文献速递腹部技术与安全US

基于自注意力机制与集成学习的神经网络分类算法用于MASLD超声图像

Neural Network Classification Algorithm Based on Self-attention Mechanism and Ensemble Learning for MASLD Ultrasound Images.
PubMed 文献 · Ultrasound Med Biol · 2024-06-22

提出融合预训练VGG16网络、自注意力机制与堆叠集成学习(逻辑回归、随机森林、支持向量机)的混合模型,对正常、轻度、中度、重度脂肪肝超声图像进行四分类。混合模型准确率91.34%,较预训练VGG16加入自注意力机制提升3.02%,堆叠集成后准确率超过任一单一分类器(LR 89.86%、SVM 90.34%、RF 90.73%)。

要点

  • 混合模型对正常、轻度、中度、重度脂肪肝超声图像四分类准确率达91.34%。
  • 较预训练VGG16模型,加入自注意力机制使准确率提升3.02%。
  • 堆叠集成分类器准确率91.34%,超过LR 89.86%、SVM 90.34%、RF 90.73%。

核心结论

  • 所提出的混合方法能有效提高MASLD超声图像检测的效率与准确率,且抗干扰稳健性优于传统神经网络算法。

研究设计与样本

  • 研究提出融合预训练VGG16网络、自注意力机制与堆叠集成学习(逻辑回归、随机森林、支持向量机)的混合模型,基于超声图像进行正常、轻度、中度、重度脂肪肝四分类。

诊断标准与关键数值

  • 混合模型对正常、轻度、中度、重度脂肪肝超声图像四分类准确率为91.34%。
  • 与预训练VGG16模型相比,加入自注意力机制使准确率提升3.02%。
  • 堆叠集成学习模型作为分类器使准确率提升至91.34%,超过逻辑回归89.86%、支持向量机90.34%、随机森林90.73%。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND: Ultrasound image examination has become the preferred choice for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD) due to its non-invasive nature. Computer-aided diagnosis (CAD) technology can assist doctors in avoiding deviations in the detection and classification of MASLD.

METHOD: We propose a hybrid model that integrates the pre-trained VGG16 network with an attention mechanism and a stacking ensemble learning model, which is capable of multi-scale feature aggregation based on the self-attention mechanism and multi-classification model fusion (Logistic regression, random forest, support vector machine) based on stacking ensemble learning. The proposed hybrid method achieves four classifications of normal, mild, moderate, and severe fatty liver based on ultrasound images.

RESULT AND CONCLUSION: Our proposed hybrid model reaches an accuracy of 91.34% and exhibits superior robustness against interference, which is better than traditional neural network algorithms. Experimental results show that, compared with the pre-trained VGG16 model, adding the self-attention mechanism improves the accuracy by 3.02%. Using the stacking ensemble learning model as a classifier further increases the accuracy to 91.34%, exceeding any single classifier such as LR (89.86%) and SVM (90.34%) and RF (90.73%). The proposed hybrid method can effectively improve the efficiency and accuracy of MASLD ultrasound image detection.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Guo L, Shi L, Wang W, et al. Neural Network Classification Algorithm Based on Self-attention Mechanism and Ensemble Learning for MASLD Ultrasound Images. Ultrasound Med Biol. 2024. PMID: 38910034. doi:10.1016/j.ultrasmedbio.2024.05.011

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。