scholarly journals Faculty Opinions recommendation of Segmentation of Peripheral Nerves From Magnetic Resonance Neurography: A Fully-Automatic, Deep Learning-Based Approach.

Author(s):  
Jun Li
2018 ◽  
Vol 9 ◽  
Author(s):  
Fabian Balsiger ◽  
Carolin Steindel ◽  
Mirjam Arn ◽  
Benedikt Wagner ◽  
Lorenz Grunder ◽  
...  

2019 ◽  
Vol 23 (04) ◽  
pp. 347-360
Author(s):  
Majid Chalian ◽  
Avneesh Chhabra

AbstractMagnetic resonance neurography (MRN), also known as MR neurography, is a dedicated imaging technique for the peripheral nerves, used both in a clinical setting and research. However, like any other new diagnostic processes, there are technical, cost, and patient selection issues to overcome as well as potential imaging pitfalls to recognize before MRN can be adopted efficiently into routine clinical practice. This review focuses on the 10 most important practical tips to get started with MRN with a view to shortening the time needed for radiologists to implement this clinically useful technique into their imaging practices.


2017 ◽  
Vol 56 (6) ◽  
pp. E78-E84 ◽  
Author(s):  
Michael Vaeggemose ◽  
Signe Vaeth ◽  
Mirko Pham ◽  
Steffen Ringgaard ◽  
Uffe B. Jensen ◽  
...  

2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Nils Netzer ◽  
Cedric Weißer ◽  
Patrick Schelb ◽  
Xianfeng Wang ◽  
Xiaoyan Qin ◽  
...  

2015 ◽  
Vol 48 (02) ◽  
pp. 129-137 ◽  
Author(s):  
Vaishali Upadhyaya ◽  
Divya Narain Upadhyaya ◽  
Adarsh Kumar ◽  
Ashok Kumar Pandey ◽  
Ratni Gujral ◽  
...  

ABSTRACTMagnetic Resonance Imaging (MRI) is being increasingly recognised all over the world as the imaging modality of choice for brachial plexus and peripheral nerve lesions. Recent refinements in MRI protocols have helped in imaging nerve tissue with greater clarity thereby helping in the identification, localisation and classification of nerve lesions with greater confidence than was possible till now. This article on Magnetic Resonance Neurography (MRN) is based on the authors’ experience of imaging the brachial plexus and peripheral nerves using these protocols over the last several years.


2021 ◽  
Vol 16 (01) ◽  
pp. e17-e23
Author(s):  
Vanessa Ku ◽  
Cameron Cox ◽  
Andrew Mikeska ◽  
Brendan MacKay

AbstractPeripheral nerve injuries (PNIs) continue to present both diagnostic and treatment challenges. While nerve transections are typically a straightforward diagnosis, other types of PNIs, such as chronic or traumatic nerve compression, may be more difficult to evaluate due to their varied presentation and limitations of current diagnostic tools. As a result, diagnosis may be delayed, and these patients may go on to develop progressive symptoms, impeding normal activity. In the past, PNIs were diagnosed by history and clinical examination alone or techniques that raised concerns regarding accuracy, invasiveness, or operator dependency. Magnetic resonance neurography (MRN) has been increasingly utilized in clinical settings due to its ability to visualize complex nerve structures along their entire pathway and distinguish nerves from surrounding vasculature and tissue in a noninvasive manner. In this review, we discuss the clinical applications of MRN in the diagnosis, as well as pre- and postsurgical assessments of patients with peripheral neuropathies.


2017 ◽  
Vol 50 (3) ◽  
pp. 190-196 ◽  
Author(s):  
Paulo Moraes Agnollitto ◽  
Marcio Wen King Chu ◽  
Marcelo Novelino Simão ◽  
Marcello Henrique Nogueira-Barbosa

Abstract Injuries of the sciatic nerve are common causes of pain and limitation in the lower limbs. Due to its particular anatomy and its long course, the sciatic nerve is often involved in diseases of the pelvis or leg. In recent years, magnetic resonance neurography has become established as an important tool for the study of peripheral nerves and can be widely applied to the study of the sciatic nerve. Therefore, detailed knowledge of its anatomy and of the most prevalent diseases affecting it is essential to maximizing the accuracy of diagnostic imaging.


2021 ◽  
Vol 23 (1) ◽  
Author(s):  
Sona Ghadimi ◽  
Daniel A. Auger ◽  
Xue Feng ◽  
Changyu Sun ◽  
Craig H. Meyer ◽  
...  

Abstract Background Cardiovascular magnetic resonance (CMR) cine displacement encoding with stimulated echoes (DENSE) measures heart motion by encoding myocardial displacement into the signal phase, facilitating high accuracy and reproducibility of global and segmental myocardial strain and providing benefits in clinical performance. While conventional methods for strain analysis of DENSE images are faster than those for myocardial tagging, they still require manual user assistance. The present study developed and evaluated deep learning methods for fully-automatic DENSE strain analysis. Methods Convolutional neural networks (CNNs) were developed and trained to (a) identify the left-ventricular (LV) epicardial and endocardial borders, (b) identify the anterior right-ventricular (RV)-LV insertion point, and (c) perform phase unwrapping. Subsequent conventional automatic steps were employed to compute strain. The networks were trained using 12,415 short-axis DENSE images from 45 healthy subjects and 19 heart disease patients and were tested using 10,510 images from 25 healthy subjects and 19 patients. Each individual CNN was evaluated, and the end-to-end fully-automatic deep learning pipeline was compared to conventional user-assisted DENSE analysis using linear correlation and Bland Altman analysis of circumferential strain. Results LV myocardial segmentation U-Nets achieved a DICE similarity coefficient of 0.87 ± 0.04, a Hausdorff distance of 2.7 ± 1.0 pixels, and a mean surface distance of 0.41 ± 0.29 pixels in comparison with manual LV myocardial segmentation by an expert. The anterior RV-LV insertion point was detected within 1.38 ± 0.9 pixels compared to manually annotated data. The phase-unwrapping U-Net had similar or lower mean squared error vs. ground-truth data compared to the conventional path-following method for images with typical signal-to-noise ratio (SNR) or low SNR (p < 0.05), respectively. Bland–Altman analyses showed biases of 0.00 ± 0.03 and limits of agreement of − 0.04 to 0.05 or better for deep learning-based fully-automatic global and segmental end-systolic circumferential strain vs. conventional user-assisted methods. Conclusions Deep learning enables fully-automatic global and segmental circumferential strain analysis of DENSE CMR providing excellent agreement with conventional user-assisted methods. Deep learning-based automatic strain analysis may facilitate greater clinical use of DENSE for the quantification of global and segmental strain in patients with cardiac disease.


Sign in / Sign up

Export Citation Format

Share Document