| 摘要: |
| 超声图像检查因其无创性而成为诊断非酒精性脂肪性肝病(NAFLD)的优先选择,计算机辅助诊断(CAD)技术的引入可以帮助医生减少在NAFLD检测和分类的偏差。为此,提出了一种将结合注意力机制的预训练VGG16网络与stacking集成学习模式相结合的混合模型,集合了基于自注意力机制的多尺度特征聚合和基于stacking集成学习的多分类模型(逻辑回归、随机森林、支持向量机)融合的特性,实现基于肝脏超声图像的正常肝脏、轻度脂肪肝、中度脂肪肝、重度脂肪肝的四分类,准确率为91.34%,略优于传统神经网络算法。实验结果表明,相比于VGG16预训练模型,引入自注意力机制使得准确率提高了3.02%,使用stacking集成学习模型作为分类器进一步将准确率提高到 91.34%,超过了 LR(89.86%)、SVM(90.34%)和 RF(90.73%)等单一分类器。该方法能有效提升NAFLD超声图像检测的效率和准确性。 |
| 关键词: 超声图像 NAFLD VGG 自注意力 集成学习 |
| DOI： |
| 投稿时间：2023-12-04修订日期：2023-12-25 |
| 基金项目:山西省基础研究计划(自由探索类)项目(20210302124433)；山西省高等学校科技创新计划项目(2023L112) |
|
| Self-attention-based neural network classification algorithm for NAFLD ultrasound images |
| Guo Lijuan,Shi Liling,Wang Wenjuan,Wang Xiaotong |
| (Children’s Hospital of Shanxi Women Health Center of Shanxi) |
| Abstract: |
| Ultrasound image examination has become the preferred choice for diagnosing non-alcoholic fatty liver disease (NAFLD) due to its non-invasive. Computer-aided diagnosis (CAD) technology can help doctors avoiding deviations of detection and classification in NAFLD. Therefore, we propose a hybrid model that combines the pre-trained VGG16 network combined with the attention mechanism and the stacking ensemble learning model, which has ability 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, and it reaches an accuracy of 91.34%, which is slightly better than traditional neural network algorithms. Experimental results show that compared with the pretrained 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 one 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 NAFLD ultrasound image detection. |
| Key words: ultrasound image, NAFLD, VGG, self-attention, ensemble learning |
