Literature DB >> 30905742

Diagnosing osteoarthritis from T2 maps using deep learning: an analysis of the entire Osteoarthritis Initiative baseline cohort.

V Pedoia1, J Lee2, B Norman3, T M Link4, S Majumdar5.   

Abstract

OBJECTIVE: We aim to study to what extent conventional and deep-learning-based T2 relaxometry patterns are able to distinguish between knees with and without radiographic osteoarthritis (OA).
METHODS: T2 relaxation time maps were analyzed for 4,384 subjects from the baseline Osteoarthritis Initiative (OAI) Dataset. Voxel Based Relaxometry (VBR) was used for automatic quantification and voxel-based analysis of the differences in T2 between subjects with and without radiographic OA. A Densely Connected Convolutional Neural Network (DenseNet) was trained to diagnose OA from T2 data. For comparison, more classical feature extraction techniques and shallow classifiers were used to benchmark the performance of our algorithm's results. Deep and shallow models were evaluated with and without the inclusion of risk factors. Sensitivity and Specificity values and McNemar test were used to compare the performance of the different classifiers.
RESULTS: The best shallow model was obtained when the first ten Principal Components, demographics and pain score were included as features (AUC = 77.77%, Sensitivity = 67.01%, Specificity = 71.79%). In comparison, DenseNet trained on raw T2 data obtained AUC = 83.44%, Sensitivity = 76.99%, Specificity = 77.94%. McNemar test on two misclassified proportions form the shallow and deep model showed that the boost in performance was statistically significant (McNemar's chi-squared = 10.33, degree of freedom (DF) = 1, P-value = 0.0013).
CONCLUSION: In this study, we presented a Magnetic Resonance Imaging (MRI)-based data-driven platform using T2 measurements to characterize radiographic OA. Our results showed that feature learning from T2 maps has potential in uncovering information that can potentially better diagnose OA than simple averages or linear patterns decomposition.
Copyright © 2019 Osteoarthritis Research Society International. Published by Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Convolutional neural network; Deep learning; Quantitative MRI; T(2) relaxation times; Voxel based relaxometry

Year:  2019        PMID: 30905742      PMCID: PMC6579664          DOI: 10.1016/j.joca.2019.02.800

Source DB:  PubMed          Journal:  Osteoarthritis Cartilage        ISSN: 1063-4584            Impact factor:   6.576


  31 in total

Review 1.  Controlling the familywise error rate in functional neuroimaging: a comparative review.

Authors:  Thomas Nichols; Satoru Hayasaka
Journal:  Stat Methods Med Res       Date:  2003-10       Impact factor: 3.021

2.  Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging.

Authors:  Fang Liu; Zhaoye Zhou; Hyungseok Jang; Alexey Samsonov; Gengyan Zhao; Richard Kijowski
Journal:  Magn Reson Med       Date:  2017-07-21       Impact factor: 4.668

3.  Early articular cartilage MRI T2 changes after anterior cruciate ligament reconstruction correlate with later changes in T2 and cartilage thickness.

Authors:  Ashley Williams; Carl S Winalski; Constance R Chu
Journal:  J Orthop Res       Date:  2016-07-29       Impact factor: 3.494

4.  Number of Persons With Symptomatic Knee Osteoarthritis in the US: Impact of Race and Ethnicity, Age, Sex, and Obesity.

Authors:  Bhushan R Deshpande; Jeffrey N Katz; Daniel H Solomon; Edward H Yelin; David J Hunter; Stephen P Messier; Lisa G Suter; Elena Losina
Journal:  Arthritis Care Res (Hoboken)       Date:  2016-11-03       Impact factor: 4.794

5.  Longitudinal analysis of MRI T2 knee cartilage laminar organization in a subset of patients from the osteoarthritis initiative: a texture approach.

Authors:  Julio Carballido-Gamio; Gabby B Joseph; John A Lynch; Thomas M Link; Sharmila Majumdar
Journal:  Magn Reson Med       Date:  2010-12-02       Impact factor: 4.668

6.  Response of knee cartilage T1rho and T2 relaxation times to in vivo mechanical loading in individuals with and without knee osteoarthritis.

Authors:  R B Souza; D Kumar; N Calixto; J Singh; J Schooler; K Subburaj; X Li; T M Link; S Majumdar
Journal:  Osteoarthritis Cartilage       Date:  2014-04-30       Impact factor: 6.576

Review 7.  Multiple testing corrections, nonparametric methods, and random field theory.

