Background: Contrast-enhanced magnetic resonance angiography (MRA) is used to assess various cardiovascular conditions. However, gadolinium-based contrast agents (GBCAs) carry a risk of dose-related adverse effects.
Purpose: To develop a deep learning method to reduce GBCA dose by 80%.
Study Type: Retrospective and prospective.
Population: A total of 1157 retrospective and 40 prospective congenital heart disease patients for training/validation and testing, respectively.
Field Strength/sequence: A 1.5 T, T1-weighted three-dimensional (3D) gradient echo.
Assessment: A neural network was trained to enhance low-dose (LD) 3D MRA using retrospective synthetic data and tested with prospective LD data. Image quality for LD (LD-MRA), enhanced LD (ELD-MRA), and high-dose (HD-MRA) was assessed in terms of signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and a quantitative measure of edge sharpness and scored for perceptual sharpness and contrast on a 1-5 scale. Diagnostic confidence was assessed on a 1-3 scale. LD- and ELD-MRA were assessed against HD-MRA for sensitivity/specificity and agreement of vessel diameter measurements (aorta and pulmonary arteries).
Statistical Tests: SNR, CNR, edge sharpness, and vessel diameters were compared between LD-, ELD-, and HD-MRA using one-way repeated measures analysis of variance with post-hoc t-tests. Perceptual quality and diagnostic confidence were compared using Friedman's test with post-hoc Wilcoxon signed-rank tests. Sensitivity/specificity was compared using McNemar's test. Agreement of vessel diameters was assessed using Bland-Altman analysis.
Results: SNR, CNR, edge sharpness, perceptual sharpness, and perceptual contrast were lower (P < 0.05) for LD-MRA compared to ELD-MRA and HD-MRA. SNR, CNR, edge sharpness, and perceptual contrast were comparable between ELD and HD-MRA, but perceptual sharpness was significantly lower. Sensitivity/specificity was 0.824/0.921 for LD-MRA and 0.882/0.960 for ELD-MRA. Diagnostic confidence was 2.72, 2.85, and 2.92 for LD, ELD, and HD-MRA, respectively (P , P < 0.05). Vessel diameter measurements were comparable, with biases of 0.238 (LD-MRA) and 0.278 mm (ELD-MRA).
Data Conclusion: Deep learning can improve contrast in LD cardiovascular MRA.
Level Of Evidence Level: 2 TECHNICAL EFFICACY: Stage 2.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9681557 | PMC |
| http://dx.doi.org/10.1002/jmri.27573 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A method for comparing MRI sequences of the knee for segmentation based on morphological features.
PLoS One
December 2024
Department of Materials and Production, Aalborg University, Aalborg, Denmark.
Background: In magnetic resonance imaging (MRI) segmentation research, the choice of sequence influences the segmentation accuracy. This study introduces a method to compare sequences. By aligning sequences with specific segmentation objectives, we provide an example of a comparative analysis of various sequences for knee images.
View Article and Find Full Text PDFAnalysis of cutting forces and microdamage during indentation cutting of bone.
J Mech Behav Biomed Mater
December 2024
Department of Mechanical, Manufacturing and Biomedical Engineering, School of Engineering, Trinity College Dublin, Dublin 2, Ireland; Trinity Centre for Biomedical Engineering, Trinity Biomedical Sciences Institute, Trinity College Dublin, D02 R590, Dublin, Ireland; Advanced Materials and Bioengineering Research Centre (AMBER), Royal College of Surgeons in Ireland and Trinity College Dublin, Dublin 2, Ireland.
Article Synopsis
- In surgery, wedge-shaped blades are used to cut bone, but there's little research on how blade shape affects cutting forces and resultant microdamage.
- The study tested compact bovine bone with various wedge blade geometries, identifying significant relationships between blade angle, edge radius, orientation, cutting force, and microdamage.
- Results indicated a direct correlation between the cutting force and the level of microdamage, enhancing our understanding of the biomechanics involved in surgical bone cutting.
Deep learning reconstruction for accelerated high-resolution upper abdominal MRI improves lesion detection without time penalty.
Diagn Interv Imaging
November 2024
Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, 72076 Tuebingen, Germany. Electronic address:
Article Synopsis
- The study aimed to compare two MRI techniques: conventional T1-weighted VIBE and a high-resolution (HR-VIBE) version, focusing on image quality and lesion detection in upper abdominal imaging.
- Conducted at a tertiary center between December 2023 and March 2024, 50 patients underwent both MRI sequences, and various aspects of the images were evaluated by three blinded readers.
- Results revealed that HR-VIBE provided better image clarity and detection rates for lesions (97.5% vs. 93.2%) while maintaining a similar acquisition time, highlighting its potential advantages over the conventional method.
Evaluation of SR-DLR in low-dose abdominal CT: superior image quality and noise reduction.
Abdom Radiol (NY)
November 2024
Iwate Medical University School of Medicine, Shiwa-gun, Japan.
Objectives: To evaluate the effectiveness of super-resolution deep learning reconstruction (SR-DLR) in low-dose abdominal computed tomography (CT) imaging compared with hybrid iterative reconstruction (HIR) and conventional deep learning reconstruction (cDLR) algorithms.
Methods: We retrospectively analyzed abdominal CT scans performed using a low-dose protocol. Three different image reconstruction algorithms-HIR, cDLR, and SR-DLR-were applied to the same raw image data.
MMD-Net: Image domain multi-material decomposition network for dual-energy CT imaging.
Med Phys
November 2024
Research Center for Advanced Detection Materials and Medical Imaging Devices, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China.
Background: Multi-material decomposition is an interesting topic in dual-energy CT (DECT) imaging; however, the accuracy and performance may be limited using the conventional algorithms.
Purpose: In this work, a novel multi-material decomposition network (MMD-Net) is proposed to improve the multi-material decomposition performance of DECT imaging.
Methods: To achieve dual-energy multi-material decomposition, a deep neural network, named as MMD-Net, is proposed in this work.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!