalıklarından biridir. Hastalığın ileri aşamalarından ziyade erken aşamada tespit edilmesi hastanın kör olmasının önüne geçebilmektedir. Bu noktada şüphe duyulan hastaların sürekli olarak kontrol edilmesi gerekmektedir. Sürekli olarak hastaların kontrol ve takip edilmesi ise yorucu ve zahmetli bir işlemdir. Belirtilen sebeplerden dolayı bu makalede katarakt tanı ve tespitinde kullanılabilecek göz doktorlarının yaptıkları iş ve işlemlere yardımcı iki farklı derin öğrenme modeli önerilmiştir. Önerilen derin öğrenme modelleri normal ve katarakt belirtilerine sahip fundus veri seti üzerinde çalıştırılmıştır. Önerilen derin öğrenme modelleri normal ve kataraktlı görüntülerin otomatik olarak sınıflandırmasını sağlamaktadır. MobileNet V3 Small adlı önceden eğitilmiş derin öğrenme modeli kullanılarak üst katmanda ince ayarlamalar ve katman eklemeleri gerçekleştirilmiştir. Üst katmanlarında ince ayarlamalar ve katman eklemeleri yapılarak zenginleştirilen modelin performans değerlendirmesini yapabilmek için temel bir MobileNet V3 Small modeli de oluşturulmuştur. Önerilen model ile temel model arasındaki fark katarakt ve normal görüntülerin sınıflandırma performanslarını karşılaştırılarak doğruluk ve karmaşıklık matris ölçümleri ile gösterilmiştir. K Katlı seçeneğine göre eğitim ve test verileri ayrılarak yapılan performans karşılaştırmalarında elde edilen en iyi sonuçlara göre önerilen model, temel modelden 8.26% daha başarılı bir sonuç grafiği vermiştir. Son olarak, önerilen MobileNet V3 modeli, iki farklı veri setinin birleşmesinden oluşan görüntüler üzerinde de test edilmiştir. Ortalama olarak birleştirilmiş veri seti üzerinde önerilen MobileNet V3 modeli ile %96.62 doğruluk oranına ulaşmıştır.

Anahtar Kelimeler

Transfer öğrenme, MobileNet V3, MobileNet V3 Small, Derin öğrenme, katarakt

Cataract disease classification from fundus images with transfer learning based deep learning model on two ocular disease datasets

Öz

Cataract is one of the most serious eye diseases that can blind if left untreated. Detection of the disease in the early stages rather than in the advanced stages can prevent the patient from being blind. At this point, suspected patients should be constantly checked. Continuous control and follow-up of patients is a tiring and laborious process. For the reasons stated, two different deep learning models are proposed in this article that can be used in the diagnosis and detection of cataracts to assist the work and procedures of ophthalmologists. The proposed deep learning models were run on a fundus dataset with normal and cataract symptoms. The proposed deep learning models provide automatic classification of normal and cataract images. Fine-tuning and layer additions were performed on the upper layer using a pre-trained deep learning model called MobileNet V3 Small. A basic MobileNet V3 Small model has also been created to evaluate the performance of the model, which has been enriched by fine-tuning and adding layers to its upper layers. The difference between the proposed model and the basic model is demonstrated by comparing the classification performances of cataract and normal images with accuracy and complexity matrix measurements. According to the best results obtained in the performance comparisons made by separating the training and test data according to the KFold option, the proposed model gave a more successful result graph of 8.26% than the basic model. Finally, the proposed MobileNet V3 model has also been tested on images composed of two different datasets. On average, the proposed MobileNet V3 model on the combined dataset reached 96.62% accuracy.

