Treffer: A hybrid deep learning framework for skin disease localization and classification using wearable sensors.

Accurate detection of skin diseases is essential for timely intervention and treatment. This article proposes a patch-based, interpretable deep learning framework for skin disease detection using wearable sensors and clinical data. Specifically, a fully convolutional residual neural network (FCRN) is employed to extract local features from high-resolution skin images captured via wearable sensors, using a patch-level training approach. Pre-processing techniques—including image resampling, intensity normalization, and noise reduction—standardize the input data to ensure consistency across sensor variations. To enhance local feature learning, the FCRN incorporates residual modules, which mitigate gradient vanishing and improve model performance. The framework generates disease probability maps that visualize regions of high diagnostic risk, providing interpretable insights into skin anomalies. In the proposed methodology, a convolutional neural network (CNN) integrates image-derived features with clinical data such as patient demographics, symptoms, and medical history. This CNN-based multimodal fusion approach improves the model's ability to capture spatial relationships and enhances classification performance. Experimental evaluations demonstrate that the proposed framework achieves state-of-the-art results across multiple evaluation metrics, including accuracy, sensitivity, and specificity. The interpretable disease probability maps highlight affected skin regions, enhancing model transparency and clinical usability. This approach demonstrates the potential of combining wearable sensor technology with deep learning for efficient, scalable, and explainable skin disease detection, laying the foundation for real-time clinical applications. [ABSTRACT FROM AUTHOR]

Copyright of PeerJ Computer Science is the property of PeerJ Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)