Scholarlink

<p>In the intricate landscape of dermatological diagnostics, traditional methodologies often necessitate the specialized expertise of healthcare professionals to discern between subtly varying skin conditions. To bridge this gap, our research advances a computational framework that amalgamates classical convolutional neural networks (CNNs) with custom-designed layers for nuanced skin lesion classification. The model accommodates 224 × 224 pixel images across three color channels (RGB) and counters inconsistencies such as variable lighting through data augmentation techniques like random contrast adjustments. Established architectures like VGG16 and ResNet101 are employed via transfer learning for initial feature extraction. Unique to our model are custom layers: a Fourier layer for frequency domain characteristics, a Laplacian layer for edge detection, a Gabor layer for texture analysis, an RGB-to-HSV layer for color variation, and a histogram equalization layer for image contrast. These are aggregated in a ‘CombinedOutput’ layer and processed by feed-forward layer-X and layer-A using GELU activation and batch normalization. A final concatenation layer leads to a softmax-activated prediction layer. We employed exhaustive performance evaluation metrics: Accuracy, Precision, Recall, AUC, F1. Our best-performing custom model exhibited a Recall of 94.2%, Accuracy of 94.2%, Precision of 94.2%, AUC of 97.8%, F1 of 94.2%. Comparatively, the ConvNeXtXLarge model, which did not employ the custom layers, achieved a Recall of 92.6%, Accuracy of 92.7%. This differential performance attests to the efficacy of our hybrid architecture, which integrates both traditional and custom-designed neural layers. Thus, our multi-layered architecture not only showcases superior diagnostic capabilities but also stands as a promising candidate for early-stage clinical implementations, particularly in the timely detection of melanoma, where early identification is pivotal for effective treatment and containment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Transforming Dermatological Diagnostics: An Integrated CNN Approach with Specialized Feature Extraction Layers

  • 期刊论文

  • 发表日期：

    2026年5月28日

查看全文
  • Sushopti Gawade,
  • Kshitij Patil,
  • Shivalika Pillai,
  • Swati Chopade,
  • Ashok Bhansali

摘要

In the intricate landscape of dermatological diagnostics, traditional methodologies often necessitate the specialized expertise of healthcare professionals to discern between subtly varying skin conditions. To bridge this gap, our research advances a computational framework that amalgamates classical convolutional neural networks (CNNs) with custom-designed layers for nuanced skin lesion classification. The model accommodates 224 × 224 pixel images across three color channels (RGB) and counters inconsistencies such as variable lighting through data augmentation techniques like random contrast adjustments. Established architectures like VGG16 and ResNet101 are employed via transfer learning for initial feature extraction. Unique to our model are custom layers: a Fourier layer for frequency domain characteristics, a Laplacian layer for edge detection, a Gabor layer for texture analysis, an RGB-to-HSV layer for color variation, and a histogram equalization layer for image contrast. These are aggregated in a ‘CombinedOutput’ layer and processed by feed-forward layer-X and layer-A using GELU activation and batch normalization. A final concatenation layer leads to a softmax-activated prediction layer. We employed exhaustive performance evaluation metrics: Accuracy, Precision, Recall, AUC, F1. Our best-performing custom model exhibited a Recall of 94.2%, Accuracy of 94.2%, Precision of 94.2%, AUC of 97.8%, F1 of 94.2%. Comparatively, the ConvNeXtXLarge model, which did not employ the custom layers, achieved a Recall of 92.6%, Accuracy of 92.7%. This differential performance attests to the efficacy of our hybrid architecture, which integrates both traditional and custom-designed neural layers. Thus, our multi-layered architecture not only showcases superior diagnostic capabilities but also stands as a promising candidate for early-stage clinical implementations, particularly in the timely detection of melanoma, where early identification is pivotal for effective treatment and containment.