Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain

• Published in: Magma (New York, N.Y.) Vol. 33; no. 4; pp. 483 - 493
• Main Authors: Kemnitz, Jana, Baumgartner, Christian F., Eckstein, Felix, Chaudhari, Akshay, Ruhdorfer, Anja, Wirth, Wolfgang, Eder, Sebastian K., Konukoglu, Ender
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.08.2020
• Subjects: Biomedical Engineering and Bioengineering; Clinical Applications – Musculoskeletal; Computer Appl. in Life Sciences; Health Informatics; Imaging; Medicine; Medicine & Public Health; Radiology; Research Article; Solid State Physics; Deep learning; Muscle; Magnetic resonance imaging; Convolutional neural networks; Automated segmentation
• ISSN: 0968-5243; 1352-8661; 1352-8661
• DOI: 10.1007/s10334-019-00816-5

Objective Segmentation of thigh muscle and adipose tissue is important for the understanding of musculoskeletal diseases such as osteoarthritis. Therefore, the purpose of this work is (a) to evaluate whether a fully automated approach provides accurate segmentation of muscles and adipose tissue cross-sectional areas (CSA) compared with manual segmentation and (b) to evaluate the validity of this method based on a previous clinical study. Materials and methods The segmentation method is based on U-Net architecture trained on 250 manually segmented thighs from the Osteoarthritis Initiative (OAI). The clinical evaluation is performed on a hold-out test set bilateral thighs of 48 subjects with unilateral knee pain. Results The segmentation time of the method is < 1 s and demonstrated high agreement with the manual method (dice similarity coeffcient: 0.96 ± 0.01). In the clinical study, the automated method shows that similar to manual segmentation (− 5.7 ± 7.9%, p  < 0.001, effect size: 0.69), painful knees display significantly lower quadriceps CSAs than contralateral painless knees (− 5.6 ± 7.6%, p  < 0.001, effect size: 0.73). Discussion Automated segmentation of thigh muscle and adipose tissues has high agreement with manual segmentations and can replicate the effect size seen in a clinical study on osteoarthritic pain.