IEEE Trans Biomed Eng. 2020 Nov;67(11):3026-3034. doi: 10.1109/TBME.2020.2974650. Epub 2020 Feb 18.
Prediction of post-hemorrhagic hydrocephalus (PHH) outcome-i.e., whether it requires intervention or not-in premature neonates using cranial ultrasound (CUS) images is challenging. In this paper, we present a novel fully-automatic method to perform phenotyping of the brain lateral ventricles and predict PHH outcome from CUS.
Our method consists of two parts: ventricle quantification followed by prediction of PHH outcome. First, cranial bounding box and brain interhemispheric fissure are detected to determine the anatomical position of ventricles and correct the cranium rotation. Then, lateral ventricles are extracted using a new deep learning-based method by incorporating the convolutional neural network into a probabilistic atlas-based weighted loss function and an image-specific adaption. PHH outcome is predicted using a support vector machine classifier trained using ventricular morphological phenotypes and clinical information.
Experiments demonstrated that our method achieves accurate ventricle segmentation results with an average Dice similarity coefficient of 0.86, as well as very good PHH outcome prediction with accuracy of 0.91.
Automatic CUS-based ventricular phenotyping in premature newborns could objectively and accurately predict the progression to severe PHH.
Early prediction of severe PHH development in premature newborns could potentially advance criteria for diagnosis and offer an opportunity for early interventions to improve outcome.
利用头颅超声（CUS）图像预测早产儿迟发性脑积水（PHH）的结局，即是否需要干预，这是具有挑战性的。本文提出了一种新的全自动方法，用于对脑侧脑室进行表型分析，并从 CUS 预测 PHH 的结局。
我们的方法包括两部分：脑室定量和 PHH 结局预测。首先，检测颅边界框和大脑半球间裂，以确定脑室的解剖位置并校正颅骨旋转。然后，通过将卷积神经网络纳入基于概率图谱的加权损失函数和特定于图像的自适应方法，使用新的基于深度学习的方法提取侧脑室。使用基于脑室形态表型和临床信息的支持向量机分类器来预测 PHH 结局。
实验表明，我们的方法在脑室分割方面取得了准确的结果，平均 Dice 相似系数为 0.86，在 PHH 结局预测方面也取得了非常好的效果，准确率为 0.91。
基于 CUS 的自动脑室表型分析可客观、准确地预测早产儿严重 PHH 的进展。
早期预测早产儿严重 PHH 的发生，可能有助于提前制定诊断标准，并为早期干预提供机会，以改善结局。
