Purpose: To evaluate whether the addition of the three-dimensional diffusion-weighted reversed fast imaging with steady state free precession (3D DW-PSIF) sequence improves the identification of peripheral nerves in the distal extremities.

Materials And Methods: Twelve MR neurography (MRN) studies of the distal upper extremity and 12 MRN studies of distal lower extremity were evaluated. From the 24 subjects who were enrolled, 10 had clinically suspected peripheral neuropathy, whereas 14 suffered from various orthopedic diseases and had no clinical signs of neuropathy. In each examination, the ability to identify each peripheral nerve on T2-weighted and 3D DW-PSIF sequences was evaluated using a semi-quantitative (0-2) scale. Thereafter, a total certainty score was registered for each sequence.

Results: Combining the results of all studies, the mean certainty score was 1.92 ± 0.28 on the 3D DW-PSIF images and 1.50 ± 0.72 on the T2-weighted images (P < 0.001). In the upper extremity studies, the corresponding certainty scores were 2.0 and 1.70 ± 0.55, respectively (P = 0.008), and in the lower extremity studies, 1.86 ± 0.35 and 1.36 ± 0.79, respectively (P < 0.001).

Conclusion: The 3D DW-PSIF images provide improved identification of the nerves compared with the T2-weighted images, and should be incorporated in the MRN protocol, whenever accurate nerve localization and/or presurgical evaluation are required.

Download full-text PDF

Source
http://dx.doi.org/10.1002/jmri.22684DOI Listing

Publication Analysis

Top Keywords

three-dimensional diffusion-weighted
8
peripheral nerve
8
mrn studies
8
studies distal
8
upper extremity
8
lower extremity
8
certainty score
8
dw-psif images
8
t2-weighted images
8
extremity studies
8

Similar Publications

Objectives: To evaluate the prevalence and predictors of ischemic lesions on thin-slice DWI (2 mm) in endovascular treatments for unruptured intracranial aneurysms (UIA), particularly explore the potential relationship with pathway plaques.

Methods: Participants eligible for endovascular treatments with UIA at a national stroke center between March 2023 and August 2023 were prospectively enrolled. All participants performed thin-slice DWI (slice thickness of 2 mm) before and after procedures.

View Article and Find Full Text PDF

Background: Anal fistula is a common anorectal disorder that significantly diminishes the quality of life for affected patients. Accurate preoperative evaluation of the fistula's traits is essential for customizing surgical strategies, improving patient outcomes, and reducing the likelihood of the disease returning. This study aimed to evaluate the diagnostic accuracy of multi-phase contrast-enhanced fat-suppressed T1-weighted imaging using three-dimensional gradient echo sequence volumetric interpolated breath-hold examination (CE-FS-T1-3D-VIBE) and fat-suppressed T2-weighted imaging combined with diffusion-weighted imaging (FS-T2WI-DWI) sequence in delineating the characteristics of anal fistulas.

View Article and Find Full Text PDF

Objective: To explore the value of three-dimensional arterial spin labeling (ASL) and six diffusion magnetic resonance imaging (MRI) models in differentiating solid benign and malignant renal tumors.

Methods: This retrospective study included 89 patients with renal tumors. All patients underwent ASL and ZOOMit diffusion-weighted imaging (DWI) examinations and were divided into three groups: clear cell renal cell carcinoma (ccRCC), non-ccRCC, and benign renal tumors (BRT).

View Article and Find Full Text PDF

Introduction: Magnetic resonance imaging (MRI) is both a crucial clinical and research tool for patients with deep brain stimulation (DBS) devices. However, safety concerns predominantly related to device heating have limited such imaging. Rigorous safety testing has demonstrated that scanning outside of vendor guidelines may be both safe and feasible, unlocking unique opportunities for advanced imaging in this patient population.

View Article and Find Full Text PDF

Deep Learning Applied to Diffusion-weighted Imaging for Differentiating Malignant from Benign Breast Tumors without Lesion Segmentation.

Radiol Artif Intell

January 2025

From the Department of Fundamental Development for Advanced Low Invasive Diagnostic Imaging, Nagoya University Graduate School of Medicine, 65 Tsurumai-cho, Showa-ku, Nagoya 466-8550, Japan (M.I.); Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan (M.I., M.K., M.H., Y.N.); A.I. System Research, Kyoto, Japan (R.M.); Kyoto University Faculty of Medicine, Kyoto, Japan (K.T., T.Y.); Department of Diagnostic Radiology, Kyoto City Hospital, Kyoto, Japan (A.M.); Department of Diagnostic Radiology, Kansai Electric Power Hospital, Osaka, Japan (M.H.); e-Growth, Kyoto, Japan (K.I.); and Department of Breast Surgery, Kyoto University Graduate School of Medicine, Kyoto, Japan (M.T.).

Article Synopsis
  • - The study aimed to assess how well various AI models, specifically different types of convolutional neural networks (CNNs), could distinguish between benign and malignant breast tumors using diffusion-weighted imaging (DWI), and compared these results to evaluations made by radiologists.
  • - Data was collected from 334 breast lesions scanned between May 2019 and March 2022, and results indicated that a small 2D CNN model outperformed a 3D CNN and matched or exceeded radiologists in diagnostic accuracy for identifying tumors.
  • - The findings suggested that AI models, especially the small 2D CNN using data augmentation techniques, performed comparably to radiologists in both sensitivity and specificity, making them a viable tool in radiological
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!