Differential Diagnosis of Diabetic Foot with Deep Learning Methods

Year 2023, , 288 - 305, 31.12.2023

Maide Çakır Bayer , Hüseyin Canbolat , Gökalp Tulum

https://doi.org/10.53501/rteufemud.1377390

Abstract

Diabetic foot complications, caused by prolonged hyperglycemia, are a significant health concern among diabetes patients. Majority of patients develop diabetic foot complications, contributing significantly to diabetes-related hospital admissions. These complications include foot ulcers, infections, ischemia, Charcot foot, and neuropathy. They also increase the risk of amputation, affecting quality of life and putting strain on healthcare systems. At this stage, early diagnosis plays a vital role. The process of diagnosing involves not only identifying the presence or absence of a disease, but also categorizing the disease. In this study, we examine the use of deep learning methods in the diagnosis of diabetic foot conditions. It explores various aspects such as predictive modeling and image analysis. The study discusses the progression of model designs, data sources, and interpretability methodologies, with a focus on improving accuracy and early detection. Overall, the study provides a comprehensive analysis of the current state of deep learning in diabetic foot problems with highlighting advancements.

Keywords

Deep learning, differential diagnosis, diabetic foot, classification.

Diyabetik Ayağın Derin Öğrenme Yöntemleriyle Ayırıcı Tanısı

Abstract

Uzun süreli hipergliseminin neden olduğu diyabetik ayak komplikasyonları diyabet hastaları arasında önemli bir sağlık sorunudur. Hastaların çoğunda diyabetik ayak komplikasyonları gelişir ve bu da diyabetle ilişkili hastaneye başvurulara önemli ölçüde sebebiyet verir. Bu komplikasyonlar arasında ayak ülserleri, enfeksiyonlar, iskemi, Charcot ayağı ve nöropati yer alır. Ayrıca amputasyon riskini artırarak yaşam kalitesini etkiler ve sağlık sistemleri üzerinde baskı yaratır. Bu aşamada erken teşhis hayati önem taşır. Teşhis süreci yalnızca bir hastalığın varlığını veya yokluğunu belirlemeyi değil aynı zamanda hastalığın kategorize edilmesini de içerir. Bu çalışmada diyabetik ayak rahatsızlıklarının tanısında derin öğrenme yöntemlerinin kullanımı incelenmiştir. Çalışma, tahmine dayalı modelleme ve resim analizi de dahil olmak üzere farklı yönleri de ele alır. Doğruluğun ve erken tespitin geliştirilmesine odaklanarak model tasarımlarının, veri kaynaklarının ve yorumlanabilirlik metodolojilerinin ilerleyişini tartışır. Genel olarak bu çalışma, diyabetik ayak problemlerinde derin öğrenmenin mevcut durumunun kapsamlı bir analizini ve ilerlemelerin altını çizmektedir.

