DermFusion-CBAMNet: A Dual-Backbone Attention-Guided Framework for Robust Multiclass Skin Disease Classification
DOI:
https://doi.org/10.4108/eetiot.13764Keywords:
Skin disease, Transfer Learning, Fusion model, EfficientNet B2, DenseNet121, VGG19Abstract
Skin diseases are a major health care problem all over the world. Accurate and prompt diagnosis of skin disorders can result in efficient treatment and better patient outcomes. However, various skin disorders still remain challenging to be automatically classified due to the significant inter-class similarities, intra-class variances, diversified lesion appearances and complicated image backgrounds. We propose DermFusion-CBAMNet, a new dual-backbone attention-based deep learning architecture for multiclass skin disease categorization. Instead of the typical transfer learning techniques that use only one pre-trained model or just replace the classification layers, the framework proposed here maintains the structural integrity of two complementary pre-trained architectures, DenseNet121 and EfficientNet-B2, and merges their learned features through an efficient feature fusion strategy. In addition, both feature extraction branches are integrated with Convolutional Block Attention Module (CBAM) to refine the channel-wise and spatial feature representations by focusing on diagnostically relevant lesion characteristics selectively and suppressing redundant information. Such attention-guided fusion helps the model to acquire more discriminative and robust representations to correctly classify several kinds of skin diseases. The proposed architecture is assessed using a benchmark dataset that contains 10 types of skin illness, with the help of comprehensive performance metrics like accuracy, precision, recall, F1-score, Receiver Operating Characteristic (ROC) and Area Under the Curve (AUC). The experimental findings show that DermFusion-CBAMNet beats the baseline models. These results prove that DermFusion-CBAMNet is a robust, interpretable and reliable framework for automated multiclass skin disease classification and has great potential to be deployed in computer-aided dermatological diagnosis and clinical decision support systems.
Downloads
References
[1] Do TT, Zhou Y, Zheng H, Cheung NM, Koh D. Early melanoma diagnosis with mobile imaging. In2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2014 Aug 26 (pp. 6752-6757). IEEE.
[2] World Health Organization. WHO’s first global meeting on skin NTDs calls for greater efforts to address their burden [Internet]. Geneva: World Health Organization; 2023 Mar 31 [cited 2026 Sep 30]. Available from: https://www.who.int/news/item/31-03-2023-who-first-global-meeting-on-skin-ntds-calls-for-greater-efforts-to-address-their-burden
[3] Sarkar R, Sinha S, editors. Skin Diseases in Females. Springer Nature; 2022 Nov 11.
[4] Srinivasu PN, SivaSai JG, Ijaz MF, Bhoi AK, Kim W, Kang JJ. Classification of skin disease using deep learning neural networks with MobileNet V2 and LSTM. Sensors. 2021 Apr 18;21(8):2852.
[5] Ali MS, Miah MS, Haque J, Rahman MM, Islam MK. An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models. Machine Learning with Applications. 2021 Sep 15;5:100036.
[6] Hasanat TU, Tahsin S, Mahmud A, Reshni NJ, Fateha TT, Hossain MS. An Interpretable Deep Learning Approach for Multi-Disease Skin Lesion Classification Using a Custom Convolutional Neural Network: A Comparative Study. In2025 28th International Conference on Computer and Information Technology (ICCIT) 2025 Dec 19 (pp. 2265-2270). IEEE.
[7] Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. nature. 2017 Feb 2;542(7639):115-8.
[8] Anand V, Gupta S, Koundal D, Nayak SR, Nayak J, Vimal S. Multi-class skin disease classification using transfer learning model. International Journal on Artificial Intelligence Tools. 2022 Mar 31;31(02):2250029.
[9] Alruwaili M, Mohamed M. An integrated deep learning model with EfficientNet and ResNet for accurate multi-class skin disease classification. Diagnostics. 2025 Feb 25;15(5):551.
[10] Vellela SS, Roja D, Sowjanya C, SK KB, Dalavai L, Kumar KK. Multi-Class Skin Diseases Classification with Color and Texture Features Using Convolution Neural Network. In 2023 6th International Conference on Contemporary Computing and Informatics (IC3I) 2023 Sep 14 (Vol. 6, pp. 1682-1687). IEEE.
[11] Badr M, Elkasaby A, Alrahmawy M, El-Metwally S. A multi-model deep learning architecture for diagnosing multi-class skin diseases. Journal of Imaging Informatics in Medicine. 2025 Jun;38(3):1776-95.
[12] Almustafa KM. Predictive modeling and optimization in dermatology: Machine learning for skin disease classification. Computers in Biology and Medicine. 2025 May 1;189:109946.
[13] Ozdemir B, Pacal I. A robust deep learning framework for multiclass skin cancer classification. Scientific Reports. 2025 Feb 10;15(1):4938. 8. Gairola AK, Kumar V, Sahoo AK, Diwakar M, Singh P, Garg D. Multi-feature fusion deep network for skin disease diagnosis. Multimedia Tools and Applications. 2025 Jan;84(1):419-44.
[14] Gairola AK, Kumar V, Sahoo AK, Diwakar M, Singh P, Garg D. Multi-feature fusion deep network for skin disease diagnosis. Multimedia Tools and Applications. 2025 Jan;84(1):419-44.
