• Home
  • Search
  • A few-shot diabetes foot ulcer image classification method based on deep ResNet and transfer learning
  • Cite Icon11
  • https://doi.org/10.1038/s41598-024-80691-wCopy DOI Icon

A few-shot diabetes foot ulcer image classification method based on deep ResNet and transfer learning

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Diabetes foot ulcer (DFU) is one of the common complications of diabetes patients, which may lead to infection, necrosis and even amputation. Therefore, early diagnosis, classification of severity and related treatment are crucial for the patients. Current DFU classification methods often require experienced doctors to manually classify the severity, which is time-consuming and low accuracy. The objective of the study is to propose a few-shot DFU image classification method based on deep residual neural network and transfer learning. Considering the difficulty in obtaining clinical DFU images, it is a few-shot problem. Therefore, the methods include: (1) Data augmentation of the original DFU images by using geometric transformations and random noise; (2) Deep ResNet models selection based on different convolutional layers comparative experiments; (3) DFU classification model training with transfer learning by using the selected pre-trained ResNet model and fine tuning. To verify the proposed classification method, the experiments were performed with the original and augmented datasets by separating three classifications: zero grade, mild grade, severe grade. (1) The datasets were augmented from the original 146 to 3000 image datasets and the corresponding DFU classification’s average accuracy from 0.9167 to 0.9867; (2) Comparative experiments were conducted with ResNet18, ResNet34, ResNet50, ResNet101, ResNet152 by using 3000 image datasets, and the average accuracy/loss is 0.9325/0.2927, 0.9276/0.3234, 0.9901/0.1356, 0.9865/0.1427, 0.9790/0.1583 respectively; (3) Based on the augmented 3000 image datasets, it was achieved 0.9867 average accuracy with the DFU classification model, which was trained by the pre-trained ResNet50 and hyper-parameters. The experimental results indicated that the proposed few-shot DFU image classification method based on deep ResNet and transfer learning got very high accuracy, and it is expected to be suitable for low-cost and low-computational terminal equipment, aiming at helping clinical DFU classification efficiently and auxiliary diagnosis.

Similar Papers
  • Research Article
  • Citations302

Systematic reviews of wound care management: (3) antimicrobial agents for chronic wounds; (4) diabetic foot ulceration

  • May 01, 2001
  • Health Technology Assessment
  • S O'Meara +3
  • Research Article
  • Citations1

485-P: DFUCare Deep-Learning–Based Mobile App for Diabetic Foot Ulcer Monitoring

  • Jun 01, 2022
  • Diabetes
  • Varun Sendilraj +2
  • Research Article

STUDY OF SURGICAL MANAGEMENT AND COMPLICATIONS OF DIABETIC FOOT ULCER

  • Feb 27, 2019
  • International Journal of Medical and Biomedical Studies
  • Dr Devi Das Verma +1
  • Research Article
  • Citations7

Bacterial Infections Profile and Patterns for Diabetic Foot Ulcers in Nongovernmental Hospitals of Jordan

  • Mar 18, 2021
  • Journal of Pharmaceutical Research International
  • Hashem A Abu-Harirah +5
  • Research Article
  • Citations16

Region-wise severity analysis of diabetic plantar foot thermograms.

  • Jun 09, 2023
  • Biomedical Engineering / Biomedizinische Technik
  • Naveen Sharma +4
  • Research Article

A Retrospective Qualitative Study on Current Management of Diabetic Foot Ulcer and Discussion on Extended Role of Clinical Pharmacist

  • Jan 01, 2017
  • Marmara Pharmaceutical Journal
  • A Porselvi +3
  • Research Article

HUBUNGAN DERAJAT DIABETIC FOOT ULCER TERHADAP TINGKAT DEPRESI PADA PASIEN DIABETES MELITUS DI RSUD Dr. H. MOCH ANSARI SALEH BANJARMASIN/THE RELATIONSHIP OF THE DEGREE OF DIABETIC FOOT ULCER TO THE LEVEL OF DEPRESSION IN DIABETES MELLITUS PATIENTS AT HOSP

  • Jul 10, 2025
  • Jurnal Ilmu Kesehatan
  • Yudit Seftia Marini +3
  • PDF
  • Research Article
  • Citations15

A Multi-Faceted Digital Health Solution for Monitoring and Managing Diabetic Foot Ulcer Risk: A Case Series

  • Apr 23, 2024
  • Sensors (Basel, Switzerland)
  • Emily Matijevich +5
  • Research Article
  • Citations1

A Survey on Impact of Internet of Medical Things Against Diabetic Foot Ulcer

  • Feb 21, 2024
  • EAI Endorsed Transactions on Pervasive Health and Technology
  • R Athi Vaishnavi +3
  • Research Article

To study efficacy of foot temperature monitoring and footprint study in preventing diabetic foot ulcer in type 2 diabetic patients with peripheral neuropathy

  • Jan 01, 2025
  • Asian Journal of Medical Sciences
  • Manjunath Ashok Kolachi +3
  • PDF
  • Research Article
  • Citations3

Diabetic Foot Ulcer Risk with Diabetic Kidney Disease and Renal Failure among 10,680 Patients

  • Dec 01, 2021
  • SciMedicine Journal
  • Kamran Mahmood Ahmed Aziz
  • Research Article
  • Citations1

Demonstration of the Effectiveness of Epidermal Growth Factor in Diabetic Foot Ulcers

  • Nov 30, 2022
  • Journal of Contemporary Medicine
  • Halit Baykan +1
  • Research Article
  • Citations7

A Retrospective Qualitative Study on Current Diabetic Foot Ulcer Management and Discussion on Extended Role of Clinical Pharmacist

  • Apr 01, 2017
  • Marmara Pharmaceutical Journal
  • A Porselvi +3
  • Research Article
  • Citations5

Association between sarcopenia and the foot-ankle function in type 2 diabetic foot ulcer

  • Nov 13, 2024
  • Diabetology & Metabolic Syndrome
  • Shujing An +6
  • Research Article
  • Citations1

Diabetic Foot Ulcer (DFU) and Its Pharmaceutical and Therapeutic Strategies: A Systematic Review

  • Sep 06, 2019
  • International Journal of Drug Research And Dental Science
  • Mahboobe Khodadadi +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.