Keywords

Derin öğrenme, ayırıcı tanı, diyabetik ayak, sınıflandırma

References

• Ahsan, M., Naz, S., Ahmad, R., Ehsan, H., and Sikandar, A. (2023). A deep learning approach for diabetic foot ulcer classification and recognition. Information, 14(1), 36. https://doi.org/10.3390/info14010036
• Alzubaidi, L., Fadhel, M. A., Oleiwi, S. R., Al-Shamma, O., and Zhang, J. (2020). DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network. Multimedia Tools and Applications, 79(21-22), 15655-15677. https://doi.org/10.1007/s11042-019-07820-w
• Amin, J., Sharif, M., Anjum, M. A., Khan, H. U., Malik, M. S. A., and Kadry, S. (2020). An integrated design for classification and localization of diabetic foot ulcer based on CNN and YOLOv2-DFU models. IEEE Access, 8, 228586-228597. https://doi.org/10.1109/ACCESS.2020.3045732
• Anaya-Isaza, A., and Zequera-Diaz, M. (2022a). Detection of diabetes mellitus with deep learning and data augmentation techniques on foot thermography. IEEE Access, 10, 59564-59591. https://doi.org/10.1109/ACCESS.2022.3180036
• Anaya-Isaza, A., and Zequera-Diaz, M. (2022b). Fourier transform-based data augmentation in deep learning for diabetic foot thermograph classification. Biocybernetics and Biomedical Engineering, 42(2), 437-452. https://doi.org/10.1016/j.bbe.2022.03.001
• Basiri, R., Popovic, M. R., and Khan, S. S. (2022). Domain-Specific Deep Learning Feature Extractor for Diabetic Foot Ulcer Detection. IEEE International Conference on Data Mining Workshops (ICDMW), 2022, Orlando, FL, USA. https://doi.org/10.1109/ICDMW58026.2022.00041
• Belsti, Y., Akalu, Y., and Animut, Y. (2020). Attitude, practice and its associated factors towards Diabetes complications among type 2 diabetic patients at Addis Zemen District hospital, Northwest Ethiopia. BMC Public Health, 20, 1-11. https://doi.org/10.1186/s12889-020-08953-6
• Bengio, Y., Simard, P., and Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE transactions on neural networks, 5(2), 157-166. https://doi.org/10.1109/72.279181
• Bouallal, D., Douzi, H., and Harba, R. (2022). Diabetic foot thermal image segmentation using Double Encoder-ResUnet (DE-ResUnet). Journal of Medical Engineering and Technology, 46(5), 378-392. https://doi.org/10.1080/03091902.2022.2077997
• Cao, C., Qiu, Y., Wang, Z., Ou, J., Wang, J., Hounye, A. H., . . . Zhang, J. (2023). Nested segmentation and multi-level classification of diabetic foot ulcer based on mask R-CNN. Multimedia Tools and Applications, 82(12), 18887-18906. https://doi.org/10.1007/s11042-022-14101-6
• Chamberlain, R. C., Fleetwood, K., Wild, S. H., Colhoun, H. M., Lindsay, R. S., Petrie, J. R., . . . Sattar, N. (2022). Foot ulcer and risk of lower limb amputation or death in people with diabetes: a national population-based retrospective cohort study. Diabetes Care, 45(1), 83-91. https://doi.org/10.2337/dc21-1596
• Chan, H.-P., Samala, R. K., Hadjiiski, L. M., and Zhou, C. (2020). Deep learning in medical image analysis. Deep Learning in Medical Image Analysis: Challenges and Applications, 3-21. https://doi.org/10.1007/978-3-030-33128-3_1
• Cruz-Vega, I., Hernandez-Contreras, D., Peregrina-Barreto, H., Rangel-Magdaleno, J. d. J., and Ramirez-Cortes, J. M. (2020). Deep learning classification for diabetic foot thermograms. Sensors, 20(6), 1762. https://doi.org/10.3390/s20061762
• Oliveira, A. L., de Carvalho, A. B., and Dantas, D. O. (2021). Faster R-CNN Approach for Diabetic Foot Ulcer Detection. 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP volume 4: 677-684p), 2021, Vienna, Austria. https://doi.org/10.5220/0010255506770684
• Das, S. K., Roy, P., and Mishra, A. K. (2022). DFU_SPNet: A stacked parallel convolution layers based CNN to improve Diabetic Foot Ulcer classification. ICT Express, 8(2), 271-275. https://doi.org/10.1016/j.icte.2021.08.022
• Das, S. K., Roy, P., Singh, P., Diwakar, M., Singh, V., Maurya, A., . . . Kim, J. (2023). Diabetic foot ulcer identification: A Review. Diagnostics, 13(12), 1998. https://doi.org/10.3390/diagnostics13121998
• Ferreira, A. C. B. H., Ferreira, D. D., Oliveira, H. C., de Resende, I. C., Anjos, A., and de Moraes Lopes, M. H. B. (2020). Competitive neural layer-based method to identify people with high risk for diabetic foot. Computers in biology and medicine, 120, 103744. https://doi.org/10.1016/j.compbiomed.2020.103744
• Gamage, C., Wijesinghe, I., and Perera, I. (2019). Automatic scoring of diabetic foot ulcers through deep CNN based feature extraction with low rank matrix factorization. IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 2019, Athens, Greece, 2019, pp. https://doi.org/10.1109/BIBE.2019.00069
• Goyal, M., Reeves, N. D., Davison, A. K., Rajbhandari, S., Spragg, J., and Yap, M. H. (2018). Dfunet: Convolutional neural networks for diabetic foot ulcer classification. IEEE Transactions on Emerging Topics in Computational Intelligence, 4(5), 728-739. https://doi.org/10.1109/TETCI.2018.2866254
• Goyal, M., Reeves, N. D., Rajbhandari, S., Ahmad, N., Wang, C., and Yap, M. H. (2020). Recognition of ischaemia and infection in diabetic foot ulcers: Dataset and techniques. Computers in Biology and Medicine, 117, 103616. https://doi.org/10.1016/j.compbiomed.2020.103616
• Harahap, M., Anjelli, S. K., Sinaga, W. A. M., Alward, R., Manawan, J. F. W., and Husein, A. M. (2022). Classification of diabetic foot ulcer using convolutional neural network (CNN) in diabetic patients. Jurnal Infotel, 14(3), 196-202. https://doi.org/10.20895/infotel.v14i3.796
