A 2D/3D Non-rigid Registration Method for Lung Images Based on a Non-linear Correlation Between Displacement Vectors and Similarity Measures

Zhang, Jiayi; Xia, Wei; Jin, Qingpeng; Gao, Xin

doi:10.1007/s40846-021-00609-z

Cited by 9 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method can be utilized in deformable 2D-3D registration by considering the dynamic and flexible nature of anatomical structures, which is a crucial advancement along with existing techniques 37 – 39 Thus, the use of a particle-based SSIM and its projection methods represents a significant step forward in deformable registration medical imaging, offering improved adaptability in patient-specific bone modeling and kinematics assessments.…”

Section: Discussionmentioning

confidence: 99%

Fast digitally reconstructed radiograph generation using particle-based statistical shape and intensity model

Oh,

Koo

2024

J. Med. Imag.

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Fast digitally reconstructed radiograph generation using particle-based statistical shape and intensity model

Oh,

Koo

2024

J. Med. Imag.

View full text Add to dashboard Cite

“…The advent of deep learning has made it possible to perform tasks previously limited to 3D images using ultra-sparse x-ray images. One approach involves 2D/3D registration (Zhang et al 2021, Dong et al 2023, while another directly reconstructs 3D images from ultra-sparse 2D images. For instance, X2CT-GAN (Ying et al 2019) is an end-to-end CT image generation method that utilizes a 2D convolutional neural network (CNN), a 3D CNN, and generative adversarial networks.…”

Section: Introductionmentioning

confidence: 99%

XTransCT: ultra-fast volumetric CT reconstruction using two orthogonal x-ray projections for image-guided radiation therapy via a transformer network

Zhang,

Liu,

Dai

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective:The aim of this study was to reconstruct Volumetric Computed Tomography (CT) images in real-time from ultra-sparse two-dimensional X-ray projections, facilitating easier navigation and positioning during image-guided radiation therapy.Approach: Our approach leverages a voxel-sapce-searching Transformer model to overcome the limitations of conventional CT reconstruction techniques, which require extensive X-ray projections and lead to high radiation doses and equipment constraints.Main Results: The proposed XTransCT algorithm demonstrated superior performance in terms of image quality, structural accuracy, and generalizability across different datasets, including a hospital set of 50 patients, the large-scale public LIDC-IDRI dataset, and the LNDb dataset for cross-validation. Notably, the algorithm achieved an approximately 300$\%$ improvement in reconstruction speed, with a rate of 44 ms per 3D image reconstruction compared to former 3D convolution-based methods.Significance: The XTransCT architecture has the potential to impact clinical practice by providing high-quality CT images faster and with substantially reduced radiation exposure for patients. The model’s generalizability suggests it has the potential applicable in various healthcare settings.

show abstract

“…Therefore, CPD is more robust in terms of nonlinear deformation and noise. Several time-course studies have adopted CPD to align deformed lung images with shape variation in the trachea and pulmonary vessels [37][38][39][40]. However, conventional CPD applied to the entire thoracic cavity for image registration may not produce satisfactory results due to its inability to align the disparate deformations caused by breathing and to achieve local optimization.…”

Section: Introductionmentioning

confidence: 99%

Longitudinal Registration of Chest CT Images With Radiation-Induced Lung Disease

Lin¹,

Lee²,

Lor³

et al. 2022

Preprint

View full text Add to dashboard Cite

Longitudinal image registration of pulmonary computed tomography (PCT) images may serve as an essential tool for investigating the relationship between radiation dose distribution and the occurrence and phenotype of radiation-induced lung disease (RILD). Although numerous longitudinal registration algorithms have been developed for PCT, most similarity-based approaches are not suitable for PCT involving RILD due to the complex tissue variation between two PCT images. Moreover, conventional feature-based approaches might fail to find a sufficient number of matched pairs of feature points due to the disparate lung deformation caused by breathing and RILD. To overcome the challenges resulting from RILD, component structure coherence point drift (CSCPD) was proposed to establish a deformation model by decomposing the chest into several components and matching them with individual parameters based on coherence point drift (CPD). Moreover, a regional vascular point matching (RVPM) algorithm was proposed to generate a vascular subtree and to substantially increase the number of corresponding pairs between two images. Eventually, the components were recomposed and aligned by a thin plate spline algorithm. A performance assessment on 15 pairs of PCT images of patients with RILD yielded recall and precision values of 0.85 and 0.89 for RVPM, respectively. Moreover, the target registration error of CSCPD with RVPM (2.3 ± 1.79) was significantly better than that of conventional CPD with RVPM (2.95 ± 1.89) and conventional CPD (5.04 ± 2.87). Therefore, the proposed registration system is robust enough to address the disparate deformation of lungs with RILD, and it improves registration accuracy within the parenchyma.

show abstract

A 2D/3D Non-rigid Registration Method for Lung Images Based on a Non-linear Correlation Between Displacement Vectors and Similarity Measures

Cited by 9 publications

References 29 publications

Fast digitally reconstructed radiograph generation using particle-based statistical shape and intensity model

Fast digitally reconstructed radiograph generation using particle-based statistical shape and intensity model

XTransCT: ultra-fast volumetric CT reconstruction using two orthogonal x-ray projections for image-guided radiation therapy via a transformer network

Longitudinal Registration of Chest CT Images With Radiation-Induced Lung Disease

Contact Info

Product

Resources

About