Authors:  Thomas E Nichols
Journal:  Neuroimage       Date:  2012-04-12       Impact factor: 6.556

8.  Knee Injury and Osteoarthritis Outcome Score (KOOS)--development of a self-administered outcome measure.

Authors:  E M Roos; H P Roos; L S Lohmander; C Ekdahl; B D Beynnon
Journal:  J Orthop Sports Phys Ther       Date:  1998-08       Impact factor: 4.751

9.  Fully automatic analysis of the knee articular cartilage T1ρ relaxation time using voxel-based relaxometry.

Authors:  Valentina Pedoia; Xiaojuan Li; Favian Su; Nathaniel Calixto; Sharmila Majumdar
Journal:  J Magn Reson Imaging       Date:  2015-10-07       Impact factor: 4.813

10.  Detecting and classifying lesions in mammograms with Deep Learning.

Authors:  Dezső Ribli; Anna Horváth; Zsuzsa Unger; Péter Pollner; István Csabai
Journal:  Sci Rep       Date:  2018-03-15       Impact factor: 4.379

View more
  16 in total

Review 1.  Current applications and future directions of deep learning in musculoskeletal radiology.

Authors:  Pauley Chea; Jacob C Mandell
Journal:  Skeletal Radiol       Date:  2019-08-04       Impact factor: 2.199

2.  DADP: Dynamic abnormality detection and progression for longitudinal knee magnetic resonance images from the Osteoarthritis Initiative.

Authors:  Chao Huang; Zhenlin Xu; Zhengyang Shen; Tianyou Luo; Tengfei Li; Daniel Nissman; Amanda Nelson; Yvonne Golightly; Marc Niethammer; Hongtu Zhu
Journal:  Med Image Anal       Date:  2022-01-01       Impact factor: 8.545

Review 3.  Studying osteoarthritis with artificial intelligence applied to magnetic resonance imaging.

Authors:  Francesco Calivà; Nikan K Namiri; Maureen Dubreuil; Valentina Pedoia; Eugene Ozhinsky; Sharmila Majumdar
Journal:  Nat Rev Rheumatol       Date:  2021-11-30       Impact factor: 20.543

Review 4.  AI MSK clinical applications: cartilage and osteoarthritis.

Authors:  Gabby B Joseph; Charles E McCulloch; Jae Ho Sohn; Valentina Pedoia; Sharmila Majumdar; Thomas M Link
Journal:  Skeletal Radiol       Date:  2021-11-04       Impact factor: 2.199

5.  Machine learning to predict incident radiographic knee osteoarthritis over 8 Years using combined MR imaging features, demographics, and clinical factors: data from the Osteoarthritis Initiative.

Authors:  G B Joseph; C E McCulloch; M C Nevitt; T M Link; J H Sohn
Journal:  Osteoarthritis Cartilage       Date:  2021-11-18       Impact factor: 6.576

6.  Synthesizing Quantitative T2 Maps in Right Lateral Knee Femoral Condyles from Multicontrast Anatomic Data with a Conditional Generative Adversarial Network.

Authors:  Bragi Sveinsson; Akshay S Chaudhari; Bo Zhu; Neha Koonjoo; Martin Torriani; Garry E Gold; Matthew S Rosen
Journal:  Radiol Artif Intell       Date:  2021-05-26

7.  Open Source Software for Automatic Subregional Assessment of Knee Cartilage Degradation Using Quantitative T2 Relaxometry and Deep Learning.

Authors:  Kevin A Thomas; Dominik Krzemiński; Łukasz Kidziński; Rohan Paul; Elka B Rubin; Eni Halilaj; Marianne S Black; Akshay Chaudhari; Garry E Gold; Scott L Delp
Journal:  Cartilage       Date:  2021-09-08       Impact factor: 3.117

Review 8.  Deep Learning for Lesion Detection, Progression, and Prediction of Musculoskeletal Disease.

Authors:  Richard Kijowski; Fang Liu; Francesco Caliva; Valentina Pedoia
Journal:  J Magn Reson Imaging       Date:  2019-11-25       Impact factor: 4.813

9.  CORR Insights®: What Is the Correlation Among dGEMRIC, T1p, and T2* Quantitative MRI Cartilage Mapping Techniques in Developmental Hip Dysplasia?

Authors:  Hollis G Potter
Journal:  Clin Orthop Relat Res       Date:  2021-05-01       Impact factor: 4.176

10.  How feasible is the stratification of osteoarthritis phenotypes by means of artificial intelligence?

Authors:  Amanda E Nelson
Journal:  Expert Rev Precis Med Drug Dev       Date:  2020-11-23
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.