IEEE J Biomed Health Inform. 2023 Nov;27(11):5518-5529. doi: 10.1109/JBHI.2023.3303573. Epub 2023 Nov 7.
Fetal congenital heart disease (FCHD) is a common, serious birth defect affecting ∼1% of newborns annually. Fetal echocardiography is the most effective and important technique for prenatal FCHD diagnosis. The prerequisites for accurate ultrasound FCHD diagnosis are accurate view recognition and high-quality diagnostic view extraction. However, these manual clinical procedures have drawbacks such as, varying technical capabilities and inefficiency. Therefore, the automatic identification of high-quality multiview fetal heart scan images is highly desirable to improve prenatal diagnosis efficiency and accuracy of FCHD. Here, we present a framework for multiview fetal heart ultrasound image recognition and quality assessment that comprises two parts: a multiview classification and localization network (MCLN) and an improved contrastive learning network (ICLN). In the MCLN, a multihead enhanced self-attention mechanism is applied to construct the classification network and identify six accurate and interpretable views of the fetal heart. In the ICLN, anatomical structure standardization and image clarity are considered. With contrastive learning, the absolute loss, feature relative loss and predicted value relative loss are combined to achieve favorable quality assessment results. Experiments show that the MCLN outperforms other state-of-the-art networks by 1.52-13.61% when determining the F1 score in six standard view recognition tasks, and the ICLN is comparable to the performance of expert cardiologists in the quality assessment of fetal heart ultrasound images, reaching 97% on a test set within 2 points for the four-chamber view task. Thus, our architecture offers great potential in helping cardiologists improve quality control for fetal echocardiographic images in clinical practice.
胎儿先天性心脏病（Fetal Congenital Heart Disease，FCHD）是一种常见且严重的出生缺陷，每年影响约 1%的新生儿。胎儿超声心动图是产前 FCHD 诊断最有效和最重要的技术。准确的超声 FCHD 诊断的前提是准确的视图识别和高质量的诊断视图提取。然而，这些手动的临床程序存在技术能力和效率不同等缺点。因此，自动识别高质量的多视图胎儿心脏扫描图像对于提高产前诊断效率和 FCHD 的准确性非常有必要。在这里，我们提出了一种多视图胎儿心脏超声图像识别和质量评估框架，该框架包括两部分：多视图分类和定位网络（Multiview Classification and Localization Network，MCLN）和改进的对比学习网络（Improved Contrastive Learning Network，ICLN）。在 MCLN 中，应用多头增强自注意力机制构建分类网络，以识别胎儿心脏的六个准确和可解释的视图。在 ICLN 中，考虑了解剖结构标准化和图像清晰度。通过对比学习，将绝对损失、特征相对损失和预测值相对损失相结合，实现了良好的质量评估结果。实验表明，在确定六个标准视图识别任务的 F1 分数时，MCLN 比其他最先进的网络表现好 1.52-13.61%，而 ICLN 在胎儿心脏超声图像的质量评估方面与专家心脏病学家的表现相当，在四腔心视图任务中，在测试集上达到了 97%，误差为 2 分。因此，我们的架构在帮助心脏病学家提高临床实践中胎儿超声心动图图像的质量控制方面具有很大的潜力。
