Fully Automated Placental Volume Quantification From 3D Ultrasound for Prediction of Small-for-Gestational-Age Infants.
Fully Automated Placental Volume Quantification From 3D Ultrasound for Prediction of Small-for-Gestational-Age Infants.
复制标题
DOI：
10.1002/jum.15835
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Oguz B
中科院分区：
文献类型：
--
作者：
Schwartz N;Oguz I;Wang J;Pouch A;Yushkevich N;Parameshwaran S;Gee J;Yushkevich P;Oguz B
早期胎盘体积（PV）与小于第10/第5百分位数（SGA 10/SGA 5）的小于胎龄儿相关。3DUS的手动或半自动PV定量是时间密集型的，限制了其纳入临床护理。我们设计了一种新的卷积神经网络（CNN）管道，用于从3DUS图像中进行全自动胎盘分割，探索计算的PV和SGA之间的关联。从妊娠11-14周的单胎妊娠中获得的3DUS体积由我们的CNN管道自动分割，并在99/25图像上进行训练和测试，将两个2D和一个3D模型与下采样/上采样架构相结合。从自动分割（PVCNN）中获得的PV用于训练SGA 10/SGA 5的多变量逻辑回归分类器。将预测SGA的测试性能与通过半自动VOCAL（GE-Healthcare）方法（PVVOCAL）获得的PV进行比较。我们纳入了442例受试者，分别有37例（8.4%）和18例（4.1%）SGA 10/SGA 5婴儿。我们的分割管道在独立测试集上的平均Dice得分为0.88。包括PVCNN或PVVOCAL的调整模型对SGA 10的预测相似（AUC：PVCNN=0.780，PVVOCAL=0.768）。将PVCNN添加到不包括任何PV的临床模型（AUC=0.725）中产生AUC的统计学显著改善（P<0.05）;而PVVOCAL没有（P=0.105）。此外，当预测SGA 5时，包括PVCNN（0.897）带来了与临床模型（0.839，P=0.015）以及PVVOCAL模型（0.870，P=0.039）相比的统计学显著改善。从我们的CNN分割管道中获得的孕早期胎盘体积测量值与未来的SGA显著相关。这一全自动工具能够将胎盘体积生物测量纳入床旁临床评价，作为风险分层和患者咨询的多变量预测模型的一部分。
Early placental volume (PV) has been associated with small-for-gestational-age infants born under the 10th/5th centiles (SGA10/SGA5). Manual or semi-automated PV quantification from 3DUS is time-intensive, limiting its incorporation into clinical care. We devised a novel convolutional neural network (CNN) pipeline for fully-automated placenta segmentation from 3DUS images, exploring the association between the calculated PV and SGA. 3DUS volumes obtained from singleton pregnancies at 11–14 weeks’ gestation were automatically segmented by our CNN pipeline trained and tested on 99/25 images, combining two 2D and one 3D models with downsampling/upsampling architecture. The PVs derived from the automated segmentations (PVCNN) were used to train multi-variable logistic-regression classifiers for SGA10/SGA5. The test performance for predicting SGA was compared to PVs obtained via the semi-automated VOCAL (GE-Healthcare) method (PVVOCAL). We included 442 subjects with 37 (8.4%) and 18 (4.1%) SGA10/SGA5 infants, respectively. Our segmentation pipeline achieved a mean Dice score of 0.88 on an independent test-set. Adjusted models including PVCNN or PVVOCAL were similarly predictive of SGA10 (AUCs: PVCNN=0.780, PVVOCAL=0.768). The addition of PVCNN to a clinical model without any PV included (AUC=0.725) yielded statistically significant improvement in AUC (P<0.05); whereas, PVVOCAL did not (P=0.105). Moreover, when predicting SGA5, including the PVCNN (0.897) brought statistically significant improvement over both the clinical model (0.839, P=0.015), as well as the PVVOCAL model (0.870, P=0.039). First trimester placental volume measurements derived from our CNN segmentation pipeline are significantly associated with future SGA. This fully automated tool enables the incorporation of including placental volumetric biometry into the bedside clinical evaluation as part of a multi-variable prediction model for risk stratification and patient counseling.
登录
查看更多内容
影响因子：
3.8
作者：
Hafner, E.;Metzenbauer, M.;Philipp, K.
通讯作者：
Philipp, K.
影响因子：
9.8
作者：
Schwartz, Nadav;Sammel, Mary D.;Leite, Rita;Parry, Samuel
通讯作者：
Parry, Samuel
影响因子：
7.1
作者：
Schwartz, N.;Wang, E.;Parry, S.
通讯作者：
Parry, S.
影响因子：
7.1
作者：
Roberge, S.;Nicolaides, K. H.;Bujold, E.
通讯作者：
Bujold, E.
影响因子：
2.9
作者：
DRUCKER, H;CORTES, C;VAPNIK, V
通讯作者：
VAPNIK, V