Literature DB >> 33783571

Automated cartilage segmentation and quantification using 3D ultrashort echo time (UTE) cones MR imaging with deep convolutional neural networks.

Yan-Ping Xue1,2, Hyungseok Jang1, Michal Byra1, Zhen-Yu Cai1, Mei Wu1, Eric Y Chang1,3, Ya-Jun Ma1, Jiang Du4.   

Abstract

OBJECTIVE: To develop a fully automated full-thickness cartilage segmentation and mapping of T1, T1ρ, and T2*, as well as macromolecular fraction (MMF) by combining a series of quantitative 3D ultrashort echo time (UTE) cones MR imaging with a transfer learning-based U-Net convolutional neural networks (CNN) model.
METHODS: Sixty-five participants (20 normal, 29 doubtful-minimal osteoarthritis (OA), and 16 moderate-severe OA) were scanned using 3D UTE cones T1 (Cones-T1), adiabatic T1ρ (Cones-AdiabT1ρ), T2* (Cones-T2*), and magnetization transfer (Cones-MT) sequences at 3 T. Manual segmentation was performed by two experienced radiologists, and automatic segmentation was completed using the proposed U-Net CNN model. The accuracy of cartilage segmentation was evaluated using the Dice score and volumetric overlap error (VOE). Pearson correlation coefficient and intraclass correlation coefficient (ICC) were calculated to evaluate the consistency of quantitative MR parameters extracted from automatic and manual segmentations. UTE biomarkers were compared among different subject groups using one-way ANOVA.
RESULTS: The U-Net CNN model provided reliable cartilage segmentation with a mean Dice score of 0.82 and a mean VOE of 29.86%. The consistency of Cones-T1, Cones-AdiabT1ρ, Cones-T2*, and MMF calculated using automatic and manual segmentations ranged from 0.91 to 0.99 for Pearson correlation coefficients, and from 0.91 to 0.96 for ICCs, respectively. Significant increases in Cones-T1, Cones-AdiabT1ρ, and Cones-T2* (p < 0.05) and a decrease in MMF (p < 0.001) were observed in doubtful-minimal OA and/or moderate-severe OA over normal controls.
CONCLUSION: Quantitative 3D UTE cones MR imaging combined with the proposed U-Net CNN model allows a fully automated comprehensive assessment of articular cartilage. KEY POINTS: • 3D UTE cones imaging combined with U-Net CNN model was able to provide fully automated cartilage segmentation. • UTE parameters obtained from automatic segmentation were able to reliably provide a quantitative assessment of cartilage.
© 2021. European Society of Radiology.

Entities:  

Keywords:  Biomarkers; Cartilage; Deep learning; Osteoarthritis

Mesh:

Year:  2021        PMID: 33783571      PMCID: PMC8964270          DOI: 10.1007/s00330-021-07853-6

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  36 in total

1.  elastix: a toolbox for intensity-based medical image registration.

Authors:  Stefan Klein; Marius Staring; Keelin Murphy; Max A Viergever; Josien P W Pluim
Journal:  IEEE Trans Med Imaging       Date:  2009-11-17       Impact factor: 10.048

2.  Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U-Net with transfer learning.

Authors:  Michal Byra; Mei Wu; Xiaodong Zhang; Hyungseok Jang; Ya-Jun Ma; Eric Y Chang; Sameer Shah; Jiang Du
Journal:  Magn Reson Med       Date:  2019-09-19       Impact factor: 4.668

3.  Quantitative magnetization transfer ultrashort echo time imaging using a time-efficient 3D multispoke Cones sequence.

Authors:  Ya-Jun Ma; Eric Y Chang; Michael Carl; Jiang Du
Journal:  Magn Reson Med       Date:  2017-05-03       Impact factor: 4.668

4.  Automatic Articular Cartilage Segmentation Based on Pattern Recognition from Knee MRI Images.

Authors:  Jianfei Pang; PengYue Li; Mingguo Qiu; Wei Chen; Liang Qiao
Journal:  J Digit Imaging       Date:  2015-12       Impact factor: 4.056

5.  Patellar cartilage: T2 values and morphologic abnormalities at 3.0-T MR imaging in relation to physical activity in asymptomatic subjects from the osteoarthritis initiative.

Authors:  Christoph Stehling; Hans Liebl; Roland Krug; Nancy E Lane; Michael C Nevitt; John Lynch; Charles E McCulloch; Thomas M Link
Journal:  Radiology       Date:  2009-12-17       Impact factor: 11.105

Review 6.  Quantitative radiologic imaging techniques for articular cartilage composition: toward early diagnosis and development of disease-modifying therapeutics for osteoarthritis.

Authors:  Edwin H G Oei; Jasper van Tiel; William H Robinson; Garry E Gold
Journal:  Arthritis Care Res (Hoboken)       Date:  2014-08       Impact factor: 4.794

7.  Deep convolutional neural network for segmentation of knee joint anatomy.

Authors:  Zhaoye Zhou; Gengyan Zhao; Richard Kijowski; Fang Liu
Journal:  Magn Reson Med       Date:  2018-05-17       Impact factor: 4.668

8.  Quantitative three-dimensional ultrashort echo time cones imaging of the knee joint with motion correction.

Authors:  Mei Wu; Wei Zhao; Lidi Wan; Lena Kakos; Liang Li; Saeed Jerban; Hyungseok Jang; Eric Y Chang; Jiang Du; Ya-Jun Ma
Journal:  NMR Biomed       Date:  2019-11-12       Impact factor: 4.044

9.  Quantitative cartilage imaging in knee osteoarthritis.

Authors:  Felix Eckstein; Wolfgang Wirth
Journal:  Arthritis       Date:  2010-12-08

10.  Attention gated networks: Learning to leverage salient regions in medical images.

Authors:  Jo Schlemper; Ozan Oktay; Michiel Schaap; Mattias Heinrich; Bernhard Kainz; Ben Glocker; Daniel Rueckert
Journal:  Med Image Anal       Date:  2019-02-05       Impact factor: 8.545

View more
  4 in total

Review 1.  Ultrashort Echo Time Magnetic Resonance Imaging Techniques: Met and Unmet Needs in Musculoskeletal Imaging.

Authors:  Amir Masoud Afsahi; Yajun Ma; Hyungseok Jang; Saeed Jerban; Christine B Chung; Eric Y Chang; Jiang Du
Journal:  J Magn Reson Imaging       Date:  2021-12-28       Impact factor: 5.119

Review 2.  Articular Cartilage Assessment Using Ultrashort Echo Time MRI: A Review.

Authors:  Amir Masoud Afsahi; Sam Sedaghat; Dina Moazamian; Ghazaleh Afsahi; Jiyo S Athertya; Hyungseok Jang; Ya-Jun Ma
Journal:  Front Endocrinol (Lausanne)       Date:  2022-05-26       Impact factor: 6.055

3.  Multiresolution Aggregation Transformer UNet Based on Multiscale Input and Coordinate Attention for Medical Image Segmentation.

Authors:  Shaolong Chen; Changzhen Qiu; Weiping Yang; Zhiyong Zhang
Journal:  Sensors (Basel)       Date:  2022-05-18       Impact factor: 3.847

4.  Performance and Robustness of Regional Image Segmentation Driven by Selected Evolutionary and Genetic Algorithms: Study on MR Articular Cartilage Images.

Authors:  Jan Kubicek; Alice Varysova; Martin Cerny; Kristyna Hancarova; David Oczka; Martin Augustynek; Marek Penhaker; Ondrej Prokop; Radomir Scurek
Journal:  Sensors (Basel)       Date:  2022-08-23       Impact factor: 3.847

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.