Large-scale investigation of deep learning approaches for ventilated lung segmentation using multi-nuclear hyperpolarized gas MRI.
Large-scale investigation of deep learning approaches for ventilated lung segmentation using multi-nuclear hyperpolarized gas MRI.
复制标题
DOI：
10.1038/s41598-022-14672-2
复制
发表时间：
2022-06-22
影响因子：
4.6
通讯作者：
Tahir, Bilal A.
中科院分区：
文献类型：
--
作者：
Astley, Joshua R.;Biancardi, Alberto M.;Hughes, Paul J. C.;Marshall, Helen;Smith, Laurie J.;Collier, Guilhem J.;Eaden, James A.;Weatherley, Nicholas D.;Hatton, Matthew Q.;Wild, Jim M.;Tahir, Bilal A.
呼吸系统疾病是全世界死亡和发病的主要原因。肺部成像是呼吸系统疾病诊断、治疗计划、监测和治疗评估的重要组成部分。从功能性肺MRI技术中可以了解到许多肺部病变。这些包括超极化气体通气MRI，其能够以高空间分辨率可视化和量化局部肺通气。需要对通气肺进行分割，以计算临床相关的生物标志物。深度学习（DL）的最新研究在许多分割问题上显示出了有希望的结果。在这里，我们评估了几种3D卷积神经网络，以分割超极化气体MRI扫描的通气肺区域。该数据集由759个氦-3（3 He）或氙-129（129 Xe）体积扫描和来自341名健康受试者和具有各种病理的患者的相应专家分割组成。我们通过重叠，距离和误差指标评估了几种DL实验方法的分割性能，并将其与传统的分割方法，即空间模糊c-均值（SFCM）和K-均值聚类进行了比较。我们观察到，使用3D nn-UNet进行的3 He和129 He MRI扫描联合训练优于其他DL方法，平均± SD Dice系数为0.963 ± 0.018，平均边界Hausdorff距离为1.505 ± 0.969 mm，Hausdorff第95百分位数为5.754 ± 6.621 mm，相对误差为0.075 ± 0.039。此外，在测试集中观察到129 He和3 He扫描之间的性能差异有限。129 He和3 He的联合训练比传统方法产生了统计学上显著的改善（p < 0.0001）。此外，我们观察到DL和专家分割之间非常强的相关性和一致性，Pearson相关性为0.99（p < 0.0001），Bland-Altman偏倚为-0.8%。评价的DL方法提供了通气肺区域的准确、稳健和快速分割，并成功排除了非肺区域，如气道和伪影。预计这种方法将消除或大大减少随后耗时的手工编辑。
Respiratory diseases are leading causes of mortality and morbidity worldwide. Pulmonary imaging is an essential component of the diagnosis, treatment planning, monitoring, and treatment assessment of respiratory diseases. Insights into numerous pulmonary pathologies can be gleaned from functional lung MRI techniques. These include hyperpolarized gas ventilation MRI, which enables visualization and quantification of regional lung ventilation with high spatial resolution. Segmentation of the ventilated lung is required to calculate clinically relevant biomarkers. Recent research in deep learning (DL) has shown promising results for numerous segmentation problems. Here, we evaluate several 3D convolutional neural networks to segment ventilated lung regions on hyperpolarized gas MRI scans. The dataset consists of 759 helium-3 (3He) or xenon-129 (129Xe) volumetric scans and corresponding expert segmentations from 341 healthy subjects and patients with a wide range of pathologies. We evaluated segmentation performance for several DL experimental methods via overlap, distance and error metrics and compared them to conventional segmentation methods, namely, spatial fuzzy c-means (SFCM) and K-means clustering. We observed that training on combined 3He and 129Xe MRI scans using a 3D nn-UNet outperformed other DL methods, achieving a mean ± SD Dice coefficient of 0.963 ± 0.018, average boundary Hausdorff distance of 1.505 ± 0.969 mm, Hausdorff 95th percentile of 5.754 ± 6.621 mm and relative error of 0.075 ± 0.039. Moreover, limited differences in performance were observed between 129Xe and 3He scans in the testing set. Combined training on 129Xe and 3He yielded statistically significant improvements over the conventional methods (p < 0.0001). In addition, we observed very strong correlation and agreement between DL and expert segmentations, with Pearson correlation of 0.99 (p < 0.0001) and Bland–Altman bias of − 0.8%. The DL approach evaluated provides accurate, robust and rapid segmentations of ventilated lung regions and successfully excludes non-lung regions such as the airways and artefacts. This approach is expected to eliminate the need for, or significantly reduce, subsequent time-consuming manual editing.
登录
查看更多内容
影响因子：
4.4
作者：
Hughes, Paul J. C.;Horn, Felix C.;Wild, Jim M.
通讯作者：
Wild, Jim M.
NiftyNet：医学成像深度学习平台。
影响因子：
6.1
作者：
Gibson E;Li W;Sudre C;Fidon L;Shakir DI;Wang G;Eaton-Rosen Z;Gray R;Doel T;Hu Y;Whyntie T;Nachev P;Modat M;Barratt DC;Ourselin S;Cardoso MJ;Vercauteren T
通讯作者：
Vercauteren T
影响因子：
4.8
作者：
DICE, LR
通讯作者：
DICE, LR
影响因子：
2.6
作者：
Mukesh, M.;Benson, R.;Jefferies, S.
通讯作者：
Jefferies, S.
影响因子：
19.7
作者：
Kirby, Miranda;Svenningsen, Sarah;Parraga, Grace
通讯作者：
Parraga, Grace