A feature explainability-based deep learning technique for diabetic foot ulcer identification

Abstract Diabetic foot ulcers (DFUs) are a common and serious complication of diabetes, presenting as open sores or wounds on the sole. They result from impaired blood circulation and neuropathy associated with diabetes, increasing the risk of severe infections and even amputations if untreated. Ear...

Full description

Saved in:
Bibliographic Details
Main Authors: Pramod Singh Rathore, Abhishek Kumar, Amita Nandal, Arvind Dhaka, Arpit Kumar Sharma
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-90780-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850185246143676416
author Pramod Singh Rathore
Abhishek Kumar
Amita Nandal
Arvind Dhaka
Arpit Kumar Sharma
author_facet Pramod Singh Rathore
Abhishek Kumar
Amita Nandal
Arvind Dhaka
Arpit Kumar Sharma
author_sort Pramod Singh Rathore
collection DOAJ
description Abstract Diabetic foot ulcers (DFUs) are a common and serious complication of diabetes, presenting as open sores or wounds on the sole. They result from impaired blood circulation and neuropathy associated with diabetes, increasing the risk of severe infections and even amputations if untreated. Early detection, effective wound care, and diabetes management are crucial to prevent and treat DFUs. Artificial intelligence (AI), particularly through deep learning, has revolutionized DFU diagnosis and treatment. This work introduces the DFU_XAI framework to enhance the interpretability of deep learning models for DFU labeling and localization, ensuring clinical relevance. The framework evaluates six advanced models—Xception, DenseNet121, ResNet50, InceptionV3, MobileNetV2, and Siamese Neural Network (SNN)—using interpretability techniques like SHAP, LIME, and Grad-CAM. Among these, the SNN model excelled with 98.76% accuracy, 99.3% precision, 97.7% recall, 98.5% F1-score, and 98.6% AUC. Grad-CAM heat maps effectively identified ulcer locations, aiding clinicians with precise and visually interpretable insights. The DFU_XAI framework integrates explainability into AI-driven healthcare, enhancing trust and usability in clinical settings. This approach addresses challenges of transparency in AI for DFU management, offering reliable and efficient solutions to this critical healthcare issue. Traditional DFU methods are labor-intensive and costly, highlighting the transformative potential of AI-driven systems.
format Article
id doaj-art-2c207a21f6a14e7ba287e2d49f7723a6
institution OA Journals
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2c207a21f6a14e7ba287e2d49f7723a62025-08-20T02:16:48ZengNature PortfolioScientific Reports2045-23222025-02-0115112110.1038/s41598-025-90780-zA feature explainability-based deep learning technique for diabetic foot ulcer identificationPramod Singh Rathore0Abhishek Kumar1Amita Nandal2Arvind Dhaka3Arpit Kumar Sharma4Department of Computer and Communication Engineering, Manipal University JaipurDepartment of CSE, Chandigarh UniversityDepartment of IoT and Intelligent Systems, Manipal University JaipurDepartment of Computer and Communication Engineering, Manipal University JaipurDepartment of Computer and Communication Engineering, Manipal University JaipurAbstract Diabetic foot ulcers (DFUs) are a common and serious complication of diabetes, presenting as open sores or wounds on the sole. They result from impaired blood circulation and neuropathy associated with diabetes, increasing the risk of severe infections and even amputations if untreated. Early detection, effective wound care, and diabetes management are crucial to prevent and treat DFUs. Artificial intelligence (AI), particularly through deep learning, has revolutionized DFU diagnosis and treatment. This work introduces the DFU_XAI framework to enhance the interpretability of deep learning models for DFU labeling and localization, ensuring clinical relevance. The framework evaluates six advanced models—Xception, DenseNet121, ResNet50, InceptionV3, MobileNetV2, and Siamese Neural Network (SNN)—using interpretability techniques like SHAP, LIME, and Grad-CAM. Among these, the SNN model excelled with 98.76% accuracy, 99.3% precision, 97.7% recall, 98.5% F1-score, and 98.6% AUC. Grad-CAM heat maps effectively identified ulcer locations, aiding clinicians with precise and visually interpretable insights. The DFU_XAI framework integrates explainability into AI-driven healthcare, enhancing trust and usability in clinical settings. This approach addresses challenges of transparency in AI for DFU management, offering reliable and efficient solutions to this critical healthcare issue. Traditional DFU methods are labor-intensive and costly, highlighting the transformative potential of AI-driven systems.https://doi.org/10.1038/s41598-025-90780-zLIMEHeat MapAIDLDiabetic Foot Ulcer
spellingShingle Pramod Singh Rathore
Abhishek Kumar
Amita Nandal
Arvind Dhaka
Arpit Kumar Sharma
A feature explainability-based deep learning technique for diabetic foot ulcer identification
Scientific Reports
LIME
Heat Map
AI
DL
Diabetic Foot Ulcer
title A feature explainability-based deep learning technique for diabetic foot ulcer identification
title_full A feature explainability-based deep learning technique for diabetic foot ulcer identification
title_fullStr A feature explainability-based deep learning technique for diabetic foot ulcer identification
title_full_unstemmed A feature explainability-based deep learning technique for diabetic foot ulcer identification
title_short A feature explainability-based deep learning technique for diabetic foot ulcer identification
title_sort feature explainability based deep learning technique for diabetic foot ulcer identification
topic LIME
Heat Map
AI
DL
Diabetic Foot Ulcer
url https://doi.org/10.1038/s41598-025-90780-z
work_keys_str_mv AT pramodsinghrathore afeatureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT abhishekkumar afeatureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT amitanandal afeatureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT arvinddhaka afeatureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT arpitkumarsharma afeatureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT pramodsinghrathore featureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT abhishekkumar featureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT amitanandal featureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT arvinddhaka featureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification
AT arpitkumarsharma featureexplainabilitybaseddeeplearningtechniquefordiabeticfootulceridentification