Semantic Organ Segmentation in 3D Whole-Body MR Images
Semantic Organ Segmentation in 3D Whole-Body MR Images
复制标题
DOI：
10.1109/icip.2018.8451205
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
T. Küstner;Sarah Müller;Marc Fischer;Jakob Weiss;K. Nikolaou;F. Bamberg;Bin Yang;F. Schick;S. Gatidis
中科院分区：
文献类型：
--
作者：
T. Küstner;Sarah Müller;Marc Fischer;Jakob Weiss;K. Nikolaou;F. Bamberg;Bin Yang;F. Schick;S. Gatidis
自动器官分割是在具有数千名参与者的大型队列中有效分析MR数据的先决条件。以前提出的方法的可行性和普遍性大多已在较小的队列中得到证明。这项工作的目的是实现和验证自动语义3D分割的肝脏和脾脏的多对比MR数据的身体躯干，这是在一个大型流行病学成像研究的目的，以提供一个强大的和一般的设置在有限的训练数据的设置。由经验丰富的放射科医生在173张MR图像中手动分割肝脏和脾脏，提供标记的地面实况。随机选择不同数量的训练数据集来训练基于卷积神经网络（CNN）的分割，并进行4倍患者遗漏交叉验证，并与基于随机森林（RF）的分割进行比较。参与者之间的验证显示，肝/脾分割的准确率高达99.7%/99.9%，CNN优于RF。总之，自动语义器官分割是可行的，在一个强大的和一般的设置。
Automated organ segmentation is a prerequisite for efficient analysis of MR data in large cohorts with thousands of participants. The feasibility and generalizability of previously proposed methods has mostly been demonstrated in smaller cohorts. The aim of this work is to implement and validate automated semantic 3D segmentation of liver and spleen on multi-contrast MR data of the body trunk which were acquired in a large epidemiological imaging study with the objective to provide a robust and general setup in a setting of limited training data. Liver and spleen were manually segmented in 173 MR images by an experienced radiologist, providing labeled ground-truth. Varying amount of training datasets were randomly chosen to train a convolutional neural network (CNN)-based segmentation with 4-fold patient-leave-out cross-validation and compared against a Random Forest (RF)-based segmentation. Validation amongst participants revealed high accuracies of 99.7%/99.9% for liver/spleen-segmentation with superiority of CNN to RF. In conclusion, automated semantic organ segmentation is feasible in a robust and general setup.