The Generalized Log-Ratio Transformation: Learning Shape and Adjacency Priors for Simultaneous Thigh Muscle Segmentation

Validation of musculoskeletal segmentation model with uncertainty estimation for bone and muscle assessment in hip-to-knee clinical CT images

Deep learning-based image segmentation has allowed for the fully automated, accurate, and rapid analysis of musculoskeletal (MSK) structures from medical images. However, current approaches were either applied only to 2D cross-sectional images, addressed few structures, or were validated on small datasets, which limit the application in large-scale databases. This study aimed to validate an improved deep learning model for volumetric MSK segmentation of the hip and thigh with uncertainty estimation from clinical computed tomography (CT) images. Databases of CT images from multiple manufacturers/scanners, disease status, and patient positioning were used. The segmentation accuracy, and accuracy in estimating the structures volume and density, i.e., mean HU, were evaluated. An approach for segmentation failure detection based on predictive uncertainty was also investigated. The model has improved all segmentation accuracy and structure volume/density evaluation metrics compared to a shallower baseline model with a smaller training database (N = 20). The predictive uncertainty yielded large areas under the receiver operating characteristic (AUROC) curves (AUROCs ≥ .95) in detecting inaccurate and failed segmentations. Furthermore, the study has shown an impact of the disease severity status on the model's predictive uncertainties when applied to a large-scale database. The high segmentation and muscle volume/density estimation accuracy and the high accuracy in failure detection based on the predictive uncertainty exhibited the model's reliability for analyzing individual MSK structures in large-scale CT databases.

Topology-preserving segmentation of abdominal muscle layers from ultrasound images

BACKGROUND

In clinical anesthesia, precise segmentation of muscle layers from abdominal ultrasound images is crucial for identifying nerve block locations accurately. Despite deep learning advancements, challenges persist in segmenting muscle layers with accurate topology due to pseudo and weak edges caused by acoustic artifacts in ultrasound imagery.

PURPOSE

To assist anesthesiologists in locating nerve block areas, we have developed a novel deep learning algorithm that can accurately segment muscle layers in abdominal ultrasound images with interference.

METHODS

We propose a comprehensive approach emphasizing the preservation of the segmentation's low-rank property to ensure correct topology. Our methodology integrates a Semantic Feature Extraction (SFE) module for redundant encoding, a Low-rank Reconstruction (LR) module to compress this encoding, and an Edge Reconstruction (ER) module to refine segmentation boundaries. Our evaluation involved rigorous testing on clinical datasets, comparing our algorithm against seven established deep learning-based segmentation methods using metrics such as Mean Intersection-over-Union (MIoU) and Hausdorff distance (HD). Statistical rigor was ensured through effect size quantification with Cliff's Delta, Multivariate Analysis of Variance (MANOVA) for multivariate analysis, and application of the Holm-Bonferroni method for multiple comparisons correction.

RESULTS

We demonstrate that our method outperforms other industry-recognized deep learning approaches on both MIoU and HD metrics, achieving the best outcomes with 88.21%/4.98 (p m a x = 0.1893 $p_{max}=0.1893$ ) on the standard test set and 85.48%/6.98 (p m a x = 0.0448 $p_{max}=0.0448$ ) on the challenging test set. The best&worst results for the other models on the standard test set were (87.20%/5.72)&(83.69%/8.12), and on the challenging test set were (81.25%/10.00)&(71.74%/16.82). Ablation studies further validate the distinct contributions of the proposed modules, which synergistically achieve a balance between maintaining topological integrity and edge precision.

CONCLUSIONS

Our findings validate the effective segmentation of muscle layers with accurate topology in complex ultrasound images, leveraging low-rank constraints. The proposed method not only advances the field of medical imaging segmentation but also offers practical benefits for clinical anesthesia by improving the reliability of nerve block localization.

