The performances of medical image processing techniques, in particular CT scans, are usually affected by poor contrast quality introduced by some medical imaging devices. This suggests the use of contrast enhancement methods as a solution to adjust the intensity distribution of the dark image. In this paper, an advanced adaptive and simple algorithm for dark medical image enhancement is proposed. This approach is principally based on adaptive gamma correction using discrete wavelet transform with singular-value decomposition (DWT-SVD). In a first step, the technique decomposes the input medical image into four frequency sub-bands by using DWT and then estimates the singular-value matrix of the low-low (LL) sub-band image. In a second step, an enhanced LL component is generated using an adequate correction factor and inverse singular value decomposition (SVD). In a third step, for an additional improvement of LL component, obtained LL sub-band image from SVD enhancement stage is classified into two main classes (low contrast and moderate contrast classes) based on their statistical information and therefore processed using an adaptive dynamic gamma correction function. In fact, an adaptive gamma correction factor is calculated for each image according to its class. Finally, the obtained LL sub-band image undergoes inverse DWT together with the unprocessed low-high (LH), high-low (HL), and high-high (HH) sub-bands for enhanced image generation. Different types of non-contrast CT medical images are considered for performance evaluation of the proposed contrast enhancement algorithm based on adaptive gamma correction using DWT-SVD (DWT-SVD-AGC). Results show that our proposed algorithm performs better than other state-of-the-art techniques.
14 February 2018 in Signal, Image and Video Processing
Accurate skin cancer classification is essential for early diagnosis and effective treatment planning, enabling timely interventions and improved patient outcomes. In this paper, the performance of four pre-trained models—two convolutional neural networks (ResNet50 and VGG19) and two vision transformers (ViT-b16 and ViT-b32)—is evaluated in distinguishing malignant from benign skin cancers using a publicly available dermoscopic dataset. Among these models, ResNet50 achieved the highest performance across all the evaluation metrics, with accuracy, precision, and recall of 89.09% and an F1 score of 89.08%, demonstrating its ability to effectively capture complex patterns in skin lesion images. While the other models produced competitive results, ResNet50 exhibited superior robustness and consistency. To enhance model interpretability, two eXplainable Artificial Intelligence (XAI) techniques, Local Interpretable Model-Agnostic Explanations (LIME) and integrated gradients, were employed to provide insights into the decision-making process, fostering trust in automated diagnostic systems. These findings underscore the potential of deep learning for automated skin cancer classification and highlight the importance of model transparency for clinical adoption. As AI technology continues to evolve, its integration into clinical workflows could improve diagnostic accuracy, reduce the workload of healthcare professionals, and enhance patient outcomes.
1 July 2025 in Network Modeling Analysis in Health Informatics and Bioinformatics
Skin cancer detection is a crucial task in dermatology, with accurate classification of skin lesions playing a key role in improving patient outcomes. This paper proposes a modified architecture based on Multi-Head Attention Transformer (MMHAT) for skin image classification, specifically targeting the detection of malignant melanoma and melanocytic nevus. The Transformer model leverages self-attention mechanisms to capture complex spatial relationships and contextual information across different regions of skin images, which is essential for distinguishing between various types of lesions. Unlike conventional Convolutional Neural Networks (CNNs), which are limited by kernel size and layer depth, the Transformer’s self-attention mechanism enables it to capture long-range dependencies and reduce reliance on external information, allowing for better internal data correlation. In this work, we utilize a multi-head self-attention module to extract image features, which allows the model to focus on multiple aspects of the image simultaneously, enhancing its ability to detect subtle patterns often missed by traditional CNNs. The model is evaluated on the publicly available ISIC 2018 dataset, containing a diverse range of dermoscopic images. Experimental results show that the proposed Transformer model achieves an accuracy of 0.91, outperforming conventional models such as ResNet50 and Inception V3, which achieved accuracy of 0.90 and 0.84, respectively. Furthermore, experiments with and without multi-head attention demonstrate the significant impact of the attention mechanism in improving model performance, particularly in skin cancer detection.