Artificial T1-Weighted Postcontrast Brain MRI: A Deep Learning Method for Contrast Signal Extraction.

Invest Radiol

From the Clinic of Neuroradiology, University Hospital Bonn, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany (R.H., E.K., Z.B., C.G., D.P., A.R., K.D.); Institute of Applied Mathematics, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany (T.P., A.E.); Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA (D.P.); and German Center for Neurodegenerative Diseases (DZNE), Helmholtz Association of German Research Centers, Bonn, Germany (A.R., K.D.).

Published: February 2025

AI Article Synopsis

  • The study aimed to compare three methods for synthesizing full-dose T1-weighted MRI images to reduce the use of gadolinium-based contrast agents, focusing on safety, cost, and environmental impact.
  • A group of 213 participants underwent MRI scans using both low-dose and full-dose gadolinium, with the performance of the methods evaluated through a reader-based analysis.
  • Results indicated that the proposed method (setting C) outperformed the other two methods (A and B) in terms of interchangeability and lesion enhancement conformity, showing fewer false positives and a lower mean reduction in enhancement compared to true images.

Article Abstract

Objectives: Reducing gadolinium-based contrast agents to lower costs, the environmental impact of gadolinium-containing wastewater, and patient exposure is still an unresolved issue. Published methods have never been compared. The purpose of this study was to compare the performance of 2 reimplemented state-of-the-art deep learning methods (settings A and B) and a proposed method for contrast signal extraction (setting C) to synthesize artificial T1-weighted full-dose images from corresponding noncontrast and low-dose images.

Materials And Methods: In this prospective study, 213 participants received magnetic resonance imaging of the brain between August and October 2021 including low-dose (0.02 mmol/kg) and full-dose images (0.1 mmol/kg). Fifty participants were randomly set aside as test set before training (mean age ± SD, 52.6 ± 15.3 years; 30 men). Artificial and true full-dose images were compared using a reader-based study. Two readers noted all false-positive lesions and scored the overall interchangeability in regard to the clinical conclusion. Using a 5-point Likert scale (0 being the worst), they scored the contrast enhancement of each lesion and its conformity to the respective reference in the true image.

Results: The average counts of false-positives per participant were 0.33 ± 0.93, 0.07 ± 0.33, and 0.05 ± 0.22 for settings A-C, respectively. Setting C showed a significantly higher proportion of scans scored as fully or mostly interchangeable (70/100) than settings A (40/100, P < 0.001) and B (57/100, P < 0.001), and generated the smallest mean enhancement reduction of scored lesions (-0.50 ± 0.55) compared with the true images (setting A: -1.10 ± 0.98; setting B: -0.91 ± 0.67, both P < 0.001). The average scores of conformity of the lesion were 1.75 ± 1.07, 2.19 ± 1.04, and 2.48 ± 0.91 for settings A-C, respectively, with significant differences among all settings (all P < 0.001).

Conclusions: The proposed method for contrast signal extraction showed significant improvements in synthesizing postcontrast images. A relevant proportion of images showing inadequate interchangeability with the reference remains at this dosage.

Download full-text PDF

Source
http://dx.doi.org/10.1097/RLI.0000000000001107DOI Listing

Publication Analysis

Top Keywords

method contrast
12
contrast signal
12
signal extraction
12
full-dose images
12
artificial t1-weighted
8
deep learning
8
proposed method
8
settings a-c
8
images
6
contrast
5

Similar Publications

Background: Objective structured clinical examinations (OSCEs) are a widely recognized and accepted method to assess clinical competencies but are often resource-intensive.

Objective: This study aimed to evaluate the feasibility and effectiveness of a virtual reality (VR)-based station (VRS) compared with a traditional physical station (PHS) in an already established curricular OSCE.

Methods: Fifth-year medical students participated in an OSCE consisting of 10 stations.

View Article and Find Full Text PDF

Objective: Focused ultrasound (FUS)-mediated blood-brain barrier (BBB) opening is safe and potentially beneficial in patients with Alzheimer's disease (AD) for the removal of amyloid-beta (Aβ) plaques. However, the optimal BBB opening intervals and number of treatment sessions for clinical improvement remain undefined. Therefore, the aim of this study was to evaluate the safety and benefits of repeated and more extensive BBB opening alone.

View Article and Find Full Text PDF

Preeclampsia is characterized by insufficient invasion of extravillous trophoblasts and is a consequence of failed adaption of extravillous trophoblasts to changes in the intrauterine environment developing embryo. Specific miRNAs are implicated in the development of preeclampsia (PE). miR-455-5p is present at low levels in PE but its role is not known.

View Article and Find Full Text PDF

Background: Glioblastoma is characterized by neovascularization and diffuse infiltration into the adjacent tissue. T2*-based dynamic susceptibility contrast (DSC) MR perfusion images provide useful measurements of the biomarkers associated with tumor perfusion. This study aimed to distinguish infiltrating tumors from vasogenic edema in glioblastomas using DSC-MR perfusion images.

View Article and Find Full Text PDF

Evaluation of endothelialization of an occluder device with cardiac computed tomography and assessment of the pathological validation.

PLoS One

January 2025

Department of Structural Heart Disease, Cardiovascular Institute and Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Background: Assessing the endothelialization of occlusive devices noninvasively remains a challenge. Cardiac computed tomography angiography (CTA) can be employed to evaluate device endothelialization based on contrast uptake within the occluder.

Objective: This study examined device endothelialization using cardiac CTA and investigated the pathological associations.

View Article and Find Full Text PDF

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!