[15] Chen J, Jiang Q, Ai Z, Wei Q, Xu S, Hao B, Lu Y, Huang X, Chen L. Pigmented skin disease classification via deep learning with an attention mechanism. Applied Soft Computing. 2025 Feb 1;170:112571.
[16] Sasithradevi A, Kanimozhi S, Sasidhar P, Pulipati PK, Sruthi E, Prakash P. EffiCAT: A synergistic approach to skin disease classification through multi-dataset fusion and attention mechanisms. Biomedical Signal Processing and Control. 2025 Feb 1;100:107141.
[17] Venkat NL, Tejasri MN, Uppalapati PJ, Rao VM, Sripada VL, Murty PS. Deep Learning Strategies for Multiclass Skin Disease Classification. In International Conference on Cognitive Computing and Cyber Physical Systems 2024 Apr 4 (pp. 215-233). Cham: Springer Nature Switzerland.
[18] Sohn A, Frankel A, Patel RV, Goldenberg G. Eczema. Mount Sinai Journal of Medicine: A Journal of Translational and Personalized Medicine. 2011 Sep;78(5):730-9.
[19] Aggarwal P, Knabel P, Fleischer Jr AB. United States burden of melanoma and non-melanoma skin cancer from 1990 to 2019. Journal of the American Academy of Dermatology. 2021 Aug 1;85(2):388-95.
[20] Vekaria AS, Brunner PM, Aleisa AI, Bonomo L, Lebwohl MG, Israel A, Guttman-Yassky E. protein levels, correlating with skin disease activity.
[21] Wade TR, Ackerman AB. The many faces of basal‐cell carcinoma. The Journal of dermatologic surgery and oncology. 1978 Jan;4(1):23-8.
[22] Roh MR, Eliades P, Gupta S, Tsao H. Genetics of melanocytic nevi. Pigment cell & melanoma research. 2015 Nov;28(6):661-72.
[23] Janowska A, Oranges T, Iannone M, Romanelli M, Dini V. Seborrheic keratosis-like melanoma: a diagnostic challenge. Melanoma Research. 2021 Oct 1;31(5):407-12.
[24] Lallas A, Kyrgidis A, Tzellos TG, Apalla Z, Karakyriou E, Karatolias A, Lefaki I, Sotiriou E, Ioannides D, Argenziano G, Zalaudek I. Accuracy of dermoscopic criteria for the diagnosis of psoriasis, dermatitis, lichen planus and pityriasis rosea. British Journal of Dermatology. 2012 Jun 1;166(6):1198-205.
[25] Jain A, Jain S, Rawat S. Emerging fungal infections among children: A review on its clinical manifestations, diagnosis, and prevention. Journal of Pharmacy and Bioallied Sciences. 2010 Oct 1;2(4):314-20.
[26] Roh MR, Eliades P, Gupta S, Tsao H. Genetics of melanocytic nevi. Pigment cell & melanoma research. 2015 Nov;28(6):661-72.
[27] Alrabai A, Echtioui A, Kallel F. Exploring pre-trained models for skin cancer classification. Applied System Innovation. 2025 Mar 13;8(2):35.
[28] Sarkar R, Sinha S, editors. Skin Diseases in Females. Springer Nature; 2022 Nov 11.
[29] Liu R, Chen Z, Zhang P. Skin lesion classification based on ResNet-50 enhanced with adaptive spatial feature fusion. arXiv preprint arXiv:2510.03876. 2025 Oct 4.
[30] Ogundokun RO, Li A, Babatunde RS, Umezuruike C, Sadiku PO, Abdulahi AT, Babatunde AN. Enhancing skin cancer detection and classification in dermoscopic images through concatenated MobileNetV2 and xception models. Bioengineering. 2023 Aug 19;10(8):979.
[31] Srinivasu PN, SivaSai JG, Ijaz MF, Bhoi AK, Kim W, Kang JJ. Classification of skin disease using deep learning neural networks with MobileNet V2 and LSTM. Sensors. 2021 Apr 18;21(8):2852.
[32] Jyothi UP, Dabbiru M, Bonthu S, Dayal A, Kandula NR. Comparative analysis of classification methods to predict diabetes mellitus on noisy data. In Machine Learning, Image Processing, Network Security and Data Sciences: Select Proceedings of 3rd International Conference on MIND 2021 2023 Jan 1 (pp. 301-313). Singapore: Springer Nature Singapore.
[33] Uppalapati PJ, Bhogesh KG, Gundu P, Hussain SM, Narasimharao K. A machine learning approach to identifying phishing websites: a comparative study of classification models and ensemble learning techniques. EAI Endorsed Transactions on Scalable Information Systems. 2023 May 1;10(5).
[34] Bajwa MN, Muta K, Malik MI, Siddiqui SA, Braun SA, Homey B, Dengel A, Ahmed S. Computer-aided diagnosis of skin diseases using deep neural networks. Applied Sciences. 2020 Apr 4;10(7):2488.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Padma Jyothi Uppalapati, Dr. Sridevi Bonthu, Leelavathi Arepalli
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