Bi-Graph Reasoning for Masticatory Muscle Segmentation From Cone-Beam Computed Tomography

Automated segmentation of masticatory muscles is a challenging task considering ambiguous soft tissue attachments and image artifacts of low-radiation cone-beam computed tomography (CBCT) images. In this paper, we propose a bi-graph reasoning model (BGR) for the simultaneous detection and segmentation of multi-category masticatory muscles from CBCTs. The BGR exploits the local and long-range interdependencies of regions of interest and category-specific prior knowledge of masticatory muscles by reasoning on the category graph and the region graph. The category graph of the learnable muscle prior knowledge handles high-level dependencies of muscle categories, enhancing the feature representation with noise-agnostic category knowledge. The region graph models both local and global dependencies of the candidate muscle regions of interest. The proposed BGR accommodates the high-level dependencies and enhances the region features in the presence of entangled soft tissue and image artifacts. We evaluated the proposed approach by segmenting masticatory muscles on clinically acquired CBCTs. Extensive experimental results show that the BGR effectively segments masticatory muscles with state-of-the-art accuracy.

Magnetic resonance imaging assessments for knee segmentation and their use in combination with machine/deep learning as predictors of early osteoarthritis diagnosis and prognosis

Knee osteoarthritis (OA) is a prevalent and disabling disease that can develop over decades. This disease is heterogeneous and involves structural changes in the whole joint, encompassing multiple tissue types. Detecting OA before the onset of irreversible changes is crucial for early management, and this could be achieved by allowing knee tissue visualization and quantifying their changes over time. Although some imaging modalities are available for knee structure assessment, magnetic resonance imaging (MRI) is preferred. This narrative review looks at existing literature, first on MRI-developed approaches for evaluating knee articular tissues, and second on prediction using machine/deep-learning-based methodologies and MRI as input or outcome for early OA diagnosis and prognosis. A substantial number of MRI methodologies have been developed to assess several knee tissues in a semi-quantitative and quantitative fashion using manual, semi-automated and fully automated systems. This dynamic field has grown substantially since the advent of machine/deep learning. Another active area is predictive modelling using machine/deep-learning methodologies enabling robust early OA diagnosis/prognosis. Moreover, incorporating MRI markers as input/outcome in such predictive models is important for a more accurate OA structural diagnosis/prognosis. The main limitation of their usage is the ability to move them in rheumatology practice. In conclusion, MRI knee tissue determination and quantification provide early indicators for individuals at high risk of developing this disease or for patient prognosis. Such assessment of knee tissues, combined with the development of models/tools from machine/deep learning using, in addition to other parameters, MRI markers for early diagnosis/prognosis, will maximize opportunities for individualized risk assessment for use in clinical practice permitting precision medicine. Future efforts should be made to integrate such prediction models into open access, allowing early disease management to prevent or delay the OA outcome.

Intra-operator Repeatability of Manual Segmentations of the Hip Muscles on Clinical Magnetic Resonance Images

The manual segmentation of muscles on magnetic resonance images is the gold standard procedure to reconstruct muscle volumes from medical imaging data and extract critical information for clinical and research purposes. (Semi)automatic methods have been proposed to expedite the otherwise lengthy process. These, however, rely on manual segmentations. Nonetheless, the repeatability of manual muscle volume segmentations performed on clinical MRI data has not been thoroughly assessed. When conducted, volumetric assessments often disregard the hip muscles. Therefore, one trained operator performed repeated manual segmentations (n = 3) of the iliopsoas (n = 34) and gluteus medius (n = 40) muscles on coronal T1-weighted MRI scans, acquired on 1.5 T scanners on a clinical population of patients elected for hip replacement surgery. Reconstructed muscle volumes were divided in sub-volumes and compared in terms of volume variance (normalized variance of volumes - nVV), shape (Jaccard Index-JI) and surface similarity (maximal Hausdorff distance-HD), to quantify intra-operator repeatability. One-way repeated measures ANOVA (or equivalent) tests with Bonferroni corrections for multiple comparisons were conducted to assess statistical significance. For both muscles, repeated manual segmentations were highly similar to one another (nVV: 2-6%, JI > 0.78, HD < 15 mm). However, shape and surface similarity were significantly lower when muscle extremities were included in the segmentations (e.g., iliopsoas: HD -12.06 to 14.42 mm, P < 0.05). Our findings show that the manual segmentation of hip muscle volumes on clinical MRI scans provides repeatable results over time. Nonetheless, extreme care should be taken in the segmentation of muscle extremities.