Anahtar Kelimeler

Transfer learning, MobileNet V3, MobileNet V3 Small, Deep learning, Cataract

Kaynakça

• Avenash, R., & Viswanath, P. (2019). Semantic Segmentation of Satellite Images using a Modified CNN with Hard-Swish Activation Function. VISIGRAPP (4: VISAPP), 413–420.
• Bakator, M., & Radosav, D. (2018). Deep Learning and Medical Diagnosis: A Review of Literature. In Multimodal Technologies and Interaction (Vol. 2, Issue 3). https://doi.org/10.3390/mti2030047
• Cao, L., Li, H., Zhang, Y., Zhang, L., & Xu, L. (2020). Hierarchical method for cataract grading based on retinal images using improved Haar wavelet. Information Fusion, 53, 196–208.
• Çetiner, H., & Çetiner, İ. (2022). Classification of Cataract Disease with a DenseNet201 Based Deep Learning Model. Journal, 12(3), 1264–1276.
• Chen, Y. (2022). Retina Dataset. https://github.com/yiweichen04/retina_dataset
• Doi, K. (2007). Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Computerized Medical Imaging and Graphics, 31(4–5), 198–211.
• Ertuğrul, Ö. F., Acar, E., Aldemir, E., & Öztekin, A. (2021). Automatic diagnosis of cardiovascular disorders by sub images of the ECG signal using multi-feature extraction methods and randomized neural network. Biomedical Signal Processing and Control, 64, 102260. https://doi.org/10.1016/j.bspc.2020.102260
• Fan, W., Shen, R., Zhang, Q., Yang, J.-J., & Li, J. (2015). Principal component analysis based cataract grading and classification. 2015 17th International Conference on E-Health Networking, Application & Services (HealthCom), 459–462. https://doi.org/10.1109/HealthCom.2015.7454545
• Flaxman, S. R., Bourne, R. R. A., Resnikoff, S., Ackland, P., Braithwaite, T., Cicinelli, M. V, Das, A., Jonas, J. B., Keeffe, J., & Kempen, J. H. (2017). Global causes of blindness and distance vision impairment 1990–2020: a systematic review and meta-analysis. The Lancet Global Health, 5(12), e1221–e1234.
• Fraser, M. L., Meuleners, L. B., Lee, A. H., Ng, J. Q., & Morlet, N. (2013). Vision, quality of life and depressive symptoms after first eye cataract surgery. Psychogeriatrics, 13(4), 237–243.
• Gao, X., Lin, S., & Wong, T. Y. (2015). Automatic feature learning to grade nuclear cataracts based on deep learning. IEEE Transactions on Biomedical Engineering, 62(11), 2693–2701.
• Goutte, C., & Gaussier, E. (2005). A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation. In Lecture Notes in Computer Science (Vol. 3408, pp. 345–359). https://doi.org/10.1007/978-3-540-31865-1_25
• Grewal, P. S., Oloumi, F., Rubin, U., & Tennant, M. T. S. (2018). Deep learning in ophthalmology: a review. Canadian Journal of Ophthalmology, 53(4), 309–313. https://doi.org/https://doi.org/10.1016/j.jcjo.2018.04.019
• Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. ArXiv Preprint ArXiv:1704.04861.
• Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., & Vasudevan, V. (2019). Searching for mobilenetv3. Proceedings of the IEEE/CVF International Conference on Computer Vision, 1314–1324.
• Hu, S., Wang, X., Wu, H., Luan, X., Qi, P., Lin, Y., He, X., & He, W. (2020). Unified diagnosis framework for automated nuclear cataract grading based on smartphone slit-lamp images. IEEE Access, 8, 174169–174178.
• Imran, A., Li, J., Pei, Y., Akhtar, F., Mahmood, T., & Zhang, L. (2021). Fundus image-based cataract classification using a hybrid convolutional and recurrent neural network. The Visual Computer, 37(8), 2407–2417. https://doi.org/10.1007/s00371-020-01994-3
• Jayachitra, S., Nitheesh Kanna, K., Pavithra, G., & Ranjeetha, T. (2021). A Novel Eye Cataract Diagnosis and Classification Using Deep Neural Network. Journal of Physics: Conference Series, 1937(1). https://doi.org/10.1088/1742-6596/1937/1/012053
• Junayed, M. S., Islam, M. B., Sadeghzadeh, A., & Rahman, S. (2021). CataractNet: An Automated Cataract Detection System Using Deep Learning for Fundus Images. IEEE Access, 9, 128799–128808. https://doi.org/10.1109/ACCESS.2021.3112938
• K S, Y., Mithra, N. M., KS, V., & R, K. (2021). Classification of diabetic retinopathy through identification of diagnostic keywords. 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), 716–721. https://doi.org/10.1109/ICIRCA51532.2021.9544621
• Khan, M. S., Tafshir, N., Alam, K. N., Dhruba, A. R., Khan, M. M., Albraikan, A. A., & Almalki, F. A. (2022). Deep Learning for Ocular Disease Recognition: An Inner-Class Balance. Computational Intelligence and Neuroscience, 2022.
