| 宋书豪,曾施.应用深度学习模型分类正常胎儿心脏超声切面[J].中国医学影像技术,2025,41(1):70~73 |
| 应用深度学习模型分类正常胎儿心脏超声切面 |
| Deep learning models for classifying normal fetal cardiac ultrasound views |
| 投稿时间：2024-07-14 修订日期：2024-11-01 |
| DOI：10.13929/j.issn.1003-3289.2025.01.015 |
| 中文关键词: 胎儿心脏 超声心动描记术 深度学习 |
| 英文关键词:fetal heart echocardiography deep learning |
| 基金项目:2023年度湖南省自然科学基金项目(2023JJ30743)、长沙市自然科学基金项目(kq2208341)。 |
|
| 摘要点击次数: 375 |
| 全文下载次数: 113 |
| 中文摘要: |
| 目的 观察4种深度学习(DL)模型分类正常胎儿7类心脏超声切面的价值。方法 回顾性纳入200名于孕周18~24+6周接受胎儿心脏超声检查的正常胎儿,按7∶3比例分为训练集(n=140)和测试集(n=60)。收集三血管气管(3VT)切面、心尖四腔心(A4C)切面、主动脉弓长轴切面、双腔静脉切面、左心室流出道(LVOT)切面、三血管(three-vessel, 3V)切面及右心室流出道(right ventricular outflow tract, RVOT)切面二维声像图,经过图像预处理后,采用4种DL模型Vision Transformer(ViT)、Data-efficient Image Transformer(DeiT)、Vision-long short term memory(ViL)及Multi-axis Vision Transformer (MaxViT)分别提取图像特征并构建正常胎儿心脏超声切面模型,以准确率、精确率、召回率及F1分数评估各模型于测试集中分类效能,并以梯度加权类激活映射(Grad-CAM)获取激活特征的热力图可视化图像中最具识别特征的区域。结果 ViT、DeiT、ViL及MaxViT模型分类测试集中正常胎儿心脏超声切面的效能均表现优秀,其中MaxViT为最优模型,准确率、精确率、召回率及F1分数分别为98.93%、98.93%、98.95%及98.93%。Grad-CAM可视化结果显示,以DL模型分类正常胎儿心脏超声7类切面时,心脏、血管所在区域红色最深,对于分类的贡献最大,模型关注度最高。结论 所获4种DL模型分类正常胎儿心脏超声切面均表现优越,尤以MaxViT模型效能最佳,且分类结果的可解释性获得Grad-CAM验证。 |
| 英文摘要: |
| Objective To explore the value of four deep learning (DL) models for classifying 7 cardiac ultrasound views of normal fetus. Methods Two hundred normal fetuses who received fetal cardiac ultrasound examinations in 18 to 24+6 weeks of gestation were retrospectively included and divided into training set (n=140) and test set (n=60) at a ratio of 7∶3. Two-dimensional ultrasound images were collected, including three-vessel and trachea (3VT) view, apical four-chamber (A4C) view, aortic arch long-axis view, bicaval view, left ventricular outflow tract (LVOT) view, three-vessel (3V) view and right ventricular outflow tract (RVOT) view. After image preprocessing, image features were extracted, and then 4 different DL models were constructed for classifying normal fetal cardiac ultrasound views, i.e. Vision Transformer (ViT), Data-efficient Image Transformer (DeiT), Vision-long short term memory (ViL) and Multi-axis Vision Transformer (MaxViT). The classification performance of each model in test set was assessed with accuracy, precision, recall and F1 score. Gradient-weighted class activation mapping (Grad-CAM) was used to obtain heatmaps for visualizing regions with the most distinctive features on ultrasound images. Results All ViT, DeiT, ViL and MaxViT had excellent performance in classifying normal fetal cardiac ultrasound views in test set, among which MaxViT was the optimal one, with accuracy, precision, recall and F1 score of 98.93%, 98.93%, 98.95% and 98.93%, respectively. Grad-CAM visualization results indicated that for classification of 7 cardiac ultrasound views of normal fetus using DL models, the heart and vessels present as the deepest red color, indicating the greatest contribution to the classification, also got the highest attention these models. Conclusion The obtained 4 DL models, especially MaxViT, had good capability for classifying normal fetal cardiac ultrasound views, with the interpretability of classifying results validated by Grad-CAM. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
