Sustainable AI for diabetic foot ulcer detection: a deep learning approach for early diagnosis

• Published in: Discover applied sciences Vol. 7; no. 9; p. 1012
• Main Authors: Debnath, Saswati, Khurana, Anshu, Senbagavalli, M., Naik, Shradha, Chandra Patni, Jagdish, Mishra, Pawan Kumar, Kishore, Jaydeep
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.09.2025; Springer Nature B.V
• Subjects: Accuracy; Amputation; Applied and Technical Physics; Artificial intelligence; Artificial neural networks; Bacterial infections; Chemistry/Food Science; Classification; Convolution; Deep learning; Diabetes; Diabetes mellitus; Disease; Earth Sciences; Engineering; Environment; Feet; Foot diseases; Health care; Ischemia; Leg ulcers; Machine learning; Materials Science; Medical imaging; Methods; Neural networks; Patients; Plantar ulcers; Quality of life; Remote monitoring; Skin; Smartphones; Ulcers; Deep learning; DFUNet; MobileNet; Medical imaging; Convolution neural network; Diabetic foot Ulcers
• ISSN: 2523-3963; 3004-9261; 2523-3971
• DOI: 10.1007/s42452-025-07601-1

Diabetic foot ulcer (DFU) is one of the most expensive and debilitating complications of diabetes. According to procedures developed by the National Institute of Health and Clinical Excellence, early and effective treatment of DFU can minimize the severity of complications, such as unnecessary amputations, and improve overall quality of life. In this paper, a stacked parallel convolution layers based Convolution Neural Network (CNN) is proposed, known as DFU MobileNet, to classify skin infected with DFU against normal skin. The main objective of this work is to develop a DFU recognition system that accurately identifies infected skin. DFU MobileNet consists of three blocks of parallel convolution layers, each with a unique kernel size to extract local and global features distinctly. Using the DFUC 2020 dataset, the proposed DFU MobileNet outperformed existing state-of-the-art models, achieving an accuracy of 92.2% using CNN DenseNet, 95.4% using MobileNet, and 97.8% when combining DenseNet and MobileNet. Article Highlights A mobile-friendly deep learning model detects diabetic foot ulcers with high accuracy. The model enables early infection detection using smartphone images. Supports remote DFU monitoring and reduces dependence on clinic visits.