We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us

Download Mobile App




Accelerated MRI Sequence Helps Radiologists Assess Heart Disease without Breath-Holding

By MedImaging International staff writers
Posted on 14 Feb 2024
Image: MRI examinations require patients to repeatedly perform breath holds to avoid respiratory artifacts (Photo courtesy of 123RF)
Image: MRI examinations require patients to repeatedly perform breath holds to avoid respiratory artifacts (Photo courtesy of 123RF)

Cardiac magnetic resonance imaging (MRI) is essential for evaluating and diagnosing heart damage resulting from poor blood flow. Traditional cardiac MRI examinations are time-consuming and typically require patients to perform multiple breath holds to prevent respiratory artifacts. This can be challenging, especially for patients with ischemic heart disease, and may lead to compromised image quality and potential measurement inaccuracies. Now, an accelerated MRI sequence can help radiologists assess ischemic heart disease without requiring patients to hold their breath.

Scientists at Amiens University Hospital (Amiens, France) conducted a prospective study involving patients undergoing cardiac MRI for ischemic heart disease assessment between March and June 2023. The study included an innovative, free-breathing, short-axis imaging sequence that utilized deep learning for image reconstruction. Two radiologists evaluated the image quality of both the traditional and the new MRI methods. The study involved a total of 26 patients.

The results showed that the acquisition time was shorter with the deep learning-based method compared to the standard sequence. Furthermore, this accelerated approach demonstrated no significant difference in assessing the left ventricular ejection fraction, an important measure of heart function. The radiologists observed that the subjective image quality of the deep learning-based images was superior. However, they also noted an increased frequency of blurring artifacts in these images.

“The improved subjective image quality of the cine-deep learning sequence likely in part relates to the sequence’s respiratory synchronization, in comparison with the standard sequence’s reliance on adequate breath-holding, which may be challenging in dyspneic patients,” concluded David Monteuuis, MD, at Amiens University Hospital.

Related Links:
Amiens University Hospital

Half Apron
Demi
Breast Localization System
MAMMOREP LOOP
Mammo DR Retrofit Solution
DR Retrofit Mammography
Medical Radiographic X-Ray Machine
TR30N HF

Channels

Imaging IT

view channel
Image: Researchers develop a vision-language model trained on large-scale data to generate clinically relevant findings from chest computed tomography images through visual question answering (Ms. Maiko Nagao from Meijo University, Japan)

Interactive AI Tool Supports Explainable Lung Nodule Assessment

Lung cancer is a leading cause of cancer mortality, and timely characterization of pulmonary nodules on chest computed tomography (CT) is essential for directing care. Interpreting nodule morphology demands... Read more
Copyright © 2000-2026 Globetech Media. All rights reserved.