Validity of Freehand 3-D Ultrasound System in Measurement of the 3-D Surface Shape of Shoulder Muscles

Freehand 3-D ultrasound (3DUS) system is a promising technique for accurately assessing muscle morphology. However, its accuracy has been validated mainly in terms of volume by examining lower limb muscles. This study was aimed at validating 3DUS in the measurements of 3-D surface shape and volume by comparing them with magnetic resonance imaging (MRI) measurements while ensuring the reproducibility of participant posture by focusing on the shoulder muscles. The supraspinatus, infraspinatus and posterior deltoid muscles of 10 healthy men were scanned using 3DUS and MRI while secured by an immobilization support customized for each participant. A 3-D surface model of each muscle was created from the 3DUS and MRI methods, and the agreement between them was assessed. For the muscle volume, the mean difference between the two models was within -0.51 cm³. For the 3-D surface shape, the distances between the closest points of the two models and the Dice similarity coefficient were calculated. The results indicated that the median surface distance was less than 1.12 mm and the Dice similarity coefficient was larger than 0.85. These results suggest that, given the aforementioned error is permitted, 3DUS can be used as an alternative to MRI in measuring volume and surface shape, even for the shoulder muscles.

A hybrid hemodynamic knowledge-powered and feature reconstruction-guided scheme for breast cancer segmentation based on DCE-MRI

Automatically and accurately annotating tumor in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which provides a noninvasive in vivo method to evaluate tumor vasculature architectures based on contrast accumulation and washout, is a crucial step in computer-aided breast cancer diagnosis and treatment. However, it remains challenging due to the varying sizes, shapes, appearances and densities of tumors caused by the high heterogeneity of breast cancer, and the high dimensionality and ill-posed artifacts of DCE-MRI. In this paper, we propose a hybrid hemodynamic knowledge-powered and feature reconstruction-guided scheme that integrates pharmacokinetics prior and feature refinement to generate sufficiently adequate features in DCE-MRI for breast cancer segmentation. The pharmacokinetics prior expressed by time intensity curve (TIC) is incorporated into the scheme through objective function called dynamic contrast-enhanced prior (DCP) loss. It contains contrast agent kinetic heterogeneity prior knowledge, which is important to optimize our model parameters. Besides, we design a spatial fusion module (SFM) embedded in the scheme to exploit intra-slices spatial structural correlations, and deploy a spatial-kinetic fusion module (SKFM) to effectively leverage the complementary information extracted from spatial-kinetic space. Furthermore, considering that low spatial resolution often leads to poor image quality in DCE-MRI, we integrate a reconstruction autoencoder into the scheme to refine feature maps in an unsupervised manner. We conduct extensive experiments to validate the proposed method and show that our approach can outperform recent state-of-the-art segmentation methods on breast cancer DCE-MRI dataset. Moreover, to explore the generalization for other segmentation tasks on dynamic imaging, we also extend the proposed method to brain segmentation in DSC-MRI sequence. Our source code will be released on https://github.com/AI-medical-diagnosis-team-of-JNU/DCEDuDoFNet.

