PDF(Pubmed)
Abstract：
BACKGROUND: The aim of this study was to develop a pipeline using state-of-the-art deep learning methods to automatically delineate and measure several of the most important brain structures in fetal brain ultrasound (US) images.
METHODS: The dataset was composed of 5,331 images of the fetal brain acquired during the routine mid-trimester US scan. Our proposed pipeline automatically performs the following three steps: brain plane classification (transventricular, transthalamic, or transcerebellar plane); brain structures delineation (9 different structures); and automatic measurement (from the structure delineations). The methods were trained on a subset of 4,331 images and each step was evaluated on the remaining 1,000 images.
RESULTS: Plane classification reached 98.6% average class accuracy. Brain structure delineation obtained an average pixel accuracy higher than 96% and a Jaccard index higher than 70%. Automatic measurements get an absolute error below 3.5% for the four standard head biometries (head circumference, biparietal diameter, occipitofrontal diameter, and cephalic index), 9% for transcerebellar diameter, 12% for cavum septi pellucidi ratio, and 26% for Sylvian fissure operculization degree.
CONCLUSIONS: The proposed pipeline shows the potential of deep learning methods to delineate fetal head and brain structures and obtain automatic measures of each anatomical standard plane acquired during routine fetal US examination.
METHODS: The dataset was composed of 5,331 images of the fetal brain acquired during the routine mid-trimester US scan. Our proposed pipeline automatically performs the following three steps: brain plane classification (transventricular, transthalamic, or transcerebellar plane); brain structures delineation (9 different structures); and automatic measurement (from the structure delineations). The methods were trained on a subset of 4,331 images and each step was evaluated on the remaining 1,000 images.
RESULTS: Plane classification reached 98.6% average class accuracy. Brain structure delineation obtained an average pixel accuracy higher than 96% and a Jaccard index higher than 70%. Automatic measurements get an absolute error below 3.5% for the four standard head biometries (head circumference, biparietal diameter, occipitofrontal diameter, and cephalic index), 9% for transcerebellar diameter, 12% for cavum septi pellucidi ratio, and 26% for Sylvian fissure operculization degree.
CONCLUSIONS: The proposed pipeline shows the potential of deep learning methods to delineate fetal head and brain structures and obtain automatic measures of each anatomical standard plane acquired during routine fetal US examination.
摘要：
背景：这项研究的目的是使用最先进的深度学习方法开发一种管道，以自动描绘和测量胎儿脑超声图像中几个最重要的大脑结构。
方法：数据集由在妊娠中期常规超声扫描期间采集的5,331张胎儿大脑图像组成。我们建议的管道自动执行以下三个步骤：大脑平面分类(跨心室，丘脑或小脑平面）；脑结构描绘（9种不同的结构）；和自动测量（从结构描绘）。这些方法是在4,331张图像的子集上进行训练的，每个步骤都在剩余的1,000张图像上进行评估。
结果：平面分类平均分类准确率达到98.6%。脑结构描绘获得了高于96%的平均像素精度和高于70%的Jaccard指数。自动测量得到的绝对误差低于3.5%的四个标准头围(头围,双顶直径，枕额直径和头指数），9%为经小脑直径，透明隔腔比例为12％，西尔维安裂隙操作度为26％。
结论：拟议的管道显示了深度学习方法描绘胎儿头部和大脑结构的潜力，并获得在常规胎儿超声检查期间获得的每个解剖标准平面的自动测量。
方法：数据集由在妊娠中期常规超声扫描期间采集的5,331张胎儿大脑图像组成。我们建议的管道自动执行以下三个步骤：大脑平面分类(跨心室，丘脑或小脑平面）；脑结构描绘（9种不同的结构）；和自动测量（从结构描绘）。这些方法是在4,331张图像的子集上进行训练的，每个步骤都在剩余的1,000张图像上进行评估。
结果：平面分类平均分类准确率达到98.6%。脑结构描绘获得了高于96%的平均像素精度和高于70%的Jaccard指数。自动测量得到的绝对误差低于3.5%的四个标准头围(头围,双顶直径，枕额直径和头指数），9%为经小脑直径，透明隔腔比例为12％，西尔维安裂隙操作度为26％。
结论：拟议的管道显示了深度学习方法描绘胎儿头部和大脑结构的潜力，并获得在常规胎儿超声检查期间获得的每个解剖标准平面的自动测量。
