Lung Respiratory Motion Estimation Based on Fast Kalman Filtering and 4D CT Image Registration

Xue, Peng; Fu, Yu; Ji, Huizhong; Cui, Wentao; Dong, Enqing

doi:10.1109/jbhi.2020.3030071

Cited by 10 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For dynamic motion estimation of continuous phases, in 2020, P. Xue et al [ 104 ] proposed a lung respiratory motion estimation method (LRME-4DCT) based on fast Kalman filtering and 4DCT image registration. Each phase was registered using isoPTV and HOMRF registration methods, and the registration results were used as the observation and prediction vectors of the constructed motion estimation model, respectively.…”

Section: Resultsmentioning

confidence: 99%

Current Research Status of Respiratory Motion for Thorax and Abdominal Treatment: A Systematic Review

Wu,

Wang,

Chu

et al. 2024

Biomimetics

View full text Add to dashboard Cite

Malignant tumors have become one of the serious public health problems in human safety and health, among which the chest and abdomen diseases account for the largest proportion. Early diagnosis and treatment can effectively improve the survival rate of patients. However, respiratory motion in the chest and abdomen can lead to uncertainty in the shape, volume, and location of the tumor, making treatment of the chest and abdomen difficult. Therefore, compensation for respiratory motion is very important in clinical treatment. The purpose of this review was to discuss the research and development of respiratory movement monitoring and prediction in thoracic and abdominal surgery, as well as introduce the current research status. The integration of modern respiratory motion compensation technology with advanced sensor detection technology, medical-image-guided therapy, and artificial intelligence technology is discussed and analyzed. The future research direction of intraoperative thoracic and abdominal respiratory motion compensation should be non-invasive, non-contact, use a low dose, and involve intelligent development. The complexity of the surgical environment, the constraints on the accuracy of existing image guidance devices, and the latency of data transmission are all present technical challenges.

show abstract

Section: Resultsmentioning

confidence: 99%

Current Research Status of Respiratory Motion for Thorax and Abdominal Treatment: A Systematic Review

Wu,

Wang,

Chu

et al. 2024

Biomimetics

View full text Add to dashboard Cite

show abstract

“…Even though the PCA movement model described by [11] appears promising based on the findings of a limited group of patients, more research is needed to determine why it operates and whether there is a deeper relationship between the 2 pulmonary movement models than their surface mathematical similarities. Low's 5D pulmonary movement model is a physiological concept that is based on pulmonary architecture and movement dynamics [12]. The PCA movement model, on either side, is more mathematically flavored and is based on a multivariate statistical technique.…”

Section: Methodsmentioning

confidence: 99%

Biomedical image restoration using machine learning GPU acceleration approach for precision improvement

Hazela

Aarti

Khandelwal

et al. 2022

ijhs

View full text Add to dashboard Cite

Focusing the image in a single x-ray projection, an algorithm proposed for actual time volumetric image rebuilt and 3-dimensional location of the lump. Using the Principal Component Analysis (PCA) initialize the parameterized Deformation Vector Fields (DVF) of pulmonary movement. By adjusting the PCA coefficients, applied the DVF applied to optimize the reference image so that, the simulated projection of the rebuilt image matches the observed projection. The digital phantom & patient information was used to evaluate the technique. The phantom has an average relative image rebuilt error of 7.5 percent and a 3-dimensional location of the lump inaccuracy of 0.9 mm, correspondingly. The patient's location of the lump inaccuracy is less than 2 mm. On a GPU NVIDIA C1060, recreating a single volumetric image from every projection takes about 0.2 & 0.3 secs for patient and phantom. From a single image, clinical relevance could lead to reliable 3-dimensional lump tracking.

show abstract

“…GPU-accelerated lung DIR has been implemented in [12,13,18,19,23,26,30], achieving computational acceleration compared to the CPU implementation while maintaining similar levels of registration accuracy. For example, in [30], the authors accomplished an impressive runtime of around 6 seconds, setting a record as the fastest completion time within the Case 1 to Case 4 DIR-Lab dataset. In particular, a GPU implementation of the Demons algorithm is detailed in [13,23], showcasing substantial acceleration compared to its CPU implementation.…”

Section: Single Gpu Implementationmentioning

confidence: 99%

“…This limits medical applications that are highly time-constrained, such as image-guided adaptive radiation therapy, where images must be continuously registered while the patient is breathing. Several studies have proposed DIR methods to achieve a speedup by utilizing different accelerators such as graphics processing units (GPUs) [3,12,13,18,19,23,26,30]. A few authors have also proposed a multi-GPU-based DIR framework to accelerate the registration time [2].…”

mentioning

confidence: 99%

CLAIRE-ROP: Rapid Partitioning-based Deformable Image Registration on Multi-GPU Accelerator

Kiani,

Jäkel,

Fröning

2023

Preprint

View full text Add to dashboard Cite

<p>Deformable image registration (DIR) is an important tool for clinical applications, especially in medical imaging and radiotherapy, as it ensures accurate image alignment and analysis. Given the high computational demands, acceleration of DIR is essential to ensure efficient and timely medical procedures. The use of a multi-GPU implementation holds the potential for significant DIR acceleration. However, the challenges posed by high communication times and increasing complexity have made using multi-GPU configurations impractical in the clinical setting. In this paper, we propose a novel solution, called CLAIRE-ROP (Rapid Overlapped Partitioning-based) to address these challenges to develop an efficient multi-GPU implementation. Our approach incorporates an efficient partitioning scheme that divides lung images into multiple partitions and allows individual registration for each partition without compromising accuracy. Our method successfully registers images from the largest openly available lung dataset in less than 0.5 seconds with a Dice score of 0.991. </p>

show abstract

Lung Respiratory Motion Estimation Based on Fast Kalman Filtering and 4D CT Image Registration

Cited by 10 publications

References 37 publications

Current Research Status of Respiratory Motion for Thorax and Abdominal Treatment: A Systematic Review

Current Research Status of Respiratory Motion for Thorax and Abdominal Treatment: A Systematic Review

Biomedical image restoration using machine learning GPU acceleration approach for precision improvement

CLAIRE-ROP: Rapid Partitioning-based Deformable Image Registration on Multi-GPU Accelerator

Contact Info

Product

Resources

About