Automatic quadriceps and patellae segmentation of MRI with cascaded U2 -Net and SASSNet deep learning model

PURPOSE

Automatic muscle segmentation is critical for advancing our understanding of human physiology, biomechanics, and musculoskeletal pathologies, as it allows for timely exploration of large multi-dimensional image sets. Segmentation models are rarely developed/validated for the pediatric model. As such, autosegmentation is not available to explore how muscle architectural changes during development and how disease/pathology affects the developing musculoskeletal system. Thus, we aimed to develop and validate an end-to-end, fully automated, deep learning model for accurate segmentation of the rectus femoris and vastus lateral, medialis, and intermedialis using a pediatric database.

METHODS

We developed a two-stage cascaded deep learning model in a coarse-to-fine manner. In the first stage, the U² -Net roughly detects the muscle subcompartment region. Then, in the second stage, the shape-aware 3D semantic segmentation method SASSNet refines the cropped target regions to generate the more finer and accurate segmentation masks. We utilized multifeature image maps in both stages to stabilize performance and validated their use with an ablation study. The second-stage SASSNet was independently run and evaluated with three different cropped region resolutions: the original image resolution, and images downsampled 2× and 4× (high, mid, and low). The relationship between image resolution and segmentation accuracy was explored. In addition, the patella was included as a comparator to past work. We evaluated segmentation accuracy using leave-one-out testing on a database of 3D MR images (0.43 × 0.43 × 2 mm) from 40 pediatric participants (age 15.3 ± 1.9 years, 55.8 ± 11.8 kg, 164.2 ± 7.9 cm, 38F/2 M).

RESULTS

The mid-resolution second stage produced the best results for the vastus medialis, rectus femoris, and patella (Dice similarity coefficient = 95.0%, 95.1%, 93.7%), whereas the low-resolution second stage produced the best results for the vastus lateralis and vastus intermedialis (DSC = 94.5% and 93.7%). In comparing the low- to mid-resolution cases, the vasti intermedialis, vastus medialis, rectus femoris, and patella produced significant differences (p = 0.0015, p = 0.0101, p < 0.0001, p = 0.0003) and the vasti lateralis did not (p = 0.2177). The high-resolution stage 2 had significantly lower accuracy (1.0 to 4.4 dice percentage points) compared to both the mid- and low-resolution routines (p value ranged from < 0.001 to 0.04). The one exception was the rectus femoris, where there was no difference between the low- and high-resolution cases. The ablation study demonstrated that the multifeature is more reliable than the single feature.

CONCLUSIONS

Our successful implementation of this two-stage segmentation pipeline provides a critical tool for expanding pediatric muscle physiology and clinical research. With a relatively small and variable dataset, our fully automatic segmentation technique produces accuracies that matched or exceeded the current state of the art. The two-stage segmentation avoids memory issues and excessive run times by using a first stage focused on cropping out unnecessary data. The excellent Dice similarity coefficients improve upon previous template-based automatic and semiautomatic methodologies targeting the leg musculature. More importantly, with a naturally variable dataset (size, shape, etc.), the proposed model demonstrates slightly improved accuracies, compared to previous neural networks methods.

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

Quantitative MRI combines non-invasive imaging techniques to reveal alterations in muscle pathophysiology. Creating muscle-specific labels manually is time consuming and requires an experienced examiner. Semi-automatic and fully automatic methods reduce segmentation time significantly. Current machine learning solutions are commonly trained on data from healthy subjects using homogeneous databases with the same image contrast. While yielding high Dice scores (DS), those solutions are not applicable to different image contrasts and acquisitions. Therefore, the aim of our study was to evaluate the feasibility of automatic segmentation of a heterogeneous database. To create a heterogeneous dataset, we pooled lower leg muscle images from different studies with different contrasts and fields-of-view, containing healthy controls and diagnosed patients with various neuromuscular diseases. A second homogenous database with uniform contrasts was created as a subset of the first database. We trained three 3D-convolutional neuronal networks (CNN) on those databases to test performance as compared to manual segmentation. All networks, training on heterogeneous data, were able to predict seven muscles with a minimum average DS of 0.75. U-Net performed best when trained on the heterogeneous dataset (DS: 0.80 ± 0.10, AHD: 0.39 ± 0.35). ResNet and DenseNet yielded higher DS, when trained on a heterogeneous dataset (both DS: 0.86), as compared to a homogeneous dataset (ResNet DS: 0.83, DenseNet DS: 0.76). In conclusion, a CNN trained on a heterogeneous dataset achieves more accurate labels for predicting a heterogeneous database of lower leg muscles than a CNN trained on a homogenous dataset. We propose that a large heterogeneous database is needed, to make automated segmentation feasible for different kinds of image acquisitions.

