Publications by authors named "Robert Terzis"
Purpose: To evaluate a novel flow-independent sequence (Relaxation-Enhanced Angiography without Contrast and Triggering (REACT)) for imaging of the extracranial arteries in acute ischemic stroke (AIS) at 1.5 T.
Methods: This retrospective single-center study included 47 AIS patients who received REACT (scan time: 3:01 min) and contrast-enhanced MRA (CE-MRA) of the extracranial arteries at 1.
Article Synopsis
- Some medical scans called MRA take too long, so a new method called REACT was tested for quick images of blood vessels in stroke patients.
- The study involved 76 stroke patients, and both REACT and another method (CE-MRA) were used to check for blockages in a main artery in the neck.
- REACT showed very good results, finding 88.5% of serious blockages accurately and matching well with CE-MRA in how doctors rated the scans and their quality.
Purpose: To investigate the potential of combining Compressed Sensing (CS) and a newly developed AI-based super resolution reconstruction prototype consisting of a series of convolutional neural networks (CNN) for a complete five-minute 2D knee MRI protocol.
Methods: In this prospective study, 20 volunteers were examined using a 3T-MRI-scanner (Ingenia Elition X, Philips). Similar to clinical practice, the protocol consists of a fat-saturated 2D-proton-density-sequence in coronal, sagittal and transversal orientation as well as a sagittal T1-weighted sequence.
Background: To investigate the potential of combining compressed sensing (CS) and deep learning (DL) for accelerated two-dimensional (2D) and three-dimensional (3D) magnetic resonance imaging (MRI) of the shoulder.
Methods: Twenty healthy volunteers were examined using at 3-T scanner with a fat-saturated, coronal, 2D proton density-weighted sequence with four acceleration levels (2.3, 4, 6, and 8) and a 3D sequence with three acceleration levels (8, 10, and 13), all accelerated with CS and reconstructed using the conventional algorithm and a new DL-based algorithm (CS-AI).
Article Synopsis
- - The study compared the image quality and diagnostic accuracy of deep-learning-based image denoising algorithms (DLIDs) against traditional iterative reconstruction methods in low-dose CT scans for patients with suspected kidney stones.
- - Results showed that image noise decreased progressively from filtered-back projection (FBP) to hybrid iterative reconstruction (HIR) to DLID, with model-based iterative reconstruction (MBIR) producing the best overall image quality and diagnostic accuracy.
- - Diagnostic accuracy for detecting urinary stones was highest with MBIR (0.94), while DLID (0.90) performed similarly to HIR (0.90) but outperformed FBP (0.84); stone size measurements were consistent across all methods.