Automated Analysis Of Diabetic Vasculopathy Using Semantic Segmentation Of Thermal Images Of Peroneal Vessel
DOI:
https://doi.org/10.56294/dm2024.367Keywords:
Diabetic Vasculopathy (DV), Semantic Segmentation (SS), Thermoregulation Imaging, Unet++, MobileNetV2, Deep Learning (DL)Abstract
Introduction: Diabetic vascular disease is one of most serious health problems in diabetic patients, it causes the development of severe complications including delayed wound healing and increased susceptibility to infections.
Methods: To provide accurate and are non-invasive diagnosis, current work emphasizes on Diabetic Vasculopathy (DV) that is analysed with thermoregulation images through Semantic Segmentation (SS). A novel methodology was adapted, combining thermoregulation imaging with SS using the U-Net++ model to investigate temperature distributions at the skin level. This work introduces a novel method that utilizes MobileNetV2 as the encoder for fast Feature Extraction (FE).
Results: The results from the suggested model, achieves a segmentation accuracy of 95%, which is significantly more compared to that of DeepLabV3+ and PSPNet models. A mean and Intersection over Union (IoU) of 85% and 87% was reported by the suggested frameworks throughout the training and validation phases.
Conclusion: Classifying normal and abnormal regions can be done via the outcomes, as it offers the great visibility in the thermal image for clinicians by detecting the non-thermal regions
References
1. Gururajarao SB, Venkatappa U, Shivaram JM, Sikkandar MY, and Al Amoudi A. Infrared thermography and soft computing for diabetic foot assessment. In Machine Learning in Bio-Signal Analysis and Diagnostic Imaging, pp. 73-97. https://doi.org/10.1016/B978-0-12-816086-2.00004-7.
2. Patel K, Horak H, and Tiryaki E. Diabetic neuropathies. Muscle & Nerve, 63(1), pp. 22-30. https://doi.org/10.1002/mus.27014.
3. Yavuz DG. Classification, risk factors, and clinical presentation diabetic neuropathy. In Diabetic neuropathy, pp. 1-9. https://doi.org/10.1016/B978-0-12-820669-0.00014-1
4. Sloan G, Pan Q, Gao L, Guo L, and Tesfaye S. Clinical Features of Diabetes Neuropathies. In Diabetic Neuropathy: Advances in Pathophysiology and Clinical Management, pp. 37-49. https://doi.org/10.1007/978-3-031-15613-7_3.
5. Tsakiridis I, Mamopoulos A, Athanasiadis A, Kourtis A, and Dagklis T. Management of pregestational diabetes mellitus: a comparison of guidelines. The Journal of Maternal-Fetal & Neonatal Medicine, 35(3), pp. 423-432. https://doi.org/10.1080/14767058.2020.1719481.
6. Qin X, Chen D, Zhan Y, and Yin D. Classification of diabetic retinopathy based on improved deep forest model. Biomedical signal processing and control, 79, p. 104020. https://doi.org/10.1016/j.bspc.2022.104020.
7. Gizińska M, Rutkowski R, Szymczak-Bartz L, Romanowski W, and Straburzyńska-Lupa A. Thermal imaging for detecting temperature changes within the rheumatoid foot. Journal of Thermal Analysis and Calorimetry, 145(1), pp. 77-85. https://doi.org/10.1007/s10973-020-09665-0.
8. Hernandez-Contreras DA, Peregrina-Barreto H, de Jesus Rangel-Magdaleno J, and Renero-Carrillo FJ. Plantar thermogram database for the study of diabetic foot complications. IEEE Access, 7, pp. 161296-161307. https://doi.org/10.1109/ACCESS.2019.2951356.
9. Salazar CA, and Zequera Díaz ML. Thermography as a diagnostic tool for early detection of diabetic foot ulceration risk: a review. In VIII Latin American Conference on Biomedical Engineering and XLII National Conference on Biomedical Engineering: Proceedings of CLAIB-CNIB 2019, October 2-5, 2019, Cancún, México, pp. 1233-1252. https://doi.org/10.1007/978-3-030-30648-9_16.
10. Anaya-Isaza A, and Zequera-Diaz M. Fourier transform-based data augmentation in deep learning for diabetic foot thermograph classification. Biocybernetics and Biomedical Engineering, 42(2), pp. 437-452. https://doi.org/10.1016/j.bbe.2022.03.001.
11. Astasio-Picado Á, Martínez EE, and Gómez-Martín B. Comparative thermal map of the foot between patients with and without diabetes through the use of infrared thermography. Enfermería Clínica (English Edition), 30(2), pp. 119-123. https://doi.org/10.1016/j.enfcle.2018.11.004.
12. Serantoni V, Jourdan F, Louche H, Avignon A, and Sultan A. Definition of thermal indicators for the study of thermoregulation alterations in the foot of people living within diabetic peripheral neuropathy: A proof of concept. Journal of Thermal Biology, 118, p. 103729. https://doi.org/10.1016/j.jtherbio.2023.103729.
13. Arabi PM, Joshi G, Lohith S, Mubashir M, Pallavi PY, and Surabhi M. Early Diagnosis of Diabetic Vasculopathy by Thermo-Regulatory Vascular Impairment. In 2020 5th International Conference on Communication and Electronics Systems (ICCES), pp. 1368-1373. https://doi.org/10.1109/ICCES48766.2020.9137907.
14. Duan Y, Zhang K, Xu Y, Ren W, and Pu F. A promising method for reducing the incidence of diabetic foot ulcers: Regulating foot temperature during walking. Medical Hypotheses, 183, p. 111268. https://doi.org/10.1016/j.mehy.2024.111268.
15. Fasihi-Shirehjini O, and Babapour-Mofrad F. Effectiveness of ConvNeXt variants in diabetic feet diagnosis using plantar thermal images. Quantitative InfraRed Thermography Journal, pp. 1-18. https://doi.org/10.1080/17686733.2024.2310794.
16. Cornelius VA, Fulton JR, and Margariti A. Alternative Splicing: A Key Mediator of Diabetic Vasculopathy. Genes, 12(9), p. 1332. https://doi.org/10.3390/genes12091332
Published
Issue
Section
License
Copyright (c) 2024 Gayatri Joshi, Punal M Arabi (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