Deep generative models for automated muscle segmentation in computed tomography scanning

Accurate gluteus medius (GMd) volume evaluation may aid in the analysis of muscular atrophy states and help gain an improved understanding of patient recovery via rehabilitation. However, the segmentation of muscle regions in GMd images for cubic muscle volume assessment is time-consuming and labor-intensive. This study automated GMd-region segmentation from the computed tomography (CT) images of patients diagnosed with hip osteoarthritis using deep learning and evaluated the segmentation accuracy. To this end, 5250 augmented pairs of training data were obtained from five participants, and a conditional generative adversarial network was used to identify the relationships between the image pairs. Using the preserved test datasets, the results of automatic segmentation with the trained deep learning model were compared to those of manual segmentation in terms of the dice similarity coefficient (DSC), volume similarity (VS), and shape similarity (MS). As observed, the average DSC values for automatic and manual segmentations were 0.748 and 0.812, respectively, with a significant difference (p < 0.0001); the average VS values were 0.247 and 0.203, respectively, with no significant difference (p = 0.069); and the average MS values were 1.394 and 1.156, respectively, with no significant difference (p = 0.308). The GMd volumes obtained by automatic and manual segmentation were 246.2 cm³ and 282.9 cm³, respectively. The noninferiority of the DSC obtained by automatic segmentation was verified against that obtained by manual segmentation. Accordingly, the proposed GAN-based automatic GMd-segmentation technique is confirmed to be noninferior to manual segmentation. Therefore, the findings of this research confirm that the proposed method not only reduces time and effort but also facilitates accurate assessment of the cubic muscle volume.

Overview of MR Image Segmentation Strategies in Neuromuscular Disorders

Neuromuscular disorders are rare diseases for which few therapeutic strategies currently exist. Assessment of therapeutic strategies efficiency is limited by the lack of biomarkers sensitive to the slow progression of neuromuscular diseases (NMD). Magnetic resonance imaging (MRI) has emerged as a tool of choice for the development of qualitative scores for the study of NMD. The recent emergence of quantitative MRI has enabled to provide quantitative biomarkers more sensitive to the evaluation of pathological changes in muscle tissue. However, in order to extract these biomarkers from specific regions of interest, muscle segmentation is mandatory. The time-consuming aspect of manual segmentation has limited the evaluation of these biomarkers on large cohorts. In recent years, several methods have been proposed to make the segmentation step automatic or semi-automatic. The purpose of this study was to review these methods and discuss their reliability, reproducibility, and limitations in the context of NMD. A particular attention has been paid to recent deep learning methods, as they have emerged as an effective method of image segmentation in many other clinical contexts.

Healthy versus pathological learning transferability in shoulder muscle MRI segmentation using deep convolutional encoder-decoders

