Literature DB >> 32696257

Deep learning for the rapid automatic quantification and characterization of rotator cuff muscle degeneration from shoulder CT datasets.

Elham Taghizadeh1, Oskar Truffer1, Fabio Becce2, Sylvain Eminian2, Stacey Gidoin2, Alexandre Terrier3, Alain Farron4, Philippe Büchler5.   

Abstract

OBJECTIVES: This study aimed at developing a convolutional neural network (CNN) able to automatically quantify and characterize the level of degeneration of rotator cuff (RC) muscles from shoulder CT images including muscle atrophy and fatty infiltration.
METHODS: One hundred three shoulder CT scans from 95 patients with primary glenohumeral osteoarthritis undergoing anatomical total shoulder arthroplasty were retrospectively retrieved. Three independent radiologists manually segmented the premorbid boundaries of all four RC muscles on standardized sagittal-oblique CT sections. This premorbid muscle segmentation was further automatically predicted using a CNN. Automatically predicted premorbid segmentations were then used to quantify the ratio of muscle atrophy, fatty infiltration, secondary bone formation, and overall muscle degeneration. These muscle parameters were compared with measures obtained manually by human raters.
RESULTS: Average Dice similarity coefficients for muscle segmentations obtained automatically with the CNN (88% ± 9%) and manually by human raters (89% ± 6%) were comparable. No significant differences were observed for the subscapularis, supraspinatus, and teres minor muscles (p > 0.120), whereas Dice coefficients of the automatic segmentation were significantly higher for the infraspinatus (p < 0.012). The automatic approach was able to provide good-very good estimates of muscle atrophy (R2 = 0.87), fatty infiltration (R2 = 0.91), and overall muscle degeneration (R2 = 0.91). However, CNN-derived segmentations showed a higher variability in quantifying secondary bone formation (R2 = 0.61) than human raters (R2 = 0.87).
CONCLUSIONS: Deep learning provides a rapid and reliable automatic quantification of RC muscle atrophy, fatty infiltration, and overall muscle degeneration directly from preoperative shoulder CT scans of osteoarthritic patients, with an accuracy comparable with that of human raters. KEY POINTS: • Deep learning can not only segment RC muscles currently available in CT images but also learn their pre-existing locations and shapes from invariant anatomical structures visible on CT sections. • Our automatic method is able to provide a rapid and reliable quantification of RC muscle atrophy and fatty infiltration from conventional shoulder CT scans. • The accuracy of our automatic quantitative technique is comparable with that of human raters.

Entities:  

Keywords:  Computed tomography; Deep learning; Muscle atrophy; Rotator cuff; Sarcopenia

Mesh:

Year:  2020        PMID: 32696257      PMCID: PMC7755645          DOI: 10.1007/s00330-020-07070-7

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


  11 in total

1.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation.

Authors:  Simon K Warfield; Kelly H Zou; William M Wells
Journal:  IEEE Trans Med Imaging       Date:  2004-07       Impact factor: 10.048

Review 2.  Shoulder arthroplasty.

Authors:  Florian M Buck; Bernhard Jost; Juerg Hodler
Journal:  Eur Radiol       Date:  2008-07-11       Impact factor: 5.315

3.  Rotator cuff fatty infiltration and atrophy are associated with functional outcomes in anatomic shoulder arthroplasty.

Authors:  Peter L C Lapner; Liangfu Jiang; Tinghua Zhang; George S Athwal
Journal:  Clin Orthop Relat Res       Date:  2014-09-30       Impact factor: 4.176

4.  Importance of a three-dimensional measure of humeral head subluxation in osteoarthritic shoulders.

Authors:  Alexandre Terrier; Julien Ston; Alain Farron
Journal:  J Shoulder Elbow Surg       Date:  2014-08-29       Impact factor: 3.019

5.  Measurements of three-dimensional glenoid erosion when planning the prosthetic replacement of osteoarthritic shoulders.

Authors:  A Terrier; J Ston; X Larrea; A Farron
Journal:  Bone Joint J       Date:  2014-04       Impact factor: 5.082

6.  Ruling out rotator cuff tear in shoulder radiograph series using deep learning: redefining the role of conventional radiograph.

Authors:  Youngjune Kim; Dongjun Choi; Kyong Joon Lee; Yusuhn Kang; Joong Mo Ahn; Eugene Lee; Joon Woo Lee; Heung Sik Kang
Journal:  Eur Radiol       Date:  2020-02-05       Impact factor: 5.315

7.  The Association Between Rotator Cuff Muscle Fatty Infiltration and Glenoid Morphology in Glenohumeral Osteoarthritis.

Authors:  Kenneth W Donohue; Eric T Ricchetti; Jason C Ho; Joseph P Iannotti
Journal:  J Bone Joint Surg Am       Date:  2018-03-07       Impact factor: 5.284

Review 8.  Current peri-operative imaging concepts surrounding shoulder arthroplasty.

Authors:  Travis J Dekker; J R Steele; E V Vinson; G E Garrigues
Journal:  Skeletal Radiol       Date:  2019-02-23       Impact factor: 2.199

9.  Fatty infiltration and atrophy of the rotator cuff do not improve after rotator cuff repair and correlate with poor functional outcome.

Authors:  James N Gladstone; Julie Y Bishop; Ian K Y Lo; Evan L Flatow
Journal:  Am J Sports Med       Date:  2007-03-02       Impact factor: 6.202

10.  Deep Learning Convolutional Neural Networks for the Automatic Quantification of Muscle Fat Infiltration Following Whiplash Injury.

Authors:  Kenneth A Weber; Andrew C Smith; Marie Wasielewski; Kamran Eghtesad; Pranav A Upadhyayula; Max Wintermark; Trevor J Hastie; Todd B Parrish; Sean Mackey; James M Elliott
Journal:  Sci Rep       Date:  2019-05-28       Impact factor: 4.379

View more
  1 in total

1.  Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma.

Authors:  Ella Mi; Radvile Mauricaite; Lillie Pakzad-Shahabi; Jiarong Chen; Andrew Ho; Matt Williams
Journal:  Br J Cancer       Date:  2021-11-30       Impact factor: 7.640

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.