Purpose. Imaging studies about the relevance of muscles in spinal disorders, and sarcopenia in general, require the segmentation of the muscles in the images which is very labour-intensive if performed manually and poses a practical limit to the number of investigated subjects. This study aimed at developing a deep learning-based tool able to fully automatically perform an accurate segmentation of the lumbar muscles in axial MRI scans, and at validating the new tool on an external dataset. Methods. A set of 60 axial MRI images of the lumbar spine was retrospectively collected from a clinical database. Psoas major, quadratus lumborum, erector spinae, and multifidus were manually segmented in all available slices. The dataset was used to train and validate a deep neural network able to segment muscles automatically. Subsequently, the network was externally validated on images purposely acquired from 22 healthy volunteers. Results. The Jaccard index for the individual muscles calculated for the 22 subjects of the external validation set ranged between 0.862 and 0.935, demonstrating a generally excellent performance of the network. Cross-sectional area and fat fraction of the muscles were in agreement with published data. Conclusions. The externally validated deep neural network was able to perform the segmentation of the paravertebral muscles in axial MRI scans in an accurate and fully automated manner, and is therefore a suitable tool to perform large-scale studies in the field of spinal disorders and sarcopenia, overcoming the limitations of non-automated methods.

Skeletal muscle volume has been mainly investigated under static conditions, i.e. isometric contractions. The aim of our study is to use ultrasound imaging to determine muscle deformation during movement. We used a customdesigned scanning rig to obtain 3D ultrasound images of a subject moving the foot from plantarflexion to dorsiflexion at constant velocity. Using motion capture, we computed the respective angle of the ankle for each frame and collected them in bins based on the measured angle (rounded on the next normal number). For each degree, we used Stradwin for the 3D reconstruction of the respective volume. We found increasing cross-sectional areas for increasing dorsiflexion angles. The proposed method is a promising approach for determining muscle volume during movement. Future studies aim at collecting more data to compute muscle volume and length during contraction and compare the results to isometric measurements.

No abstract