Fully-automated segmentation of pathological shoulder muscles in patients with musculo-skeletal diseases is a challenging task due to the huge variability in muscle shape, size, location, texture and injury. A reliable automatic segmentation method from magnetic resonance images could greatly help clinicians to diagnose pathologies, plan therapeutic interventions and predict interventional outcomes while eliminating time consuming manual segmentation. The purpose of this work is three-fold. First, we investigate the feasibility of automatic pathological shoulder muscle segmentation using deep learning techniques, given a very limited amount of available annotated pediatric data. Second, we address the learning transferability from healthy to pathological data by comparing different learning schemes in terms of model generalizability. Third, extended versions of deep convolutional encoder-decoder architectures using encoders pre-trained on non-medical data are proposed to improve the segmentation accuracy. Methodological aspects are evaluated in a leave-one-out fashion on a dataset of 24 shoulder examinations from patients with unilateral obstetrical brachial plexus palsy and focus on 4 rotator cuff muscles (deltoid, infraspinatus, supraspinatus and subscapularis). The most accurate segmentation model is partially pre-trained on the large-scale ImageNet dataset and jointly exploits inter-patient healthy and pathological annotated data. Its performance reaches Dice scores of 82.4%, 82.0%, 71.0% and 82.8% for deltoid, infraspinatus, supraspinatus and subscapularis muscles. Absolute surface estimation errors are all below 83 mm² except for supraspinatus with 134.6 mm². The contributions of our work offer new avenues for inferring force from muscle volume in the context of musculo-skeletal disorder management.

A Knowledge-Based Modality-Independent Technique for Concurrent Thigh Muscle Segmentation: Applicable to CT and MR Images

The mass of the lower extremity muscles is a clinically significant metric. Manual segmentation of these muscles is a time-consuming task. Most of the segmentation methods for the thigh muscles are based on statistical models and atlases which need manually segmented datasets. The goal of this work is an automatic segmentation of the thigh muscles with only one initial segmented slice. A new automatic method is proposed for concurrent individual thigh muscles segmentation using a hybrid level set method and anatomical information of the muscles. In the proposed method, the muscle regions are extracted by the Fast and Robust Fuzzy C-Means Clustering (FRFCM) method, and then a contour is determined for each muscle which changes according to the muscle shape variation through its length. The anatomical information is used to control the contours variations and to refine the final boundaries. The method was validated by 22 CT datasets. The average dice similarity coefficient (DSC) of the method for individual muscle segmentation with one and two initial slices were 89.29 ± 2.59 (%) and 91.77 ± 1.87 (%), respectively. Also, the average symmetric surface distances (ASSDs) were 0.93 ± 0.29 mm and 0.64 ± 0.18 mm. Furthermore, applying to ten MRI datasets, the average DSC and ASSD for muscles were 90.9 ± 2.61 (%) and 0.71 ± 0.33 mm, respectively. The quantitative and intuitive results of the proposed method show the effectiveness of this method in segmentation of large and small muscles in CT and MR images. The consumed computation time is lower than the previous works, and this method does not need any training datasets.

ERGO: Efficient Recurrent Graph Optimized Emitter Density Estimation in Single Molecule Localization Microscopy

Single molecule localization microscopy (SMLM) allows unprecedented insight into the three-dimensional organization of proteins at the nanometer scale. The combination of minimal invasive cell imaging with high resolution positions SMLM at the forefront of scientific discovery in cancer, infectious, and degenerative diseases. By stochastic temporal and spatial separation of light emissions from fluorescent labelled proteins, SMLM is capable of nanometer scale reconstruction of cellular structures. Precise localization of proteins in 3D astigmatic SMLM is dependent on parameter sensitive preprocessing steps to select regions of interest. With SMLM acquisition highly variable over time, it is non-trivial to find an optimal static parameter configuration. The high emitter density required for reconstruction of complex protein structures can compromise accuracy and introduce artifacts. To address these problems, we introduce two modular auto-tuning pre-processing methods: adaptive signal detection and learned recurrent signal density estimation that can leverage the information stored in the sequence of frames that compose the SMLM acquisition process. We show empirically that our contributions improve accuracy, precision and recall with respect to the state of the art. Both modules auto-tune their hyper-parameters to reduce the parameter space for practitioners, improve robustness and reproducibility, and are validated on a reference in silico dataset. Adaptive signal detection and density prediction can offer a practitioner, in addition to informed localization, a tool to tune acquisition parameters ensuring improved reconstruction of the underlying protein complex. We illustrate the challenges faced by practitioners in applying SMLM algorithms on real world data markedly different from the data used in development and show how ERGO can be run on new datasets without retraining while motivating the need for robust transfer learning in SMLM.

