3D-QCNet - A pipeline for automated artifact detection in diffusion MRI images.

3D-QCNet - A pipeline for automated artifact detection in diffusion MRI images.
复制标题

DOI:
10.1016/j.compmedimag.2022.102151
复制
发表时间:
2023-01
期刊:
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
影响因子:
--
通讯作者:
--
中科院分区:
其他
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

伪影是扩散磁共振成像(DMRI)扫描中常见的一种现象。识别和删除它们对于确保对这些扫描执行的任何后处理的准确性和可行性至关重要。这使得质量控制(QC)成为分析dMRI数据之前的关键第一步。存在几种用于人工制品检测的QC方法,但是它们存在诸如需要人工干预以及无法在不同的人工制品和数据集上进行推广等问题。在本文中,我们提出了一种自动深度学习(DL)管道,它利用3D-Densenet体系结构来训练扩散体积模型,以用于自动伪影检测。我们的方法在来自7个大型临床数据集的9000个数据集上得到了验证,这些数据集来自多台扫描仪的不同采集协议(具有不同的梯度方向、高和低b值、单壳和多壳采集)。此外,它们代表了不同的受试者人口统计学,包括年龄、性别和是否有病理改变。我们的QC方法通过在我们的测试集中平均正确检测92%的人工产物,被发现能够准确地概括这些异质数据。这种在不同数据集上的一致性能强调了我们方法的普适性,这是目前阻碍自动化QC技术广泛采用的一个重要障碍。因此,3D-QCNet可以集成到扩散管道中,有效地自动化艰巨而耗时的伪像检测过程。
Artifacts are a common occurrence in Diffusion MRI (dMRI) scans. Identifying and removing them is essential to ensure the accuracy and viability of any post-processing carried out on these scans. This makes quality control (QC) a crucial first step prior to any analysis of dMRI data. Several QC methods for artifact detection exist, however they suffer from problems like requiring manual intervention and the inability to generalize across different artifacts and datasets. In this paper, we propose an automated deep learning (DL) pipeline that utilizes a 3D-Densenet architecture to train a model on diffusion volumes for automatic artifact detection. Our method is validated on 9000 volumes sourced from 7 large clinical datasets spanning different acquisition protocols (with different gradient directions, high and low b-values, single-shell and multi-shell acquisitions) from multiple scanners. Additionally, they represent diverse subject demographics including age, sex and the presence or absence of pathologies. Our QC method is found to accurately generalize across this heterogenous data by correctly detecting 92% artifacts on average across our test set. This consistent performance over diverse datasets underlines the generalizability of our method, which currently is a significant barrier hindering the widespread adoption of automated QC techniques. Thus, 3D-QCNet can be integrated into diffusion pipelines to effectively automate the arduous and time-intensive process of artifact detection.
DOI: 10.1016/j.neuroimage.2018.09.073
发表时间: 2019-01-01
期刊: NeuroImage
影响因子: 5.7
作者:
Bastiani M;Cottaar M;Fitzgibbon SP;Suri S;Alfaro-Almagro F;Sotiropoulos SN;Jbabdi S;Andersson JLR
通讯作者: Andersson JLR
DOI: 10.4329/wjr.v8.i9.785
发表时间: 2016-09-28
影响因子: 2.5
作者:
Baliyan V;Das CJ;Sharma R;Gupta AK
通讯作者: Gupta AK
DOI: 10.1016/j.neuroimage.2014.12.006
发表时间: 2015-02-15
期刊: NeuroImage
影响因子: 5.7
作者:
Reuter M;Tisdall MD;Qureshi A;Buckner RL;van der Kouwe AJW;Fischl B
通讯作者: Fischl B
DOI: 10.3389/fnins.2019.01456
发表时间: 2020-01-22
影响因子: 4.3
作者:
Samani, Zahra Riahi;Alappatt, Jacob Antony;Verma, Ragini
通讯作者: Verma, Ragini
DOI: 10.1016/j.neuroimage.2018.05.077
发表时间: 2018-09-01
期刊: NEUROIMAGE
影响因子: 5.7
作者:
Graham, Mark S.;Drobnjak, Ivana;Zhang, Hui
通讯作者: Zhang, Hui