• Hyun, J., Lee, Y., Son, H. M., Lee, S. H., Pham, V., Park, J. U., and Chung, T.-M. (2021). Synthetic data generation system for AI-based diabetic foot diagnosis. SN Computer Science, 2(5), 345. https://doi.org/10.1007/s42979-021-00667-9
• LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
• Liu, Z., Agu, E., Pedersen, P., Lindsay, C., Tulu, B., and Strong, D. (2023). Chronic wound ımage augmentation and assessment using semi-supervised progressive multi-granularity EfficientNet. IEEE Open Journal of Engineering in Medicine and Biology, (Early Access). https://doi.org/10.1109/OJEMB.2023.3248307
• Liu, Z., John, J., and Agu, E. (2022). Diabetic Foot Ulcer Ischemia and Infection Classification Using EfficientNet Deep Learning Models. IEEE Open Journal of Engineering in Medicine and Biology, 3, 189-201. https://doi.org/10.1109/OJEMB.2022.3219725
• Maltese, G., Koufakis, T., Kotsa, K., Basile, G., and Siow, R. (2023). Mediterranean diet, type 2 diabetes prevention and healthy ageing: do we need more evidence? Diabetes research and clinical practice (In Press, Journal Pre-proof),110928. https://doi.org/10.1016/j.diabres.2023.110928
• Min, S., Lee, B., and Yoon, S. (2017). Deep learning in bioinformatics. Briefings in bioinformatics, 18(5), 851-869. https://doi.org/10.1093/bib/bbw068
• Munadi, K., Saddami, K., Oktiana, M., Roslidar, R., Muchtar, K., Melinda, M., . . . Arnia, F. (2022). A deep learning method for early detection of diabetic foot using decision fusion and thermal images. Applied Sciences, 12(15), 7524. https://doi.org/10.3390/app12157524
• Ogurtsova, K., Guariguata, L., Barengo, N. C., Ruiz, P. L.-D., Sacre, J. W., Karuranga, S., . . . Magliano, D. J. (2022). IDF diabetes Atlas: Global estimates of undiagnosed diabetes in adults for 2021. Diabetes research and clinical practice, 183, 109118. https://doi.org/10.1016/j.diabres.2021.109118
• Prabhu, M. S., and Verma, S. (2021). A Deep Learning framework and its Implementation for Diabetic Foot Ulcer Classification. 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)(ICRITO), 2021, Noida, India. https://doi.org/10.1109/ICRITO51393.2021.9596380
• Rania, N., Douzi, H., Yves, L., Sylvie, T. (2020). Semantic Segmentation of Diabetic Foot Ulcer Images: Dealing with Small Dataset in DL Approaches. In: El Moataz, A., Mammass, D., Mansouri, A., Nouboud, F. (eds) Image and Signal Processing. ICISP 2020. Lecture Notes in Computer Science(), vol 12119. https://doi.org/10.1007/978-3-030-51935-3_17
• Reardon, R., Simring, D., Kim, B., Mortensen, J., Williams, D., and Leslie, A. (2020). The diabetic foot ulcer. Australian Journal of General Practice, 49(5), 250-255. https://doi.org/10.31128/AJGP-11-19-5161
• Reyes-Luévano, J., Guerrero-Viramontes, J., Romo-Andrade, J. R., and Funes-Gallanzi, M. (2023). DFU_VIRNet: A novel Visible-InfraRed CNN to improve diabetic foot ulcer classification and early detection of ulcer risk zones. Biomedical Signal Processing and Control, 86, 105341. https://doi.org/10.1016/j.bspc.2023.105341
• Roback, K. (2010). An overview of temperature monitoring devices for early detection of diabetic foot disorders. Expert review of medical devices, 7(5), 711-718. https://doi.org/10.1586/erd.10.35
• Sharma, N., Mirza, S., Rastogi, A., and Mahapatra, P. K. (2023). Utilizing Mask R-CNN for automated evaluation of diabetic foot ulcer healing trajectories: A novel approach. Traitement du Signal, 40(4). https://doi.org/10.18280/ts.400428
• Tan, M., and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. Paper presented at the International conference on machine learning. https://doi.org/10.48550/arXiv.1905.11946
• Toofanee, M. S. A., Dowlut, S., Hamroun, M., Tamine, K., Duong, A. K., Petit, V., and Sauveron, D. (2023). DFU-Helper: An innovative framework for longitudinal diabetic foot ulcer diseases evaluation using deep learning. Applied Sciences, 13(18), 10310. https://doi.org/10.3390/app131810310
• Wang, Y., Jia, Y., Tian, Y., and Xiao, J. (2022). Deep reinforcement learning with the confusion-matrix-based dynamic reward function for customer credit scoring. Expert Systems with Applications, 200, 117013. https://doi.org/10.1016/j.eswa.2022.117013
• Yap, M. H., Cassidy, B., Pappachan, J. M., O’Shea, C., Gillespie, D., and Reeves, N. D. (2021a). Analysis towards classification of infection and ischaemia of diabetic foot ulcers. IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), 2021, Athens, Greece. https://doi.org/10.1109/BHI50953.2021.9508563
• Yap, M. H., Hachiuma, R., Alavi, A., Brüngel, R., Cassidy, B., Goyal, M.,. Huang, X. (2021b). Deep learning in diabetic foot ulcers detection: A comprehensive evaluation. Computers in biology and medicine, 135, 104596. https://doi.org/10.1016/j.compbiomed.2021.104596
• Zhang, J., Qiu, Y., Peng, L., Zhou, Q., Wang, Z., and Qi, M. (2022). A comprehensive review of methods based on deep learning for diabetes-related foot ulcers. Frontiers in Endocrinology, 13, 945020. https://doi.org/10.3389/fendo.2022.945020
• Zhu, T., Li, K., Herrero, P., and Georgiou, P. (2020). Deep learning for diabetes: a systematic review. IEEE Journal of Biomedical and Health Informatics, 25(7), 2744-2757. https://doi.org/10.1109/JBHI.2020.3040225