Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Year of publication
- 2018 (2) (remove)
Document Type
- Journal article (2) (remove)
Language
- English (2)
Keywords
- MRI (2) (remove)
Institute
Sonstige beteiligte Institutionen
EU-Project number / Contract (GA) number
- 701983 (1)
Background:
The amount of fatty degeneration (FD) has major impact on the clinical result and cuff integrity after rotator cuff repair. A quantitative analysis with magnet resonance imaging (MRI) spectroscopy was employed to analyze possible correlation of FD with tendon retraction, tendon thickness and patients’ characteristics in full thickness supraspinatus tears.
Methods:
Forty-two patients with full-thickness supraspinatus tears underwent shoulder MRI including an experimental spectroscopic sequence allowing quantification of the fat fraction in the supraspinatus muscle belly. The amount of fatty degeneration was correlated with tendon retraction, tendon thickness, patients’ age, gender, smoker status, symptom duration and body mass index (BMI). Patients were divided in to three groups of retraction (A) 0-10 mm (n=), (B) 11-20 mm (n=) and (C) < 21 mm (n=) and the means of FD for each group were calculated.
Results:
Tendon retraction (R = 0.6) and symptom duration (R = 0.6) correlated positively, whereas tendon thickness correlated negatively (R = − 0.6) with the amount of FD. The fat fraction increased significantly with tendon retraction: Group (A) showed a mean fat mount of 3.7% (±4%), group (B) of 16.7% (±8.2%) and group (C) of 37.5% (±19%). BMI, age and smoker-status only showed weak to moderate correlation with the amount of FD in this cohort.
Conclusion:
MRI spectroscopy revealed significantly higher amount of fat with increasing grade of retraction, symptom duration and decreased tendon thickness. Thus, these parameters may indirectly be associated with the severity of tendon disease.
Even as medical data sets become more publicly accessible, most are restricted to specific medical conditions. Thus, data collection for machine learning approaches remains challenging, and synthetic data augmentation, such as generative adversarial networks (GAN), may overcome this hurdle. In the present quality control study, deep convolutional GAN (DCGAN)-based human brain magnetic resonance (MR) images were validated by blinded radiologists. In total, 96 T1-weighted brain images from 30 healthy individuals and 33 patients with cerebrovascular accident were included. A training data set was generated from the T1-weighted images and DCGAN was applied to generate additional artificial brain images. The likelihood that images were DCGAN-created versus acquired was evaluated by 5 radiologists (2 neuroradiologists [NRs], vs 3 non-neuroradiologists [NNRs]) in a binary fashion to identify real vs created images. Images were selected randomly from the data set (variation of created images, 40%-60%). None of the investigated images was rated as unknown. Of the created images, the NRs rated 45% and 71% as real magnetic resonance imaging images (NNRs, 24%, 40%, and 44%). In contradistinction, 44% and 70% of the real images were rated as generated images by NRs (NNRs, 10%, 17%, and 27%). The accuracy for the NRs was 0.55 and 0.30 (NNRs, 0.83, 0.72, and 0.64). DCGAN-created brain MR images are similar enough to acquired MR images so as to be indistinguishable in some cases. Such an artificial intelligence algorithm may contribute to synthetic data augmentation for "data-hungry" technologies, such as supervised machine learning approaches, in various clinical applications.