Related Experiment Video
Updated: Jan 1, 2026
07:13
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
Published on: October 27, 2023
1.6K
Multimodality image registration in the head-and-neck using a deep learning-derived synthetic CT as a bridge
Elizabeth M McKenzie1, Anand Santhanam1, Dan Ruan1
1Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, 90024, USA.
Medical Physics
|December 20, 2019
Summary
Deep learning-based synthetic CT generation improves head-and-neck image registration accuracy. This novel technique enhances alignment between MRI and CT scans, outperforming direct multimodal registration for clinical applications.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Radiology
Background:
- Accurate image registration is crucial for head-and-neck cancer treatment planning and delivery.
- Multimodal image registration (e.g., MRI to CT) faces challenges due to inherent differences between imaging modalities.
- Deep learning offers potential solutions for synthesizing medical images and improving registration accuracy.
Purpose of the Study:
- To develop and validate a novel head-and-neck multimodality image registration technique.
- To utilize deep-learning-based cross-modality synthesis for generating synthetic CT (sCT) images from MR images.
- To demonstrate the efficacy of using sCT in image registration compared to direct multimodal registration.
Main Methods:
- A neural network was trained using fivefold cross-validation on 25 head-and-neck patients' paired MR and CT scans to synthesize CT from MR.
- Deformable registration algorithms (B-splines, mutual information) were applied using both direct MR-CT and synthetic CT-based approaches.
- Registration accuracy was evaluated using 95% Hausdorff distance, landmark error, inverse consistency, and Jacobian determinant analysis.
Main Results:
- The deep learning-based synthetic CT approach significantly reduced average landmark error in both MR-to-CT (9.8±3.1 mm to 6.0±2.1 mm) and CT-to-MR (10.0±4.3 mm to 6.6±2.0 mm) registrations.
- Improved spinal cord alignment was observed when registering CT to MRI-derived synthetic CT, especially with initial rigid misalignment.
- The method demonstrated superior inverse consistency and a high average Jacobian determinant (0.98), indicating accurate and non-degenerate deformations.
Conclusions:
- Using a deep learning-derived synthetic CT in place of actual MR or CT data enhances deformable registration performance.
- The proposed technique offers a superior alternative to direct multimodal registration for head-and-neck imaging.
- This approach holds promise for improving the accuracy and reliability of image-guided radiotherapy and other clinical applications.
Related Concept Videos
01:14Imaging Studies I: CT and MRI
726
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
726
01:27Imaging Studies III: Computed Tomography
233
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
233