A Bootstrap Self-training Method for Sequence Transfer: State-of-the-Art Placenta Segmentation in fetal MRI
A Bootstrap Self-training Method for Sequence Transfer: State-of-the-Art Placenta Segmentation in fetal MRI
复制标题
用于序列转移的 Bootstrap 自训练方法：胎儿 MRI 中最先进的胎盘分割
DOI：
10.1007/978-3-030-87735-4_18
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Leo Joskowicz
中科院分区：
文献类型：
--
作者：
Bella Specktor;Daphna Link;Shai Ferster;L. Ben‐Sira;Elka Miller;D. Ben;Leo Joskowicz
在胎儿MRI扫描中对胎盘进行定量体积评估是胎儿健康评估的重要组成部分。然而，胎盘的手动分割是一项耗时的任务，需要专业知识，并遭受高观察者的变化。用于自动分割的深度学习方法是有效的，但需要为每个扫描序列手动注释数据集。我们提出了一种新的方法，通过在不同的MRI序列上进行深度学习来引导自动胎盘分割。该方法包括自动胎盘分割与两个网络上训练的一个序列的标记的情况下，然后自动适应使用相同的网络的自我训练到一个新的序列与新的未标记的情况下，该序列。它使用了一种新的组合轮廓和软骰子损失函数的胎盘ROI检测和分割网络。我们对FIESTA序列的实验研究在21个测试案例中产生了0.847的Dice分数，其中在训练集中只有16个案例。转移到TRUFI序列在15个测试用例中产生了0.78的Dice得分，这比没有转移学习的网络结果有了显着的改进。轮廓Dice损失和自训练方法通过序列转移自举实现最先进的胎盘分割结果。
Quantitative volumetric evaluation of the placenta in fetal MRI scans is an important component of the fetal health evaluation. However, manual segmentation of the placenta is a time-consuming task that requires expertise and suffers from high observer variability. Deep learning methods for automatic segmentation are effective but require manually annotated datasets for each scanning sequence. We present a new method for bootstrapping automatic placenta segmentation by deep learning on different MRI sequences. The method consists of automatic placenta segmentation with two networks trained on labeled cases of one sequence followed by automatic adaptation using self-training of the same network to a new sequence with new unlabeled cases of this sequence. It uses a novel combined contour and soft Dice loss function for both the placenta ROI detection and segmentation networks. Our experimental studies for the FIESTA sequence yields a Dice score of 0.847 on 21 test cases with only 16 cases in the training set. Transfer to the TRUFI sequence yields a Dice score of 0.78 on 15 test cases, a significant improvement over the network results without transfer learning. The contour Dice loss and self-training approach achieve state-of-the art placenta segmentation results by sequence transfer bootstrapping.
影响因子：
48
作者：
Isensee, Fabian;Jaeger, Paul F.;Maier-Hein, Klaus H.
通讯作者：
Maier-Hein, Klaus H.
影响因子：
10.9
作者：
Xia, Yingda;Yang, Dong;Roth, Holger
通讯作者：
Roth, Holger