Integrating computer vision and non-linear optimization for automated deformable registration of three-dimensional medical images.

08:00 EDT 16th May 2019 | BioPortfolio

Summary of "Integrating computer vision and non-linear optimization for automated deformable registration of three-dimensional medical images."

Deformable image registration (DIR), the process of estimating and applying non-linear transforms to spatially align sets of two or more images, is a challenging task with many important clinical applications including kinetic analysis, cancer treatment targeting, and evaluation of treatment response. Current techniques use non-linear optimizations only to reach a local minimum and not a globally optimal solution, limiting application to cases with small spatial displacements. Various semi-dense feature-based methods drawing inspiration from mammalian systems as the basis for 2D visual processing have been implemented for automated wide baseline registration and object detection applications with great success. Extension to the 3D case, which has been shown to enable highly efficient coarse global image search, in theory could be adapted also to allow precise semi-dense global optimization. The algorithm described in this paper, dubbed Constrained Robust Affine Feature Transform (CRAFT), incorporates paradigms from various computer-vision techniques to combine aspects of the human visual pathway with proven non-linear optimization methods to automate general deformable registration with unprecedented robustness. This hybrid technique is able to estimate registration confidence and can serve as the basis of machine perception of medical images for machine learning.


Journal Details

This article was published in the following journal.

Name: Physics in medicine and biology
ISSN: 1361-6560


DeepDyve research library

PubMed Articles [8178 Associated PubMed Articles listed on BioPortfolio]

Deformable registration of 3D ultrasound volumes using automatic landmark generation.

US image registration is an important task e.g. in Computer Aided Surgery. Due to tissue deformation occurring between pre-operative and interventional images often deformable registration is necessar...

Quantification of myocardial deformation by deformable registration-based analysis of cine MRI: validation with tagged CMR.

To validate deformable registration algorithms (DRAs) for cine balanced steady-state free precession (bSSFP) assessment of global longitudinal strain (GLS) and global circumferential strain (GCS) usin...

Evaluation of deformable image registration accuracy for CT images of the thorax region.

Evaluate the performance of three commercial deformable image registration (DIR) solutions on computed tomography (CT) image-series of the thorax.

Technical Note: A method for quality assurance of landmark sets for use in evaluation of deformable image registration accuracy of lung parenchyma.

To develop a quality control method to improve the accuracy of corresponding landmark sets used for deformable image registration evaluation in the lung parenchyma.

Simplex-based navigation tool for a posteriori selection of the preferred deformable image registration outcome from a set of trade-off solutions obtained with multiobjective optimization for the case of breast MRI.

Multiobjective optimization approaches for deformable image registration (DIR) remove the need for manual adjustment of key parameters and provide a set of solutions that represent high-quality trade-...

Clinical Trials [3139 Associated Clinical Trials listed on BioPortfolio]

Deformable Registration of Multi-parametric MRI to Intra-operative Transrectal Ultrasound for Prostate Brachytherapy

Objective: To focus the high dose radiation to the gross tumor in the prostate while maintaining adequate dose for control of microscopic disease elsewhere in the prostate. In orde...

DaVinci Registry(Distinctly Assess Vision in Coronary Intervention)

Prospective Internet-Registry, Postmarketing-Surveillance, Registration and Follow-up of patients after Multi-Link VISION™ - Stent Implantation

4D-CT-based Ventilation Imaging for Adaptive Functional Guidance in Radiotherapy

To determine the appropriate class of deformable image registration algorithm and metric best suited for four-dimensional (4D) CT-based ventilation assessment.

Convergence Insufficiency Treatment Trial (CITT)

The purposes of the CITT are: - To determine whether Home-based Pencil Push-up therapy, Home-based Pencil Push-ups with Computer Vision Therapy/Orthoptics or Office-based VT/Ortho...

Prospective Study for Transplant Optimization Using Functional Imaging (TROFI)

The objective of this study is to detect BOS in an early stage by using the outcome parameters generated by Functional Respiratory Imaging (FRI). Robust and automated segmentation algorith...

Medical and Biotech [MESH] Definitions

Vision considered to be inferior to normal vision as represented by accepted standards of acuity, field of vision, or motility. Low vision generally refers to visual disorders that are caused by diseases that cannot be corrected by refraction (e.g., MACULAR DEGENERATION; RETINITIS PIGMENTOSA; DIABETIC RETINOPATHY, etc.).

Computer systems utilized as adjuncts in the treatment of disease.

A technique of operations research for solving certain kinds of problems involving many variables where a best value or set of best values is to be found. It is most likely to be feasible when the quantity to be optimized, sometimes called the objective function, can be stated as a mathematical expression in terms of the various activities within the system, and when this expression is simply proportional to the measure of the activities, i.e., is linear, and when all the restrictions are also linear. It is different from computer programming, although problems using linear programming techniques may be programmed on a computer.

Computer-based representation of physical systems and phenomena such as chemical processes.

Computer systems or programs used in accurate computations for providing radiation dosage treatment to patients.

Quick Search


DeepDyve research library

Relevant Topic

Cancer Disease
Cancer is not just one disease but many diseases. There are more than 100 different types of cancer. Most cancers are named for the organ or type of cell in which they start - for example, cancer that begins in the colon is called colon cancer; cancer th...

Searches Linking to this Article