Assessing the Efficacy of AI Models in Medical Imaging Analysis for the Early Identification of Diabetic Foot Ulcers and Gangrene: A Review

Theodor Bilharz Research Institute

Bibliographic Information

Authors: Fahmy A.M.

Journal: Premier Journal of Science

Publisher: Premier Science

Publication Date: 30 July 2025

Volume / Issue: Volume 12

Article No.: 100093

ISSN: 30499011

DOI: 10.70389/PJS.100093

Scopus: View on Scopus

Document Type: Review

Access: All Open Access; Hybrid Gold Open Access


Authors and Affiliations

Fahmy A.M., Theodor Bilharz Research Institute, Giza, Egypt


Abstract

Artificial intelligence (AI) possesses the ability to transform diabetic foot care through enhancing the early identification, categorization, and management of diabetic foot ulcers and gangrene. Incorporation of multimodal sensors, privacy-preserving federated learning, and hybrid convolutional neural network– support vector machine frameworks are some of the AIdriven approaches synthesized in this narrative review. Improving diagnostic accuracy, real-time assessment of risks, and potentially scalable, cost-effective implementation within both urban and rural areas are all included in the clinical potential of AI technology, which the literature review highlighted. Still, there are numerous obstacles to overcome—including a lack of data, inconsistent annotations, outdated technology, biased algorithms—and the need for algorithms that are both explainable and ethically acceptable. In order to cross the gap between breakthrough technology and real-world clinical significance, collaborative attempts that involve standard protocols, compliance with regulations, health care provider commitment, and multidisciplinary teamwork are needed. By addressing these issues and promoting ethical, inclusive, and transparent AI applications, the field has the opportunity to advance in the direction of fair and reliable diabetic foot care, subsequently reducing morbidity and improving patient outcomes on a global basis. © 2025, Premier Science. All rights reserved.


Keywords

Convolutional neural networks; Diabetic foot ulcers; Explainable AI; Federated learning; Gangrene detection


Citation Information

Scopus Citations: 2


For comprehensive information about the Theodor Bilharz Research Institute (TBRI), its institutional activities, scientific and research achievements, clinical and hospital services, and the diverse expertise offered through its 22 specialized research and clinical departments, as well as opportunities for professional training, specialized workshops, and scientific conferences, readers are invited to visit the Institute’s official website.

The website provides regularly updated information on the Institute’s latest news, research activities, scientific initiatives, clinical services, institutional programs, and academic and professional opportunities.

English Website: https://www.tbri.sci.eg/en/

Arabic Website: https://www.tbri.sci.eg/ar/

Prepared and Uploaded by:

Abdalla F. Abdalla

Electronic Portal Unit

Electronic Portal Unit

Popular Posts

A cost-performance index for nano-optical biosensor evaluation: Systematic evaluation of europium–salicylate luminescent platforms for GPC3-targeted early HCC diagnosis

Interpretation of liver stiffness measurement in patients with mixed liver disease etiologies

Multifunctional polycaprolactone-based composite fibers with icariin and glutathione for effective repair of critical-sized bone defects

Holothuria arenicola Extract-Loaded Polycaprolactone Nanocapsules Attenuate Bile Duct Ligation-Induced Acute Liver Injury

Mytilus edulis-mediated green synthesis of selenium nanoparticles with antimicrobial and molluscicidal applications

Microbial levan potentiates hepatic retention and antitumor activity of a PEGylated benzimidazole–curcumin nanocomplex through TLR2–FXR/FGF15-associated immunometabolic remodeling in experimental liver cancer

Variable clinical presentations of pulmonary hydatid cysts: a four-case series from a single center in United Arab Emirates, non-endemic region