SkinVisualNet: A Hybrid Deep Learning Approach Leveraging Explainable Models for Identifying Lyme Disease from Skin Rash Images

Gorde:
Xehetasun bibliografikoak
Argitaratua izan da:Machine Learning and Knowledge Extraction vol. 7, no. 4 (2025), p. 157-184
Egile nagusia: Amir, Sohel
Beste egile batzuk: Turjy Rittik Chandra Das, Bappy, Sarbajit Paul, Assaduzzaman Md, Marouf, Ahmed Al, Rokne Jon George, Alhajj Reda
Argitaratua:
MDPI AG
Gaiak:
Sarrera elektronikoa:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiketak: Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!

MARC

LEADER 00000nab a2200000uu 4500
001 3286316558
003 UK-CbPIL
022 |a 2504-4990 
024 7 |a 10.3390/make7040157  |2 doi 
035 |a 3286316558 
045 2 |b d20251001  |b d20251231 
100 1 |a Amir, Sohel  |u Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh; amir.cse@diu.edu.bd (A.S.); turjy15-6289@s.diu.edu.bd (R.C.D.T.); bappy15-6155@s.diu.edu.bd (S.P.B.); assaduzzaman.cse@diu.edu.bd (M.A.) 
245 1 |a SkinVisualNet: A Hybrid Deep Learning Approach Leveraging Explainable Models for Identifying Lyme Disease from Skin Rash Images 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Lyme disease, caused by the Borrelia burgdorferi bacterium and transmitted through black-legged (deer) tick bites, is becoming increasingly prevalent globally. According to data from the Lyme Disease Association, the number of cases has surged by more than 357% over the past 15 years. According to the Infectious Disease Society of America, traditional diagnostic methods are often slow, potentially allowing bacterial proliferation and complicating early management. This study proposes a novel hybrid deep learning framework to classify Lyme disease rashes, addressing the global prevalence of the disease caused by the Borrelia burgdorferi bacterium, which is transmitted through black-legged (deer) tick bites. This study presents a novel hybrid deep learning framework for classifying Lyme disease rashes, utilizing pre-trained models (ResNet50 V2, VGG19, DenseNet201) for initial classification. By combining VGG19 and DenseNet201 architectures, we developed a hybrid model, SkinVisualNet, which achieved an impressive accuracy of 98.83%, precision of 98.45%, recall of 99.09%, and an F1 score of 98.76%. To ensure the robustness and generalizability of the model, 5-fold cross-validation (CV) was performed, generating an average validation accuracy between 98.20% and 98.92%. Incorporating image preprocessing techniques such as gamma correction, contrast stretching and data augmentation led to a 10–13% improvement in model accuracy, significantly enhancing its ability to generalize across various conditions and improving overall performance. To improve model interpretability, we applied Explainable AI methods like LIME, Grad-CAM, CAM++, Score CAM and Smooth Grad to visualize the rash image regions most influential in classification. These techniques enhance both diagnostic transparency and model reliability, helping clinicians better understand the diagnostic decisions. The proposed framework demonstrates a significant advancement in automated Lyme disease detection, providing a robust and explainable AI-based diagnostic tool that can aid clinicians in improving patient outcomes. 
653 |a Medical diagnosis 
653 |a Infectious diseases 
653 |a Accuracy 
653 |a Arachnids 
653 |a Data augmentation 
653 |a Deep learning 
653 |a Datasets 
653 |a Classification 
653 |a Artificial intelligence 
653 |a Erythema 
653 |a Optimization techniques 
653 |a Neural networks 
653 |a Medical imaging 
653 |a Skin diseases 
653 |a Machine learning 
653 |a Explainable artificial intelligence 
653 |a Global health 
653 |a Lyme disease 
653 |a Bacteria 
700 1 |a Turjy Rittik Chandra Das  |u Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh; amir.cse@diu.edu.bd (A.S.); turjy15-6289@s.diu.edu.bd (R.C.D.T.); bappy15-6155@s.diu.edu.bd (S.P.B.); assaduzzaman.cse@diu.edu.bd (M.A.) 
700 1 |a Bappy, Sarbajit Paul  |u Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh; amir.cse@diu.edu.bd (A.S.); turjy15-6289@s.diu.edu.bd (R.C.D.T.); bappy15-6155@s.diu.edu.bd (S.P.B.); assaduzzaman.cse@diu.edu.bd (M.A.) 
700 1 |a Assaduzzaman Md  |u Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh; amir.cse@diu.edu.bd (A.S.); turjy15-6289@s.diu.edu.bd (R.C.D.T.); bappy15-6155@s.diu.edu.bd (S.P.B.); assaduzzaman.cse@diu.edu.bd (M.A.) 
700 1 |a Marouf, Ahmed Al  |u Department of Computer Science, University of Calgary, Calgary, AB T2N 1N4, Canada; rokne@ucalgary.ca (J.G.R.); alhajj@ucalgary.ca (R.A.) 
700 1 |a Rokne Jon George  |u Department of Computer Science, University of Calgary, Calgary, AB T2N 1N4, Canada; rokne@ucalgary.ca (J.G.R.); alhajj@ucalgary.ca (R.A.) 
700 1 |a Alhajj Reda  |u Department of Computer Science, University of Calgary, Calgary, AB T2N 1N4, Canada; rokne@ucalgary.ca (J.G.R.); alhajj@ucalgary.ca (R.A.) 
773 0 |t Machine Learning and Knowledge Extraction  |g vol. 7, no. 4 (2025), p. 157-184 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3286316558/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3286316558/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3286316558/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch