Literature DB >> 31143649

Fully automated segmentation of wrist bones on T2-weighted fat-suppressed MR images in early rheumatoid arthritis.

Lun Matthew Wong1, Lin Shi1, Fan Xiao1, James Francis Griffith1.   

Abstract

BACKGROUND: Magnetic resonance imaging (MRI) allows accurate determination of soft tissue and bone inflammation in rheumatoid arthritis. Inflammation can be measured semi-quantitatively using the well-established RA-MRI scoring system (RAMRIS), but its application is time consuming in routine clinical practice. To fully realize an automated quantitation of inflammation scoring for clinical use, automatic segmentation of the wrist bones on MR imaging is needed. Most previous studies extracted the wrist bones on T1-weighted (T1W) MR images, and then used registration to segment T2W fat-suppressed images for bone marrow oedema quantification, introducing spatial errors into the process. Relatively little work has tried segmentation directly from T2W fat-suppressed images and no prior study have used convolution neural network (CNN) to segment the wrist bones. The purpose of this study is to develop a CNN-based algorithm for automated segmentation of the wrist bones in early rheumatoid arthritis (ERA) patients on T2W fat-saturated MR images.
METHODS: As preliminary tests indicated that out-of-the-box segmentation CNN U-net performance was compromised by close apposition of wrist tendons and bone, we separated the volumes prior to segmentation by using classification CNN Inception V3 to group images with similar features. The classified images were then segmented by individually trained U-net. We trained the networks on 40 cases and tested them on 11 cases derived from an MR imaging dataset of 51 patients with varying severity of ERA.
RESULTS: We obtained a wrist bone segmentation with an average dice similarity coefficient (DICE) of 0.888±0.014, when compared to a manually drawn label. These results are comparable to existing atlas-based methods.
CONCLUSIONS: We have developed a fully automatic method to segment the wrist bones in ERA patients of varying severity directly from T2W fat-suppressed MR images. This compares well with manually drawn labels.

Entities:  

Keywords:  Wrist; bone marrow oedema (BME); magnetic resonance imaging (MRI); rheumatoid arthritis (RA)

Year:  2019        PMID: 31143649      PMCID: PMC6511720          DOI: 10.21037/qims.2019.04.03

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  18 in total

1.  Generalized overlap measures for evaluation and validation in medical image analysis.

Authors:  William R Crum; Oscar Camara; Derek L G Hill
Journal:  IEEE Trans Med Imaging       Date:  2006-11       Impact factor: 10.048

2.  2010 Rheumatoid arthritis classification criteria: an American College of Rheumatology/European League Against Rheumatism collaborative initiative.

Authors:  Daniel Aletaha; Tuhina Neogi; Alan J Silman; Julia Funovits; David T Felson; Clifton O Bingham; Neal S Birnbaum; Gerd R Burmester; Vivian P Bykerk; Marc D Cohen; Bernard Combe; Karen H Costenbader; Maxime Dougados; Paul Emery; Gianfranco Ferraccioli; Johanna M W Hazes; Kathryn Hobbs; Tom W J Huizinga; Arthur Kavanaugh; Jonathan Kay; Tore K Kvien; Timothy Laing; Philip Mease; Henri A Ménard; Larry W Moreland; Raymond L Naden; Theodore Pincus; Josef S Smolen; Ewa Stanislawska-Biernat; Deborah Symmons; Paul P Tak; Katherine S Upchurch; Jirí Vencovský; Frederick Wolfe; Gillian Hawker
Journal:  Arthritis Rheum       Date:  2010-09

3.  User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability.

Authors:  Paul A Yushkevich; Joseph Piven; Heather Cody Hazlett; Rachel Gimpel Smith; Sean Ho; James C Gee; Guido Gerig
Journal:  Neuroimage       Date:  2006-03-20       Impact factor: 6.556

4.  The OMERACT psoriatic arthritis magnetic resonance imaging scoring system (PsAMRIS): definitions of key pathologies, suggested MRI sequences, and preliminary scoring system for PsA Hands.

Authors:  Mikkel Ostergaard; Fiona McQueen; Charlotte Wiell; Paul Bird; Pernille Bøyesen; Bo Ejbjerg; Charles Peterfy; Frédérique Gandjbakhch; Anne Duer-Jensen; Laura Coates; Espen A Haavardsholm; Kay-Geert A Hermann; Marissa Lassere; Philip O'Connor; Paul Emery; Harry Genant; Philip G Conaghan
Journal:  J Rheumatol       Date:  2009-08       Impact factor: 4.666

Review 5.  A clinical overview of bone marrow edema.

Authors:  M Manara; M Varenna
Journal:  Reumatismo       Date:  2014-07-28

6.  Quantifying synovitis in rheumatoid arthritis using computer-assisted manual segmentation with 3 Tesla MRI scanning.

Authors:  Arista S Chand; Alexandra McHaffie; Andrew W Clarke; Quentin Reeves; Yu Mwee Tan; Nicola Dalbeth; Megan Williams; Fiona McQueen
Journal:  J Magn Reson Imaging       Date:  2011-05       Impact factor: 4.813

7.  Magnetic resonance imaging findings in 84 patients with early rheumatoid arthritis: bone marrow oedema predicts erosive progression.

Authors:  E A Haavardsholm; P Bøyesen; M Østergaard; A Schildvold; T K Kvien
Journal:  Ann Rheum Dis       Date:  2007-11-02       Impact factor: 19.103

Review 8.  OMERACT Rheumatoid Arthritis Magnetic Resonance Imaging Studies. Core set of MRI acquisitions, joint pathology definitions, and the OMERACT RA-MRI scoring system.

Authors:  Mikkel Østergaard; Charles Peterfy; Philip Conaghan; Fiona McQueen; Paul Bird; Bo Ejbjerg; Ron Shnier; Philip O'Connor; Mette Klarlund; Paul Emery; Harry Genant; Marissa Lassere; John Edmonds
Journal:  J Rheumatol       Date:  2003-06       Impact factor: 4.666

9.  Rapid improvement in rheumatoid arthritis patients on combination of methotrexate and infliximab: clinical and magnetic resonance imaging evaluation.

Authors:  Lai-Shan Tam; James F Griffith; Alfred B Yu; Tena K Li; Edmund K Li
Journal:  Clin Rheumatol       Date:  2006-07-26       Impact factor: 3.650

10.  Segmentation of bones in magnetic resonance images of the wrist.

Authors:  Justyna Włodarczyk; Kamila Czaplicka; Zbisław Tabor; Wadim Wojciechowski; Andrzej Urbanik
Journal:  Int J Comput Assist Radiol Surg       Date:  2014-08-06       Impact factor: 2.924

View more
  4 in total

1.  Three-dimensional organ extraction method for color volume image based on the closed-form solution strategy.

Authors:  Bin Liu; Xiaohui Zhang; Liang Yang; Jianxin Zhang
Journal:  Quant Imaging Med Surg       Date:  2020-04

2.  An unsupervised semi-automated pulmonary nodule segmentation method based on enhanced region growing.

Authors:  He Ren; Lingxiao Zhou; Gang Liu; Xueqing Peng; Weiya Shi; Huilin Xu; Fei Shan; Lei Liu
Journal:  Quant Imaging Med Surg       Date:  2020-01

3.  Clinical utility of F-18 sodium fluoride PET/CT for estimating disease activity in patients with rheumatoid arthritis.

Authors:  Hee Jin Park; Sung Hae Chang; Jeong Won Lee; Sang Mi Lee
Journal:  Quant Imaging Med Surg       Date:  2021-04

Review 4.  Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches.

Authors:  Benjamin Fritz; Jan Fritz
Journal:  Skeletal Radiol       Date:  2021-09-01       Impact factor: 2.199

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.