Softflatten-Net: A Deep Convolutional Neural Network Design for Monkeypox Classification From Digital Skin Lesions Images
- 26 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 32566-32576
Abstract
In scenarios where smallpox has been eradicated, the most important human orthopoxvirus pandemic is monkeypox (MP), which is a zoonotic disease that spreads more often. MP is difficult to diagnose, as it has characteristics similar to smallpox, chickenpox (CP), and measles (MS). Polymerise chain reaction (PCR), computerized histopathological nucleic acid amplification test (NAAT), immuno-histo-chemistry, enzyme-linked immunosorbent assay (ELISA) and electron microscope-based skin lesion testing are used for MP detection. But these tests are time consuming and may lead to false decision. Therefore, automation in MP detection using skin lesions images is needed for developing affordable and fast solutions. In this work, we have proposed a deep convolutional neural network architecture named the Softflatten-Net to identify and categorize MP using skin lesions. This architecture helps to avoid gradient vanishing and over-fitting problems. Classification has been conducted in seven distinct scenarios: MP vs normal (NH), MP vs. MS, MP vs. CP, MP vs. other, MP vs. CP vs. NH, MP vs. CP vs. MS, and MP vs. CP vs. MS vs. NH. Among binary classification tasks, the Softflatten-Net achieved the maximum classification accuracy (Ac) of 97.25%, sensitivity (Sen) of 92.94%, and precision (Pr) of 96.48% in classifying MP from other categories of skin images. In the three-class classification task (MP vs CP vs NH), the proposed network achieved an Ac of 94.71%, Pr of 92.11%, and Sen of 87.87%. In the four-class classification scenario, namely MP vs CP vs MS vs NH, the proposed model achieved Ac, Pr, and Sen values of 90. 73%, 84. 21% and 69. 38%, respectively. Furthermore, we have considered 4,241 skin images from IEEE data-port for nine class classification and 28,771 images from Dermnet for twenty-one class classification to validate the performance of proposed Softflatten-Net architecture. The proposed architecture performed satisfactorily on all the three datasets considered in this work and outperformed the existing state-of-the-art models in the literature. Post-image analysis is performed via local interpretable model-agnostic explanations (LIME), gradient class activation maps (G-CAM) and occlusion sensitivity (OS) approaches. In addition, to analyze misclassification, the stochastic neighbor embedding distributed with t (t-SNE) is employed. Visualization techniques aided in identifying the image regions most pertinent for classification. he proposed network can be utilized for early and reliable detection of MP using images of skin lesions.Keywords
This publication has 45 references indexed in Scilit:
- Human Monkeypox Classification from Skin Lesion Images with Deep Pre-trained Network using Mobile ApplicationJournal of Medical Systems, 2022
- Monkeypox Virus Detection Using Pre-trained Deep Learning-based ApproachesJournal of Medical Systems, 2022
- A deep learning based approach for automatic detection of COVID-19 cases using chest X-ray imagesBiomedical Signal Processing and Control, 2021
- Real‑time COVID-19 diagnosis from X-Ray images using deep CNN and extreme learning machines stabilized by chimp optimization algorithmBiomedical Signal Processing and Control, 2021
- Coronavirus (COVID-19) detection from chest radiology images using convolutional neural networksBiomedical Signal Processing and Control, 2021
- Attention-based VGG-16 model for COVID-19 chest X-ray image classificationApplied Intelligence, 2020
- Brain tumor detection using fusion of hand crafted and deep learning featuresCognitive Systems Research, 2020
- Deep Learning in Medicine—Promise, Progress, and ChallengesJAMA Internal Medicine, 2019
- The skin cancer classification using deep convolutional neural networkMultimedia Tools and Applications, 2018
- Facial Skin Classification Using Convolutional Neural Networks2017