Learning Correspondences in Knee MR Images from the Osteoarthritis Initiative

Author(s):  
Ricardo Guerrero ◽  
Claire R. Donoghue ◽  
Luis Pizarro ◽  
Daniel Rueckert
Radiology ◽  
2016 ◽  
Vol 278 (1) ◽  
pp. 164-171 ◽  
Author(s):  
Jaanika Kumm ◽  
Frank W. Roemer ◽  
Ali Guermazi ◽  
Aleksandra Turkiewicz ◽  
Martin Englund

Author(s):  
Ching Wai Yong ◽  
Khin Wee Lai ◽  
Belinda Pingguan Murphy ◽  
Yan Chai Hum

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.


2017 ◽  
Vol 88 ◽  
pp. 110-125 ◽  
Author(s):  
Akash Gandhamal ◽  
Sanjay Talbar ◽  
Suhas Gajre ◽  
Ruslan Razak ◽  
Ahmad Fadzil M. Hani ◽  
...  

2008 ◽  
Author(s):  
Hackjoon Shim ◽  
Soochan Lee ◽  
Bohyeong Kim ◽  
Cheng Tao ◽  
Samuel Chang ◽  
...  

2008 ◽  
Vol 68 (3) ◽  
pp. 349-356 ◽  
Author(s):  
D J Hunter ◽  
J Niu ◽  
Y Zhang ◽  
S Totterman ◽  
J Tamez ◽  
...  

Objective:The performance characteristics of hyaline articular cartilage measurement on magnetic resonance imaging (MRI) need to be accurately delineated before widespread application of this technology. Our objective was to assess the rate of natural disease progression of cartilage morphometry measures from baseline to 1 year in knees with osteoarthritis (OA) from a subset of participants from the Osteoarthritis Initiative (OAI).Methods:Subjects included for this exploratory analysis are a subset of the approximately 4700 participants in the OAI Study. Bilateral radiographs and 3T MRI (Siemans Trio) of the knees and clinical data were obtained at baseline and annually in all participants. 160 subjects from the OAI Progression subcohort all of whom had both frequent symptoms and, in the same knee, radiographic OA based on a screening reading done at the OAI clinics were eligible for this exploratory analysis. One knee from each subject was selected for analysis. 150 participants were included. Using sagittal 3D DESSwe (double echo, steady-state sequence with water excitation) MR images from the baseline and 12 follow-up month visit, a segmentation algorithm was applied to the cartilage plates of the index knee to compute the cartilage volume, normalised cartilage volume (volume normalised to bone surface interface area), and percentage denuded area (total cartilage bone interface area denuded of cartilage).Results:Summary statistics of the changes (absolute and percentage) from baseline at 1 year and the standardised response mean (SRM), ie, mean change divided by the SD change were calculated. On average the subjects were 60.9 years of age and obese, with a mean body mass index of 30.3 kg/m2. The SRMs for cartilage volume of various locations are: central medial tibia −0.096; central medial femur −0.394; and patella −0.198. The SRMs for normalised cartilage volume of the various locations are central medial tibia −0.044, central medial femur −0.338 and patella −0.193. The majority of participants had a denuded area at baseline in the central medial femur (62%) and central medial tibia (60%). In general, the SRMs were small.Conclusions: These descriptive results of cartilage morphometry and its change at the 1-year time point from the first substantive MRI data release from the OAI Progression subcohort indicate that the annualised rates of change are small with the central medial femur showing the greatest consistent change.


2010 ◽  
Vol 24 (1) ◽  
pp. 28-43 ◽  
Author(s):  
Jeffrey W. Prescott ◽  
Thomas M. Best ◽  
Mark S. Swanson ◽  
Furqan Haq ◽  
Rebecca D. Jackson ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document