A Nesting Segmenting and Categorizing Model for Diabetic Wound Depth Detection in Foot Using Convolutional Neural Networks

Omprakash Dewangan; Ankita Tiwari

doi:10.25163/angiotherapy.899875

Angiogenesis, Inflammation & Therapeutics | Impact 0.1 (CiteScore) | Online ISSN 2207-872X

RESEARCH ARTICLE (Open Access)

Previous Next Contents Vol 8 (9)

A Nesting Segmenting and Categorizing Model for Diabetic Wound Depth Detection in Foot Using Convolutional Neural Networks

Omprakash Dewangan ¹*, Ankita Tiwari ¹

+ Author Affiliations

Journal of Angiotherapy 8 (9) 1-6 https://doi.org/10.25163/angiotherapy.899875

Submitted: 10 September 2024 Revised: 30 August 2024 Published: 07 September 2024

Abstract

Background: Traditional methods of Diabetic Foot Ulcers (DFUs) assessment and segmentation using computer vision and Machine Learning (ML) have faced limitations in accuracy and automation. Recent advancements in Deep Learning (DL) offer potential improvements, but challenges remain in the precise quantification and categorization of DFUs. Methods: This study explores a framework combining Mask Region-based Convolutional Neural Networks (R-CNN) with a nested structure for DFU segmentation. The approach involved collecting and preprocessing DFU images from Xiangya Hospital and the DFU Challenge (DFUC) 2020. A Region Proposal Network (RPN) was employed to identify potential regions of interest, which were then analyzed using Mask R-CNN with ResNet-FPN as the backbone. The model aimed to enhance feature extraction and categorization of DFUs through a layered approach that integrates regional proposals and segmentation masks. Results: The proposed method achieved superior results in DFU categorization compared to existing techniques. The use of Mask R-CNN with ResNet-FPN improved segmentation accuracy, with the framework achieving notable enhancements in F-score and accuracy metrics—0.79%, 16.30%, and 3.24% improvements over other algorithms. The method effectively learned and categorized complex DFU structures, providing a more accurate assessment of wound severity levels. The performance was validated against various models, including R-CNN, YOLO, DetNet, and EfficientDet, demonstrating the robustness of the proposed method. Conclusion: The integration of Mask R-CNN with a nested feature extraction framework offers a promising advancement in DFU segmentation. This approach addresses existing limitations in automated DFU assessment by improving accuracy and consistency.

Keywords: Diabetic Foot Ulcer, Deep Learning, Mask R-CNN, ResNet-FPN, Segmentation

References

Ahmad, N. (2022). In vitro and in vivo characterization methods for evaluation of modern wound dressings. Pharmaceutics, 15(1), 42.

Alamer, L., Alqahtani, I. M., & Shadadi, E. (2023). Intelligent health risk and disease prediction using optimized naive Bayes classifier. Journal of Internet Services and Information Security, 13(1), 01-10.

Barakat-Johnson, M., Jones, A., Burger, M., Leong, T., Frotjold, A., Randall, S., ... & Coyer, F. (2022). Reshaping wound care: Evaluation of an artificial intelligence app to improve wound assessment and management amid the COVID-19 pandemic. International Wound Journal, 19(6), 1561-1577.

Chemello, G., Salvatori, B., Morettini, M., & Tura, A. (2022). Artificial intelligence methodologies applied to technologies for screening, diagnosis, and care of the diabetic foot: A narrative review. Biosensors, 12(11), 985.

Chino, D. Y., Scabora, L. C., Cazzolato, M. T., Jorge, A. E., Traina-Jr, C., & Traina, A. J. (2020). Segmenting skin ulcers and measuring the wound area using deep convolutional networks. Computer Methods and Programs in Biomedicine, 191, 105376.

Dhar, M. K., Wang, C., Patel, Y., Zhang, T., Niezgoda, J., Gopalakrishnan, S., ... & Yu, Z. (2024). Wound tissue segmentation in diabetic foot ulcer images using deep learning: A pilot study. arXiv preprint arXiv:2406.16012.

Dhar, M. K., Zhang, T., Patel, Y., Gopalakrishnan, S., & Yu, Z. (2024). FUSegNet: A deep convolutional neural network for foot ulcer segmentation. Biomedical Signal Processing and Control, 92, 106057.

Du, G., Cao, X., Liang, J., Chen, X., & Zhan, Y. (2020). Medical image segmentation based on U-Net: A review. Journal of Imaging Science & Technology, 64(2).

Eriksson, E., Liu, P. Y., Schultz, G. S., Martins-Green, M. M., Tanaka, R., Weir, D., ... & Gurtner, G. C. (2022). Chronic wounds: Treatment consensus. Wound Repair and Regeneration, 30(2), 156-171.

Fauzi, M. F. A., Khansa, I., Catignani, K., Gordillo, G., Sen, C. K., & Gurcan, M. N. (2021). Segmentation and management of chronic wound images: A computer-based approach. Chronic Wounds, Wound Dressings and Wound Healing, 115-134.

Monroy, B., Sanchez, K., Arguello, P., Estupiñán, J., Bacca, J., Correa, C. V., ... & Rojas-Morales, F. (2023). Automated chronic wounds medical assessment and tracking framework based on deep learning. Computers in Biology and Medicine, 165, 107335.

Thota, C., Jackson Samuel, D., Musa Jaber, M., Kamruzzaman, M. M., Ravi, R. V., Gnanasigamani, L. J., & Premalatha, R. (2024). Image smart segmentation analysis against diabetic foot ulcer using Internet of Things with virtual sensing. Big Data, 12(2), 155-172.

Wang, X., Yuan, C. X., Xu, B., & Yu, Z. (2022). Diabetic foot ulcers: Classification, risk factors, and management. World Journal of Diabetes, 13(12), 1049.

Abstract
Export Citation

View Dimensions

View Plumx

View Altmetric

Save

0
Citation

41
View

Share