A GPU-Accelerated Deformable Image Registration Algorithm With Applications to Right Ventricular Segmentation

Punithakumar, Kumaradevan; Boulanger, Pierre; Noga, Michelle

doi:10.1109/access.2017.2755863

Cited by 46 publications

(43 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Later on, with the development of medical imaging technology, intensive and specific efforts have been made to segment various types of medical images. e existent medical image segmentation algorithms can be classified as threshold-based methods [2], region-based methods [9][10][11], edge-based methods [12], active-contour-model-based methods [13][14][15][16][17][18][19][20][21][22], hybrid methods [23][24][25][26], and others [27][28][29][30][31][32].…”

Section: Segmentation Of Femur and Patella Regionsmentioning

confidence: 99%

Automatic Segmentation and Measurement on Knee Computerized Tomography Images for Patellar Dislocation Diagnosis

Sun

Kong

Huang

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Traditionally, for diagnosing patellar dislocation, clinicians make manual geometric measurements on computerized tomography (CT) images taken in the knee area, which is often complex and error-prone. erefore, we develop a prototype CAD system for automatic measurement and diagnosis. We firstly segment the patella and the femur regions on the CT images and then measure two geometric quantities, patellar tilt angle (PTA), and patellar lateral shift (PLS) automatically on the segmentation results, which are finally used to assist in diagnoses. e proposed quantities are proved valid and the proposed algorithms are proved effective by experiments.

show abstract

Section: Segmentation Of Femur and Patella Regionsmentioning

confidence: 99%

Automatic Segmentation and Measurement on Knee Computerized Tomography Images for Patellar Dislocation Diagnosis

Sun

Kong

Huang

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…However, this random initialisation scheme may produce numerous outliers in the initial patch matching field. In order to gain a robust initial patch matching result, we compute the similarity transformation T I 1 → I 2 between the consecutive frames I 1 assuming that transformations of various patches are the same in a small region. We then initialise the dense patching matching field via the following minimisation equation [8]:…”

Section: Similarity Transformation-based Patch Matchingmentioning

confidence: 99%

“…Nowadays, the optical flow estimation technology has been applied to many high-level vision tasks, e.g. 3D reconstruction [1], object segmentation and tracking [2], autonomous navigation [3], facial expression recognition [4], posture estimation [5] and video content analysis [6].…”

Section: Introductionmentioning

confidence: 99%

STDC‐Flow: large displacement flow field estimation using similarity transformation‐based dense correspondence

Zhang

Chen

Xiong

et al. 2020

IET Computer Vision

View full text Add to dashboard Cite

In order to improve the accuracy and robustness of optical flow computation under large displacements and motion occlusions, the authors present in this study a large displacement flow field estimation approach using similarity transformation‐based dense correspondence, named STDC‐Flow approach. First, the authors compute an initial nearest‐neighbour field by using the STDC‐Flow of the consecutive two frames, and then extract the consistent regions as the robust nearest‐neighbour field and label the inconsistent regions as the occlusion areas. Second, they improve a non‐local total variation with the L1 norm optical flow model by using the occlusion information to modify the weighted median filtering optimisation. Third, they fuse the robust nearest‐neighbour field and the computed flow field of the improved variational optical flow model to construct the final flow field by using the quadratic pseudo‐boolean optimisation fusion algorithm. Finally, the authors compare the proposed STDC‐Flow method with several state‐of‐the‐art approaches including the variational and deep learning‐based optical flow models by using the MPI‐Sintel and KITTI evaluation databases. The comparison results demonstrate that the proposed STDC‐Flow method has a high accuracy for flow field computation, especially the capacity of dealing with large displacements and motion occlusions.

show abstract

“…The natural feature-based tracking registration technology uses the natural features in the real world to extract the reference points [100]. Therefore, one of the basic and key technologies of the registration method is the extraction of natural features [111]- [113]. The feature points are some pixels in the real world with special appearance and representative shapes, generally satisfying the following conditions: 1) easy-to-definition spatial position coordinates; 2) vivid image nodes around them to simplify the processing steps of machine vision; 3) ensure certain stability for local and global disturbances in the image range.…”

Section: B: Natural Feature Registrationmentioning

confidence: 99%

Registration Technology of Augmented Reality in Oral Medicine: A Review

et al. 2019

View full text Add to dashboard Cite

Augmented reality (AR) technology, as a computer simulation technology, combines various technologies such as virtual reality, computer vision, computer network, and human-computer interaction. AR has been widely used in medicine. The introduction of AR can effectively help the doctors to complete preoperative planning, intraoperative guidance, postoperative evaluation, and medical training. Oral medicine is a major branch of modern medicine. AR can enhance the doctor's visual system, making the internal structure of the oral clearer and effectively reducing the difficulty of oral repair/surgery. Real-time tracking, registration, display, and interactive technologies for AR will play an important role in oral medicine. Among them, registration technology has become an important indicator for evaluating the AR system, and it is also the main bottleneck restricting the stability and applicability of the current AR system. Therefore, we reviewed the registration technology of AR in oral medicine. First, we conducted a hot spot analysis of AR keywords based on Citespace. And then, the registration technology is divided into static registration and real-time registration according to the actual clinical application, among which static registration is divided into rigid registration and non-rigid registration. We discussed problems and limitations of static registration and real-time registration in oral applications at this stage. Finally, the future direction of AR registration technology in oral medicine is proposed.

show abstract

A GPU-Accelerated Deformable Image Registration Algorithm With Applications to Right Ventricular Segmentation

Cited by 46 publications

References 31 publications

Automatic Segmentation and Measurement on Knee Computerized Tomography Images for Patellar Dislocation Diagnosis

Automatic Segmentation and Measurement on Knee Computerized Tomography Images for Patellar Dislocation Diagnosis

STDC‐Flow: large displacement flow field estimation using similarity transformation‐based dense correspondence

Registration Technology of Augmented Reality in Oral Medicine: A Review

Contact Info

Product

Resources

About