Evaluating the impact of MR image harmonization on thalamus deep network segmentation.
Evaluating the impact of MR image harmonization on thalamus deep network segmentation.
复制标题
评估 MR 图像协调对丘脑深度网络分割的影响。
DOI：
10.1117/12.2613159
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Prince,JerryL
中科院分区：
文献类型：
--
作者：
Shao,Muhan;Zuo,Lianrui;Carass,Aaron;Zhuo,Jiachen;Gullapalli,RaoP;Prince,JerryL
医学图像分割是医学图像分析的核心任务之一。脑磁共振图像(MRI)的自动分割可以用于可视化和跟踪由于正常衰老或疾病可能发生的大脑解剖结构的变化。机器学习技术在结构自动分割中有着广泛的应用。然而，训练数据和测试数据之间的对比度差异使得分割算法很难产生一致的结果。为了解决这个问题，可以使用一种称为MR图像协调的图像到图像转换技术来匹配不同数据集之间的对比度。在保持基本解剖结构的同时，变换图像强度对于协调是重要的。本文提出了一种从多个MR图像模式中分割丘脑的3D U-net算法，并研究了协调性对分割算法的影响。可在两个数据集上手动描绘丘脑核团。然而，我们的目标是在另一个缺乏地面真相标签的大型数据集中分析丘脑。我们在一个带有手工标记的数据集上训练了两个分割网络，一个带有非协调图像，另一个具有协调图像，并在另一个带有手动标记的数据集上比较了它们的性能。这两组数据被诊断出患有两种脑部疾病，并通过类似的成像方案获得。统一的目标是没有手动标签的大数据集，它也有不同的成像协议。在未经协调和协调的数据上训练的网络在评估其他数据集时没有显着差异；表明图像协调可以保持解剖结构，不影响分割任务。对这两个网络进行了关于统一目标数据集的评价，根据统一数据培训的网络比根据非协调数据培训的网络有了很大改进。因此，对统一数据进行培训的网络提供了处理来自其他地点的大量数据的潜力，即使在没有具体地点的培训数据的情况下也是如此。
Medical image segmentation is one of the core tasks of medical image analysis. Automatic segmentation of brain magnetic resonance images (MRIs) can be used to visualize and track changes of the brain’s anatomical structures that may occur due to normal aging or disease. Machine learning techniques are widely used in automatic structure segmentation. However, the contrast variation between the training and testing data makes it difficult for segmentation algorithms to generate consistent results. To address this problem, an image–to– image translation technique called MR image harmonization can be used to match the contrast between different data sets. It is important for the harmonization to transform image intensity while maintaining the underlying anatomy. In this paper, we present a 3D U-Net algorithm to segment the thalamus from multiple MR image modalities and investigate the impact of harmonization on the segmentation algorithm. Manual delineations of thalamic nuclei on two data sets are available. However, we aim to analyze the thalamus in another large data set where ground truth labels are lacking. We trained two segmentation networks, one with unharmonized images and the other with harmonized images, on one data set with manual labels, and compared their performances on the other data set with manual labels. These two data groups were diagnosed with two brain disorders and were acquired with similar imaging protocols. The harmonization target is the large data set without manual labels, which also has a different imaging protocol. The networks trained on unharmonized and harmonized data showed no significant difference when evaluating on the other data set; demonstrating that image harmonization can maintain the anatomy and does not affect the segmentation task. The two networks were evaluated on the harmonization target data set and the network trained on harmonized data showed significant improvement over the network trained on unharmonized data. Therefore, the network trained on harmonized data provides the potential to process large amounts of data from other sites, even in the absence of site-specific training data.
登录
查看更多内容
影响因子：
4.6
作者：
R. Pitcher-Wilmott;P. Hindocha;C. Wood
通讯作者：
R. Pitcher-Wilmott;P. Hindocha;C. Wood
不同 IgG 亚类中人类免疫缺陷病毒蛋白的抗体模式。
影响因子：
6.4
作者：
Per Johan Klasse;Jonas Blomberg
通讯作者：
Jonas Blomberg
人类胎儿、脐带和母体血清中的 Gamma G 亚群。
DOI：
--
发表时间：
1973
期刊：
Clinical Immunology and Immunopathology
影响因子：
--
作者：
P. Schur;E. Alpert;C. Alper
通讯作者：
C. Alper
艾滋病和艾滋病相关复合物患者的 HTLV-III 中和抗体
影响因子：
64.8
作者：
M. Robert;Monica Brown;R. Gallo
通讯作者：
R. Gallo
影响因子：
56.9
作者：
LAURENCE, J;SAUNDERS, A;KULKOSKY, J
通讯作者：
KULKOSKY, J