Article: Skin image analysis for detecting monkeypox disease: utilising new model M-Net, a non-invasive deep learning model Journal: International Journal of Data Mining and Bioinformatics (IJDMB) 2026 Vol.30 No.3/4 pp.316 - 341 Abstract: Skin and skin-related diseases pose a significant public health challenge worldwide, leading to major concerns in medical diagnosis. Various environmental factors, including bacteria, fungi, and viruses, can contribute to these conditions, resulting in a growing number of individuals affected by skin diseases. Most physicians rely on manual biopsy tests for skin disease diagnosis, which can cause delays in timely treatment. Therefore, there is a high demand for automated skin disease classification systems to provide quick and accurate results. Deep learning (DL) has recently shown remarkable effectiveness in image-based classification tasks, such as identifying skin cancer, rosacea, melanocytic nevus, tumour cells, and COVID-19 patients. Consequently, DL can also be adapted to detect monkeypox skin disease. In this article, we propose a novel approach consisting of two phases. First, new HR, UOR, and BR algorithms will be used to preprocess the images. Second, a custom CNN model will be developed for monkeypox classification. The proposed model is compared with existing approaches in the literature and demonstrates superior performance, achieving an accuracy of 95%. Inderscience Publishers - linking academia, business and industry through research

Title: Skin image analysis for detecting monkeypox disease: utilising new model M-Net, a non-invasive deep learning model

Authors: Vinod Kumar Yadav; Rajitha Bakthula

Addresses: Department of Computer Science and Engineering, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, India ' Department of Computer Science and Engineering, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, India

Abstract: Skin and skin-related diseases pose a significant public health challenge worldwide, leading to major concerns in medical diagnosis. Various environmental factors, including bacteria, fungi, and viruses, can contribute to these conditions, resulting in a growing number of individuals affected by skin diseases. Most physicians rely on manual biopsy tests for skin disease diagnosis, which can cause delays in timely treatment. Therefore, there is a high demand for automated skin disease classification systems to provide quick and accurate results. Deep learning (DL) has recently shown remarkable effectiveness in image-based classification tasks, such as identifying skin cancer, rosacea, melanocytic nevus, tumour cells, and COVID-19 patients. Consequently, DL can also be adapted to detect monkeypox skin disease. In this article, we propose a novel approach consisting of two phases. First, new HR, UOR, and BR algorithms will be used to preprocess the images. Second, a custom CNN model will be developed for monkeypox classification. The proposed model is compared with existing approaches in the literature and demonstrates superior performance, achieving an accuracy of 95%.

Keywords: image pre-processing; classification; hair removal; object removal; background removal; data augmentation.

DOI: 10.1504/IJDMB.2026.154702

International Journal of Data Mining and Bioinformatics, 2026 Vol.30 No.3/4, pp.316 - 341

Received: 02 Apr 2024
Accepted: 10 Sep 2024
Published online: 10 Jul 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Skin image analysis for detecting monkeypox disease: utilising new model M-Net, a non-invasive deep learning model

Keep up-to-date