Detecting left ventricular impaired relaxation in cardiac MRI using moving mesh correspondences

Punithakumar, Kumaradevan; Ayed, Ismail Ben; Afshin, Mariam; Goela, Aashish; Islam, Ali; Li, Shuo; Boulanger, Pierre; Becher, Harald; Noga, Michelle

doi:10.1016/j.cmpb.2015.10.015

Cited by 6 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed algorithm has a number of advantages. First, the method performs a 3D-to-3D registration, as opposed to previous related methods which have only captured 2D motion [45], [47], [48]. This is a significant improvement as 3D-to-3D registration is crucial in capturing the true motion of the heart, as 2D is unable to detect out of plane motion.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…The proposed method implements a 3D-to-3D diffeomorphic registration method, which requires a number of significant changes and improvements from previous work described by [45], [47], [48]. 1) The divergence and curl operations were formulated for use in 3D 2) The Fourier transform based Poisson equation solver was developed for the 3D case 3).…”

Section: Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel 3D-to-3D Diffeomorphic Registration Algorithm With Applications to Left Ventricle Segmentation in MR and Ultrasound Sequences

et al. 2023

View full text Add to dashboard Cite

Left ventricular segmentation is a difficult and time-consuming task performed by clinicians, requiring the use of manual contours. We propose a novel three-dimensional diffeomorphic registration algorithm for endocardial segmentation of the left ventricle in magnetic resonance images and ultrasound temporal sequences. The proposed diffeomorphic registration method computes a voxel-to-voxel correspondence in three-dimensional space and is parameterized by one radial and three curl components to emulate the cardiac deformations. In addition, the proposed method allows for enforcing constraints to control the amount of deformation. The method was evaluated on 521 temporal frames from 20 patients from the Automated Cardiac Diagnosis Challenge magnetic resonance imaging dataset and 213 frames from 10 patients undergoing ultrasound scans from the Mazankowski Alberta Heart Institute. The algorithm was compared against six other registration methods, the Symmetric Normalization algorithm from the Dipy package, two variants of the Demons algorithm from the Insight Toolkit software package, two versions of RealTiTracker, and Elastix. The proposed method yielded overall Dice scores of 98.10 (0.90)% for the MRI dataset and 92.90 (2.42)% for the ultrasound dataset. The robustness of the algorithm is demonstrated by the high performance on multiple imaging modalities and various patient abnormalities.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Proposed Methodsmentioning

confidence: 99%

A Novel 3D-to-3D Diffeomorphic Registration Algorithm With Applications to Left Ventricle Segmentation in MR and Ultrasound Sequences

et al. 2023

View full text Add to dashboard Cite

show abstract

“…First frame segmentation: in this category, the user performs manual segmentation of the images in the irst frame. Segmentation can be propagated to the next frames, creating point-to-point relationships [81] or can be used to deine edge weights in graph-based approaches [6,64,82]. It can also be used in the construction of speciic patient models, such as point dictionaries [83], distributions of radial distances and intensities [70] or pixel classiier training [47].…”

Section: Manual Roi Extractionmentioning

confidence: 99%

“…The framework encompasses characteristics such as image intensities and gradients and uses maximum likelihood estimators to estimate parameters. In [81], non-rigid transformations are used to evolve a DM and point-to-point relationships are created between segmentations of adjacent frames in order to restrict evolution.…”

Section: Deformable Modelsmentioning

confidence: 99%

“…In some approaches, the endocardial contour can be used to initialize the epicardium contour [115]. For processing a cardiac sequence, the segmentation result of a previous frame can be used in the initialization of the DM [44,81,118]. The temporal coherence between adjacent frames can be explored in the energy function, as in methods that use optical low [1,108].…”

Section: Deformable Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Left Ventricle Segmentation in Cardiac MR: A Systematic Mapping of the Past Decade

Ribeiro

Nunes

2022

ACM Comput. Surv.

View full text Add to dashboard Cite

Left ventricle segmentation in short-axis cardiac magnetic resonance images is important to diagnose heart disease. However, the repetitive manual segmentation of these images requires considerable human effort and can decrease diagnostic accuracy. In recent years, several fully and semi-automatic approaches have been proposed, mainly using image-based, atlas, graphs, deformable models, and artificial intelligence methods. This paper presents a systematic mapping on the left ventricle segmentation, considering 74 studies published in the last decade. The main contributions of this review are: definition of the main segmentation challenges in these images; proposal of a new schematization, dividing the segmentation process into stages; categorization and analysis of the segmentation methods, including hybrid combinations; and analysis of the evaluation process, metrics, and databases. The performance of the methods in the most used public database is assessed, and the main limitations, weaknesses, and strengths of each method category are presented. Finally, trends, challenges, and research opportunities are discussed. The analysis indicates that methods from all categories can achieve good performance, and hybrid methods combining deep learning and deformable models obtain the best results. Methods still fail in specific slices, segment wrong regions, and produce anatomically impossible segmentations.

show abstract

Assessment of Cardiovascular Disorders Based on 3D Left Ventricle Model of Cine Cardiac MR Sequence

Muthulakshmi

Kavitha

2019

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

Detecting left ventricular impaired relaxation in cardiac MRI using moving mesh correspondences

Cited by 6 publications

References 28 publications

A Novel 3D-to-3D Diffeomorphic Registration Algorithm With Applications to Left Ventricle Segmentation in MR and Ultrasound Sequences

A Novel 3D-to-3D Diffeomorphic Registration Algorithm With Applications to Left Ventricle Segmentation in MR and Ultrasound Sequences

Left Ventricle Segmentation in Cardiac MR: A Systematic Mapping of the Past Decade

Assessment of Cardiovascular Disorders Based on 3D Left Ventricle Model of Cine Cardiac MR Sequence

Contact Info

Product

Resources

About