当前位置: X-MOL 学术Comput. Methods Programs Biomed. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
3D deformable registration of longitudinal abdominopelvic CT images using unsupervised deep learning
Computer Methods and Programs in Biomedicine ( IF 6.1 ) Pub Date : 2021-07-08 , DOI: 10.1016/j.cmpb.2021.106261
Maureen van Eijnatten 1 , Leonardo Rundo 2 , K Joost Batenburg 3 , Felix Lucka 4 , Emma Beddowes 5 , Carlos Caldas 5 , Ferdia A Gallagher 2 , Evis Sala 2 , Carola-Bibiane Schönlieb 6 , Ramona Woitek 7
Affiliation  

Background and Objectives: Deep learning is being increasingly used for deformable image registration and unsupervised approaches, in particular, have shown great potential. However, the registration of abdominopelvic Computed Tomography (CT) images remains challenging due to the larger displacements compared to those in brain or prostate Magnetic Resonance Imaging datasets that are typically considered as benchmarks. In this study, we investigate the use of the commonly used unsupervised deep learning framework VoxelMorph for the registration of a longitudinal abdominopelvic CT dataset acquired in patients with bone metastases from breast cancer.

Methods: As a pre-processing step, the abdominopelvic CT images were refined by automatically removing the CT table and all other extra-corporeal components. To improve the learning capabilities of the VoxelMorph framework when only a limited amount of training data is available, a novel incremental training strategy is proposed based on simulated deformations of consecutive CT images in the longitudinal dataset. This devised training strategy was compared against training on simulated deformations of a single CT volume. A widely used software toolbox for deformable image registration called NiftyReg was used as a benchmark. The evaluations were performed by calculating the Dice Similarity Coefficient (DSC) between manual vertebrae segmentations and the Structural Similarity Index (SSIM).

Results: The CT table removal procedure allowed both VoxelMorph and NiftyReg to achieve significantly better registration performance. In a 4-fold cross-validation scheme, the incremental training strategy resulted in better registration performance compared to training on a single volume, with a mean DSC of 0.929±0.037 and 0.883±0.033, and a mean SSIM of 0.984±0.009 and 0.969±0.007, respectively. Although our deformable image registration method did not outperform NiftyReg in terms of DSC (0.988±0.003) or SSIM (0.995±0.002), the registrations were approximately 300 times faster.

Conclusions: This study showed the feasibility of deep learning based deformable registration of longitudinal abdominopelvic CT images via a novel incremental training strategy based on simulated deformations.



中文翻译:

使用无监督深度学习对纵向腹盆腔 CT 图像进行 3D 可变形配准

背景和目标:深度学习越来越多地用于可变形图像配准,尤其是无监督方法已显示出巨大的潜力。然而,与通常被视为基准的大脑或前列腺磁共振成像数据集中的位移相比,腹盆腔计算机断层扫描 (CT) 图像的配准仍然具有挑战性。在这项研究中,我们研究了常用的无监督深度学习框架 VoxelMorph 在乳腺癌骨转移患者中获得的纵向腹盆腔 CT 数据集的配准。

方法:作为预处理步骤,腹盆腔 CT 图像通过自动删除 CT 表和所有其他体外成分进行细化。为了在只有有限数量的训练数据可用时提高 VoxelMorph 框架的学习能力,提出了一种基于纵向数据集中连续 CT 图像模拟变形的新型增量训练策略。将此设计的训练策略与单个 CT 体积的模拟变形训练进行比较。一个广泛使用的用于可变形图像配准的软件工具箱称为 NiftyReg 被用作基准。通过计算手动椎骨分割和结构相似指数 (SSIM) 之间的骰子相似系数 (DSC) 来进行评估。

结果:CT 表移除程序允许 VoxelMorph 和 NiftyReg 实现显着更好的配准性能。在 4 倍交叉验证方案中,增量训练策略与单卷训练相比产生了更好的注册性能,平均 DSC 为0.929±0.0370.883±0.033,以及平均 SSIM 为 0.984±0.0090.969±0.007, 分别。尽管我们的可变形图像配准方法在 DSC 方面没有优于 NiftyReg(0.988±0.003) 或 SSIM (0.995±0.002),注册速度大约快了 300 倍。

结论:本研究表明,通过基于模拟变形的新型增量训练策略,基于深度学习的纵向腹盆腔 CT 图像可变形配准的可行性。

更新日期:2021-07-19
down
wechat
bug