• Kumar, B. R., & Shimna, M. P. (2017). Recent approaches for automatic cataract detection analysis using image processing. Journal of Network Communications and Emerging Technologies (JNCET), 7(10).
• Kumar, Y., & Gupta, S. (2022). Deep Transfer Learning Approaches to Predict Glaucoma, Cataract, Choroidal Neovascularization, Diabetic Macular Edema, DRUSEN and Healthy Eyes: An Experimental Review. Archives of Computational Methods in Engineering. https://doi.org/10.1007/s11831-022-09807-7
• Lee, A., Taylor, P., Kalpathy-Cramer, J., & Tufail, A. (2017). Machine Learning Has Arrived! Ophthalmology, 124(12), 1726–1728. https://doi.org/10.1016/j.ophtha.2017.08.046
• Liu, X., Jiang, J., Zhang, K., Long, E., Cui, J., Zhu, M., An, Y., Zhang, J., Liu, Z., & Lin, Z. (2017). Localization and diagnosis framework for pediatric cataracts based on slit-lamp images using deep features of a convolutional neural network. PloS One, 12(3), e0168606.
• Manchalwar, M., & Warhade, K. (2017). Detection of Cataract and Conjunctivitis Disease Using Histogram of Oriented Gradient. International Journal of Engineering and Technology, 9, 2400–2406. https://doi.org/10.21817/ijet/2017/v9i3/1709030214
• Mercioni, M. A., & Holban, S. (2020). P-Swish: Activation Function with Learnable Parameters Based on Swish Activation Function in Deep Learning. 2020 International Symposium on Electronics and Telecommunications (ISETC), 1–4. https://doi.org/10.1109/ISETC50328.2020.9301059
• Ocular Disease Recognition. (2021). Senior Data Scientist at Hospital Israelita Albert Einstein São Paulo, State of São Paulo, Brazil.
• Organization, W. H. (1998). The World health report: 1998: Life in the 21st century: a vision for all: executive summary. World Health Organization.
• Pascolini, D., & Mariotti, S. P. (2012). Global estimates of visual impairment: 2010. British Journal of Ophthalmology, 96(5), 614–618.
• Qian, S., Ning, C., & Hu, Y. (2021). MobileNetV3 for Image Classification. 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), 490–497. https://doi.org/10.1109/ICBAIE52039.2021.9389905
• Qiao, Z., Zhang, Q., Dong, Y., & Yang, J. (2017). Application of SVM based on genetic algorithm in classification of cataract fundus images. 2017 IEEE International Conference on Imaging Systems and Techniques (IST), 1–5. https://doi.org/10.1109/IST.2017.8261541
• Raju, B., Raju, N. S. D., Akkara, J. D., & Pathengay, A. (2016). Do it yourself smartphone fundus camera–DIYretCAM. Indian Journal of Ophthalmology, 64(9), 663.
• Rana, J., & Galib, S. M. (2017). Cataract detection using smartphone. 2017 3rd International Conference on Electrical Information and Communication Technology (EICT), 1–4. https://doi.org/10.1109/EICT.2017.8275136
• Roy, A. M., Bose, R., & Bhaduri, J. (2022). A fast accurate fine-grain object detection model based on YOLOv4 deep neural network. Neural Computing and Applications, 34(5), 3895–3921. https://doi.org/10.1007/s00521-021-06651-x
• Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520.
• Triyadi, A. B., Bustamam, A., & Anki, P. (2022). Deep Learning in Image Classification using VGG-19 and Residual Networks for Cataract Detection. 2022 2nd International Conference on Information Technology and Education (ICIT&E), 293–297.
• Wang, Y., Tang, C., Wang, J., Sang, Y., & Lv, J. (2021). Cataract detection based on ocular B-ultrasound images by collaborative monitoring deep learning. Knowledge-Based Systems, 231, 107442. https://doi.org/10.1016/j.knosys.2021.107442
• Xiong, L., Li, H., & Xu, L. (2017). An Approach to Evaluate Blurriness in Retinal Images with Vitreous Opacity for Cataract Diagnosis. Journal of Healthcare Engineering, 2017, 1–16. https://doi.org/10.1155/2017/5645498
• Yang, J.-J., Li, J., Shen, R., Zeng, Y., He, J., Bi, J., Li, Y., Zhang, Q., Peng, L., & Wang, Q. (2016). Exploiting ensemble learning for automatic cataract detection and grading. Computer Methods and Programs in Biomedicine, 124, 45–57.
• Zhang, L., Li, J., Zhang, i, Han, H., Liu, B., Yang, J., & Wang, Q. (2017). Automatic cataract detection and grading using Deep Convolutional Neural Network. 2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC), 60–65. https://doi.org/10.1109/ICNSC.2017.8000068