{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:14:47Z","timestamp":1765343687656,"version":"3.46.0"},"reference-count":39,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>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\u201313% 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.<\/jats:p>","DOI":"10.3390\/make7040157","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T08:49:22Z","timestamp":1764665362000},"page":"157","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SkinVisualNet: A Hybrid Deep Learning Approach Leveraging Explainable Models for Identifying Lyme Disease from Skin Rash Images"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3493-0929","authenticated-orcid":false,"given":"Amir","family":"Sohel","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3545-8457","authenticated-orcid":false,"given":"Rittik Chandra Das","family":"Turjy","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7551-0461","authenticated-orcid":false,"given":"Sarbajit Paul","family":"Bappy","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7838-0096","authenticated-orcid":false,"given":"Md","family":"Assaduzzaman","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6520-0749","authenticated-orcid":false,"given":"Ahmed Al","family":"Marouf","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Calgary, Calgary, AB T2N 1N4, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3439-2917","authenticated-orcid":false,"given":"Jon George","family":"Rokne","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Calgary, Calgary, AB T2N 1N4, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6657-9738","authenticated-orcid":false,"given":"Reda","family":"Alhajj","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Calgary, Calgary, AB T2N 1N4, Canada"},{"name":"Department of Computer Engineering, Istanbul Medipol University, Istanbul 34810, Turkey"},{"name":"Department of Health Informatics, University of Southern Denmark, 5230 Odense, Denmark"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e007744","DOI":"10.1136\/bmjgh-2021-007744","article-title":"Global seroprevalence and sociodemographic characteristics of Borrelia burgdorferi sensu lato in human populations: A systematic review and meta-analysis","volume":"7","author":"Dong","year":"2022","journal-title":"BMJ Glob. Health"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e1","DOI":"10.1093\/cid\/ciaa1215","article-title":"Clinical practice guidelines by the infectious diseases society of America (IDSA), American Academy of Neurology (AAN), and American College of Rheumatology (ACR): 2020 Guidelines for the prevention, diagnosis and treatment of lyme disease","volume":"72","author":"Lantos","year":"2020","journal-title":"Clin. Infect. Dis."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Bobe, J.R., Jutras, B.L., Horn, E.J., Embers, M.E., Bailey, A., Moritz, R.L., Zhang, Y., Soloski, M.J., Ostfeld, R.S., and Marconi, R.T. (2021). Recent Progress in Lyme Disease and Remaining Challenges. Front. Med., 8.","DOI":"10.3389\/fmed.2021.666554"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"102134","DOI":"10.1016\/j.tmaid.2021.102134","article-title":"Clinical and laboratory evidence of Lyme disease in North India, 2016\u20132019","volume":"43","author":"Vinayaraj","year":"2021","journal-title":"Travel Med. Infect. Dis."},{"key":"ref_5","unstructured":"American Academy of Dermatology Association (2024, March 05). Signs of Lyme Disease. Available online: https:\/\/www.aad.org\/public\/diseases\/a-z\/lyme-disease-signs."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shandilya, G., and Anand, V. (2024, January 13\u201315). Optimizing Lyme Bacterial Disease Identification with Fine-Tuned EfficientnetB0 Model. Proceedings of the 2024 4th International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan.","DOI":"10.1109\/ICTACS62700.2024.10840526"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.compbiomed.2018.12.007","article-title":"Automated detection of erythema migrans and other confounding skin lesions via deep learning","volume":"105","author":"Burlina","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mohan, J., Sivasubramanian, A., V., S., and Ravi, V. (2025). Enhancing skin disease classification leveraging transformer-based deep learning architectures and explainable AI. Comput. Biol. Med., 190.","DOI":"10.1016\/j.compbiomed.2025.110007"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"123056","DOI":"10.1016\/j.eswa.2023.123056","article-title":"A novel end-to-end deep convolutional neural network based skin lesion classification framework","volume":"246","author":"A","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"21281","DOI":"10.1007\/s11042-023-16306-9","article-title":"Deep learning approaches for lyme disease detection: Leveraging progressive resizing and self-supervised learning models","volume":"83","author":"Jerrish","year":"2023","journal-title":"Multimedia Tools Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"9361","DOI":"10.1007\/s00521-024-09583-4","article-title":"A new deep neuro-fuzzy system for Lyme disease detection and classification using UNet, Inception, and XGBoost model from medical images","volume":"36","author":"Priyan","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hossain, S.I., de Herve, J.D.G., Hassan, M.S., Martineau, D., Petrosyan, E., Corbin, V., Beytout, J., Lebert, I., Durand, J., and Carravieri, I. (2022). Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images. Comput. Methods Programs Biomed., 215.","DOI":"10.1016\/j.cmpb.2022.106624"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e0134421","DOI":"10.1128\/JCM.01344-21","article-title":"Serologic response to Borrelia antigens varies with clinical phenotype in children and young adults with Lyme disease","volume":"59","author":"Radtke","year":"2021","journal-title":"J. Clin. Microbiol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Dipakkumar, S.V., Shah, V.D., Shah, D., and Deshmukh, S. (2024, January 5\u20137). Automated Detection of Lyme Disease using Transfer Learning Techniques. Proceedings of the 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India.","DOI":"10.1109\/ICAAIC60222.2024.10575196"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Saravanan, M., and Shakti, S. (2023, January 14\u201315). Performance Enhancement to Improve Accuracy for the Identification of Lyme Disease by using Novel ANN Algorithm by Comparing with K-Mean Algorithm. Proceedings of the 2023 6th International Conference on Recent Trends in Advance Computing (ICRTAC), Chennai, India.","DOI":"10.1109\/ICRTAC59277.2023.10480802"},{"key":"ref_16","unstructured":"Shikamaru, S. (2024, January 05). \u201cLyme Disease Rashes Dataset,\u201d Kaggle, 2023. Available online: https:\/\/www.kaggle.com\/datasets\/sshikamaru\/lyme-disease-rashes."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/s13640-016-0138-1","article-title":"An adaptive gamma correction for image enhancement","volume":"2016","author":"Rahman","year":"2016","journal-title":"Eurasip J. Image Video Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"309","DOI":"10.19026\/rjaset.9.1409","article-title":"A Review of Image Contrast Enhancement Methods and Techniques","volume":"9","author":"Maragatham","year":"2015","journal-title":"Res. J. Appl. Sci. Eng. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"54","DOI":"10.15804\/npw20192004","article-title":"Porozumienie reguluj\u0105ce status Morza Kaspijskiego-geneza i znaczenie. [The agreement regulating the Caspian Sea status-genesis and meaning]","volume":"20","author":"Wojcieszak","year":"2019","journal-title":"Nowa Polityka Wschod."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"8","DOI":"10.4236\/jcc.2019.73002","article-title":"Image Quality Assessment through FSIM, SSIM, MSE and PSNR\u2014A Comparative Study","volume":"7","author":"Sara","year":"2019","journal-title":"J. Comput. Commun."},{"key":"ref_23","unstructured":"Rahman, M.M., Uzzaman, A., Sami, S.I., and Khatun, F. (2025, November 26). Developing a Deep Neural Network-Based Encoder-Decoder Framework in Automatic Image Captioning Systems. Available online: https:\/\/www.researchsquare.com\/article\/rs-2046359\/v1."},{"key":"ref_24","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_25","first-page":"5682","article-title":"Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning","volume":"39","author":"Vijay","year":"2020","journal-title":"J. Biomol. Struct. Dyn."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 22\u201325). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kvak, D. (2022). Leveraging Computer Vision Application in Visual Arts: A Case Study on the Use of Residual Neural Network to Classify and Analyze Baroque Paintings. arXiv.","DOI":"10.20944\/preprints202210.0448.v1"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_29","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on International Conference on Machine Learning (ICML), Lille, France."},{"key":"ref_30","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","unstructured":"Kingma, D.P., and Ba, J. (2014, January 14\u201316). Adam: A method for stochastic optimization. Proceedings of the International Conference on Learning Representations (ICLR), Banff, AB, Canada."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Banerjee, K., C, V.P., Gupta, R.R., Vyas, K., H, A., and Mishra, B. (2021). Exploring Alternatives to Softmax Function. arXiv.","DOI":"10.5220\/0010502000002996"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tejaswi, K., and Zhang, E. (2021). Using Deep Learning in Lyme Disease Diagnosis. J. Stud. Res., 10.","DOI":"10.47611\/jsrhs.v10i4.2389"},{"key":"ref_34","unstructured":"Micikevicius, P., Narang, S., Alben, J., Diamos, G.F., Elsen, E., Garc\u00eda, D., Ginsburg, B., Houston, M., Kuchaiev, O., and Venkatesh, G. (2017). Mixed Precision training. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Barron, J.T. (2019, January 15\u201320). A General and Adaptive Robust Loss Function. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00446"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e47014","DOI":"10.2196\/47014","article-title":"Identifying potential Lyme disease cases using self-reported worldwide Tweets: Deep learning modeling approach enhanced with sentimental words through emojis","volume":"25","author":"Laison","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref_37","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_39","unstructured":"Marafioti, A., Zohar, O., Farr\u00e9, M., Noyan, M., Bakouch, E., Cuenca, P., Zakka, C., Allal, L.B., Lozhkov, A., and Tazi, N. (2025). Smolvlm: Redefining small and efficient multimodal models. arXiv."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/157\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:10:59Z","timestamp":1765343459000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":39,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["make7040157"],"URL":"https:\/\/doi.org\/10.3390\/make7040157","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}