Automatic segmentation of lower limb muscles from MR images of post-menopausal women based on deep learning and data augmentation.

Individual muscle segmentation is the process of partitioning medical images into regions representing each muscle. It can be used to isolate spatially structured quantitative muscle characteristics, such as volume, geometry, and the level of fat infiltration. These features are pivotal to measuring the state of muscle functional health and in tracking the response of the body to musculoskeletal and neuromusculoskeletal disorders. The gold standard approach to perform muscle segmentation requires manual processing of large numbers of images and is associated with significant operator repeatability issues and high time requirements. Deep learning-based techniques have been recently suggested to be capable of automating the process, which would catalyse research into the effects of musculoskeletal disorders on the muscular system. In this study, three convolutional neural networks were explored in their capacity to automatically segment twenty-three lower limb muscles from the hips, thigh, and calves from magnetic resonance images. The three neural networks (UNet, Attention UNet, and a novel Spatial Channel UNet) were trained independently with augmented images to segment 6 subjects and were able to segment the muscles with an average Relative Volume Error (RVE) between -8.6% and 2.9%, average Dice Similarity Coefficient (DSC) between 0.70 and 0.84, and average Hausdorff Distance (HD) between 12.2 and 46.5 mm, with performance dependent on both the subject and the network used. The trained convolutional neural networks designed, and data used in this study are openly available for use, either through re-training for other medical images, or application to automatically segment new T1-weighted lower limb magnetic resonance images captured with similar acquisition parameters.

Automatic segmentation of skeletal muscles from MR images using modified U-Net and a novel data augmentation approach.

Rapid and accurate muscle segmentation is essential for the diagnosis and monitoring of many musculoskeletal diseases. As gold standard, manual annotation suffers from intensive labor and high inter-operator reproducibility errors. In this study, deep learning (DL) based automatic muscle segmentation from MR scans is investigated for post-menopausal women, who normally experience a decline in muscle volume. The performance of four Deep Learning (DL) models was evaluated: U-Net and UNet++ and two modified U-Net networks, which combined feature fusion and attention mechanisms (Feature-Fusion-UNet, FFU, and Attention-Feature-Fusion-UNet, AFFU). The models were tested for automatic segmentation of 16-lower limb muscles from MRI scans of two cohorts of post-menopausal women (11 subjects in PMW-1, 8 subjects in PMW-2; from two different studies so considered independent datasets) and 10 obese post-menopausal women (PMW-OB). Furthermore, a novel data augmentation approach is proposed to enlarge the training dataset. The results were assessed and compared by using the Dice similarity coefficient (DSC), relative volume error (RVE), and Hausdorff distance (HD). The best performance among all four DL models was achieved by AFFU (PMW-1: DSC 0.828 ± 0.079, 1-RVE 0.859 ± 0.122, HD 29.9 mm ± 26.5 mm; PMW-2: DSC 0.833 ± 0.065, 1-RVE 0.873 ± 0.105, HD 25.9 mm ± 27.9 mm; PMW-OB: DSC 0.862 ± 0.048, 1-RVE 0.919 ± 0.076, HD 34.8 mm ± 46.8 mm). Furthermore, the augmentation of data significantly improved the DSC scores of U-Net and AFFU for all 16 tested muscles (between 0.23% and 2.17% (DSC), 1.6%-1.93% (1-RVE), and 9.6%-19.8% (HD) improvement). These findings highlight the feasibility of utilizing DL models for automatic segmentation of muscles in post-menopausal women and indicate that the proposed augmentation method can enhance the performance of models trained on small datasets.

Deformable image registration based on single or multi-atlas methods for automatic muscle segmentation and the generation of augmented imaging datasets.

Muscle segmentation is a process relied upon to gather medical image-based muscle characterisation, useful in directly assessing muscle volume and geometry, that can be used as inputs to musculoskeletal modelling pipelines. Manual or semi-automatic techniques are typically employed to segment the muscles and quantify their properties, but they require significant manual labour and incur operator repeatability issues. In this study an automatic process is presented, aiming to segment all lower limb muscles from Magnetic Resonance (MR) imaging data simultaneously using three-dimensional (3D) deformable image registration (single inputs or multi-atlas). Twenty-three of the major lower limb skeletal muscles were segmented from five subjects, with an average Dice similarity coefficient of 0.72, and average absolute relative volume error (RVE) of 12.7% (average relative volume error of -2.2%) considering the optimal subject combinations. The multi-atlas approach showed slightly better accuracy (average DSC: 0.73; average RVE: 1.67%). Segmented MR imaging datasets of the lower limb are not widely available in the literature, limiting the potential of new, probabilistic methods such as deep learning to be used in the context of muscle segmentation. In this work, Non-linear deformable image registration is used to generate 69 manually checked, segmented, 3D, artificial datasets, allowing access for future studies to use these new methods, with a large amount of reliable reference data.

MRI-based anatomical characterisation of lower-limb muscles in older women.

The ability of muscles to produce force depends, among others, on their anatomical features and it is altered by ageing-associated weakening. However, a clear characterisation of these features, highly relevant for older individuals, is still lacking. This study hence aimed at characterising muscle volume, length, and physiological cross-sectional area (PCSA) and their variability, between body sides and between individuals, in a group of post-menopausal women. Lower-limb magnetic resonance images were acquired from eleven participants (69 (7) y. o., 66.9 (7.7) kg, 159 (3) cm). Twenty-three muscles were manually segmented from the images and muscle volume, length and PCSA were calculated from this dataset. Personalised maximal isometric force was then calculated using the latter information. The percentage difference between the muscles of the two lower limbs was up to 89% and 22% for volume and length, respectively, and up to 84% for PCSA, with no recognisable pattern associated with limb dominance. Between-subject coefficients of variation reached 36% and 13% for muscle volume and length, respectively. Generally, muscle parameters were similar to previous literature, but volumes were smaller than those from in-vivo young adults and slightly higher than ex-vivo ones. Maximal isometric force was found to be on average smaller than those obtained from estimates based on linear scaling of ex-vivo-based literature values. In conclusion, this study quantified for the first time anatomical asymmetry of lower-limb muscles in older women, suggesting that symmetry should not be assumed in this population. Furthermore, we showed that a scaling approach, widely used in musculoskeletal modelling, leads to an overestimation of the maximal isometric force for most muscles. This heavily questions the validity of this approach for older populations. As a solution, the unique dataset of muscle segmentation made available with this paper could support the development of alternative population-based scaling approaches, together with that of automatic tools for muscle segmentation.