Scholarlink

<p>Accurate classification of burn severity is crucial for effective clinical treatment; however, existing methods often fail to balance precision and real-time performance. To address this challenge, we propose a deep learning-based approach utilizing an enhanced ResNet18 architecture with integrated attention mechanisms to improve classification accuracy. The system consists of data preprocessing, classification, optimization, and post-processing modules. The optimization strategy employs an adaptive learning rate combining cosine annealing and class-specific gradient adaptation, alongside targeted adjustments for class imbalance, while an improved Adam optimizer enhances convergence stability. Post-processing incorporates confidence filtering (threshold 0.3) and selective evaluation, with weighted aggregation-integrating dynamic accuracy calculation and moving average to refine predictions and enhance diagnostic reliability. Experimental results on a burn skin test dataset demonstrate that the proposed model achieves a classification accuracy of 99.19% ± 0.12 and a mean average precision (mAP) of 98.72% ± 0.10, highlighting its potential for real-time clinical burn assessment.</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

Enhancing Burn Diagnosis through SE-ResNet18 and Confidence Filtering

  • 期刊论文

  • 发表日期：

    2025年4月8日

查看全文
  • Hanyue Mo,
  • Ziwen Kuang,
  • Haoxuan Wang,
  • Xinyi Cai,
  • Kun Cheng

摘要

Accurate classification of burn severity is crucial for effective clinical treatment; however, existing methods often fail to balance precision and real-time performance. To address this challenge, we propose a deep learning-based approach utilizing an enhanced ResNet18 architecture with integrated attention mechanisms to improve classification accuracy. The system consists of data preprocessing, classification, optimization, and post-processing modules. The optimization strategy employs an adaptive learning rate combining cosine annealing and class-specific gradient adaptation, alongside targeted adjustments for class imbalance, while an improved Adam optimizer enhances convergence stability. Post-processing incorporates confidence filtering (threshold 0.3) and selective evaluation, with weighted aggregation-integrating dynamic accuracy calculation and moving average to refine predictions and enhance diagnostic reliability. Experimental results on a burn skin test dataset demonstrate that the proposed model achieves a classification accuracy of 99.19% ± 0.12 and a mean average precision (mAP) of 98.72% ± 0.10, highlighting its potential for real-time clinical burn assessment.