From the Department of Radiology (T.D., F.D.K., P.D., S.D., M.A.)
School of Biomedical Engineering and Imaging Sciences (L.F., M.E., T.V., S.O.), King's College London, London, UK.
AJNR Am J Neuroradiol. 2023 Apr;44(4):486-491. doi: 10.3174/ajnr.A7808. Epub 2023 Mar 2.
Fetal brain MR imaging is clinically used to characterize fetal brain abnormalities. Recently, algorithms have been proposed to reconstruct high-resolution 3D fetal brain volumes from 2D slices. By means of these reconstructions, convolutional neural networks have been developed for automatic image segmentation to avoid labor-intensive manual annotations, usually trained on data of normal fetal brains. Herein, we tested the performance of an algorithm specifically developed for segmentation of abnormal fetal brains.
This was a single-center retrospective study on MR images of 16 fetuses with severe CNS anomalies (gestation, 21-39 weeks). T2-weighted 2D slices were converted to 3D volumes using a super-resolution reconstruction algorithm. The acquired volumetric data were then processed by a novel convolutional neural network to perform segmentations of white matter and the ventricular system and cerebellum. These were compared with manual segmentation using the Dice coefficient, Hausdorff distance (95th percentile), and volume difference. Using interquartile ranges, we identified outliers of these metrics and further analyzed them in detail.
The mean Dice coefficient was 96.2%, 93.7%, and 94.7% for white matter and the ventricular system and cerebellum, respectively. The Hausdorff distance was 1.1, 2.3, and 1.6 mm, respectively. The volume difference was 1.6, 1.4, and 0.3 mL, respectively. Of the 126 measurements, there were 16 outliers among 5 fetuses, discussed on a case-by-case basis.
Our novel segmentation algorithm obtained excellent results on MR images of fetuses with severe brain abnormalities. Analysis of the outliers shows the need to include pathologies underrepresented in the current data set. Quality control to prevent occasional errors is still needed.
胎儿脑磁共振成像临床上用于描述胎儿脑异常。最近，提出了一些算法来从 2D 切片重建高分辨率 3D 胎儿脑容积。通过这些重建，可以开发卷积神经网络进行自动图像分割，以避免费力的手动注释，通常在正常胎儿脑数据上进行训练。在此，我们测试了专门为异常胎儿脑分割开发的算法的性能。
这是一项单中心回顾性研究，纳入了 16 例严重中枢神经系统异常胎儿（妊娠 21-39 周）的磁共振图像。使用超分辨率重建算法将 T2 加权 2D 切片转换为 3D 容积。然后，使用新的卷积神经网络处理获得的容积数据，对白质、脑室系统和小脑进行分割。使用 Dice 系数、Hausdorff 距离（第 95 百分位）和体积差异将这些分割与手动分割进行比较。使用四分位数间距，我们确定了这些指标的异常值，并进一步进行了详细分析。
白质、脑室系统和小脑的平均 Dice 系数分别为 96.2%、93.7%和 94.7%。Hausdorff 距离分别为 1.1、2.3 和 1.6mm。体积差异分别为 1.6、1.4 和 0.3mL。在 126 个测量值中，有 5 例中的 16 个测量值为异常值，我们逐个病例进行了讨论。
我们的新型分割算法在严重脑异常胎儿的磁共振图像上获得了优异的结果。异常值的分析表明，需要纳入当前数据集中代表性不足的病变。仍然需要进行质量控制以防止偶尔出现的错误。
