Automated cartilage segmentation from 3D MR images of hip joint using an ensemble of neural networks

2017 ◽  
Author(s):  
Ying Xia ◽  
Jose V. Manjon ◽  
Craig Engstrom ◽  
Stuart Crozier ◽  
Olivier Salvado ◽  
...  
Keyword(s):  
Neural Networks ◽  
Hip Joint ◽  
Mr Images

Automated segmentation of the knee for age assessment in 3D MR images using convolutional neural networks

2018 ◽  
Vol 133 (4) ◽  
pp. 1191-1205 ◽  
Author(s):  
Paul-Louis Pröve ◽  
Eilin Jopp-van Well ◽  
Ben Stanczus ◽  
Michael M. Morlock ◽  
Jochen Herrmann ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Automated Segmentation ◽  
Mr Images ◽  
Age Assessment

Intraneural ganglia in the hip and pelvic region

2009 ◽  
Vol 111 (2) ◽  
pp. 317-325 ◽  
Author(s):  
Robert J. Spinner ◽  
Marie-Noëlle Hébert-Blouin ◽  
Robert T. Trousdale ◽  
Rajiv Midha ◽  
Stephen M. Russell ◽  
...  
Keyword(s):  
Sciatic Nerve ◽  
Mr Imaging ◽  
Hip Joint ◽  
Lumbosacral Plexus ◽  
Mr Images ◽  
Mechanism Of Formation ◽  
Intraneural Ganglion ◽  
Rare Site ◽  
Joint Connection ◽  
Insight Into

Object The authors describe their experience in a series of cases of intraneural ganglia within the hip and pelvic regions, and explain the mechanism of formation and propagation of this pathological entity. Methods Five patients with 6 intraneural ganglia are presented. Four patients presented with symptomatic intraneural ganglia in the buttock and pelvis affecting the sciatic and lumbosacral plexus elements. An asymptomatic cyst affecting the opposite sciatic nerve was found on MR imaging in 1 patient. The fifth patient, previously reported on by another group, had an obturator intraneural ganglion that the authors reinterpreted. Results All 5 intraneural ganglia affecting the sciatic and lumbosacral plexus elements were found to have a joint connection to the posteromedial aspect of the hip joint; the obturator intraneural cyst had a joint connection to the anteromedial aspect of the hip joint. In all cases, initial review of the MR images led to their misinterpretation. Conclusions To the authors' knowledge, these are the first cases of intraneural ganglia demonstrated to have a connection to the hip joint. This finding at a rare site provides further evidence for the unifying articular (synovial) theory for the formation of intraneural ganglia and reveals a shared mechanism for their propagation. Furthermore, understanding the pathogenesis of these lesions provides insight into their successful treatment and their recurrence.

scholarly journals Deep Radiogenomics of Lower-Grade Gliomas: Convolutional Neural Networks Predict Tumor Genomic Subtypes Using MR Images

2020 ◽  
Vol 2 (1) ◽  
pp. e180050
Author(s):  
Mateusz Buda ◽  
Ehab A. AlBadawy ◽  
Ashirbani Saha ◽  
Maciej A. Mazurowski
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Lower Grade ◽  
Mr Images

scholarly journals Surface Approximation using Growing Self-Organizing Nets and Gradient Information

2007 ◽  
Vol 4 (3) ◽  
pp. 125-136 ◽  
Author(s):  
Jorge Rivera-Rovelo ◽  
Eduardo Bayro-Corrochano
Keyword(s):  
Neural Networks ◽  
Geometric Algebra ◽  
Mr Images ◽  
3D Object ◽  
Gas Network ◽  
Neural Gas ◽  
Gradient Information ◽  
Surface Estimation ◽  
Space Coordinate ◽  
Self Organizing

In this paper we show how to improve the performance of two self-organizing neural networks used to approximate the shape of a 2D or 3D object by incorporating gradient information in the adaptation stage. The methods are based on the growing versions of the Kohonen's map and the neural gas network. Also, we show that in the adaptation stage the network utilizes efficient transformations, expressed as versors in the conformal geometric algebra framework, which build the shape of the object independent of its position in space (coordinate free). Our algorithms were tested with several images, including medical images (CT and MR images). We include also some examples for the case of 3D surface estimation.

Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks

2016 ◽  
Vol 35 (5) ◽  
pp. 1182-1195 ◽  
Author(s):  
Qi Dou ◽  
Hao Chen ◽  
Lequan Yu ◽  
Lei Zhao ◽  
Jing Qin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Automatic Detection ◽  
Cerebral Microbleeds ◽  
Mr Images

scholarly journals Comparative Study of Encoder–Decoder-Based Convolutional Neural Networks in Cartilage Delineation from Knee Magnetic Resonance Images

2020 ◽  
Vol 16 ◽  
Author(s):  
Ching Wai Yong ◽  
Khin Wee Lai ◽  
Belinda Pingguan Murphy ◽  
Yan Chai Hum
Keyword(s):  
Neural Networks ◽  
Magnetic Resonance ◽  
Convolutional Neural Networks ◽  
Soft Tissues ◽  
Early Stage ◽  
Joint Inflammation ◽  
Magnetic Resonance Images ◽  
Mr Images ◽  
Daily Lives ◽  
Osteoarthritis Initiative

Background: Osteoarthritis (OA) is a common degenerative joint inflammation which may lead to disability. Although OA is not lethal, this disease will remarkably affect patient’s mobility and their daily lives. Detecting OA at an early stage allows for early intervention and may slow down disease progression. Introduction: Magnetic resonance imaging is a useful technique to visualize soft tissues within the knee joint. Cartilage delineation in magnetic resonance (MR) images helps in understanding the disease progressions. Convolutional neural networks (CNNs) have shown promising results in computer vision tasks, and various encoder–decoder-based segmentation neural networks are introduced in the last few years. However, the performances of such networks are unknown in the context of cartilage delineation. Methods: This study trained and compared 10 encoder–decoder-based CNNs in performing cartilage delineation from knee MR images. The knee MR images are obtained from Osteoarthritis Initiative (OAI). The benchmarking process is to compare various CNNs based on the physical specifications and segmentation performances. Results: LadderNet has the least trainable parameters with model size of 5 MB. UNetVanilla crowned the best performances by having 0.8369, 0.9108, and 0.9097 on JSC, DSC, and MCC. Conclusion: UNetVanilla can be served as a benchmark for cartilage delineation in knee MR images while LadderNet served as alternative if there are hardware limitations during production.

Sign in / Sign up

Export Citation Format

Share Document