Automated Muscle Segmentation from Clinical CT Using Bayesian U-Net for Personalized Musculoskeletal Modeling

We propose a method for automatic segmentation of individual muscles from a clinical CT. The method uses Bayesian convolutional neural networks with the U-Net architecture, using Monte Carlo dropout that infers an uncertainty metric in addition to the segmentation label. We evaluated the performance of the proposed method using two data sets: 20 fully annotated CTs of the hip and thigh regions and 18 partially annotated CTs that are publicly available from The Cancer Imaging Archive (TCIA) database. The experiments showed a Dice coefficient (DC) of 0.891±0.016 (mean±std) and an average symmetric surface distance (ASD) of 0.994±0.230 mm over 19 muscles in the set of 20 CTs. These results were statistically significant improvements compared to the state-of-the-art hierarchical multi-atlas method which resulted in 0.845 ± 0.031 DC and 1.556 ± 0.444 mm ASD. We evaluated validity of the uncertainty metric in the multi-class organ segmentation problem and demonstrated a correlation between the pixels with high uncertainty and the segmentation failure. One application of the uncertainty metric in active-learning is demonstrated, and the proposed query pixel selection method considerably reduced the manual annotation cost for expanding the training data set. The proposed method allows an accurate patient-specific analysis of individual muscle shapes in a clinical routine. This would open up various applications including personalization of biomechanical simulation and quantitative evaluation of muscle atrophy.

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

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.

Automatic segmentation of all lower limb muscles from high-resolution magnetic resonance imaging using a cascaded three-dimensional deep convolutional neural network

High-resolution magnetic resonance imaging with fat suppression can obtain accurate anatomical information of all 35 lower limb muscles and individual segmentation can facilitate quantitative analysis. However, due to limited contrast and edge information, automatic segmentation of the muscles is very challenging, especially for athletes whose muscles are all well developed and more compact than the average population. Deep convolutional neural network (DCNN)-based segmentation methods showed great promise in many clinical applications, however, a direct adoption of DCNN to lower limb muscle segmentation is challenged by the large three-dimensional (3-D) image size and lack of the direct usage of muscle location information. We developed a cascaded 3-D DCNN model with the first step to localize each muscle using low-resolution images and the second step to segment it using cropped high-resolution images with individually trained networks. The workflow was optimized to account for different characteristics of each muscle for improved accuracy and reduced training and testing time. A testing augmentation technique was proposed to smooth the segmentation contours. The segmentation performance of 14 muscles was within interobserver variability and 21 were slightly worse than humans.

Novel stochastic framework for automatic segmentation of human thigh MRI volumes and its applications in spinal cord injured individuals

Severe spinal cord injury (SCI) leads to skeletal muscle atrophy and adipose tissue infiltration in the skeletal muscle, which can result in compromised muscle mechanical output and lead to health-related complications. In this study, we developed a novel automatic 3-D approach for volumetric segmentation and quantitative assessment of thigh Magnetic Resonance Imaging (MRI) volumes in individuals with chronic SCI as well as non-disabled individuals. In this framework, subcutaneous adipose tissue, inter-muscular adipose tissue and total muscle tissue are segmented using linear combination of discrete Gaussians algorithm. Also, three thigh muscle groups were segmented utilizing the proposed 3-D Joint Markov Gibbs Random Field model that integrates first order appearance model, spatial information, and shape model to localize the muscle groups. The accuracy of the automatic segmentation method was tested both on SCI (N = 16) and on non-disabled (N = 14) individuals, showing an overall 0.93±0.06 accuracy for adipose tissue and muscle compartments segmentation based on Dice Similarity Coefficient. The proposed framework for muscle compartment segmentation showed an overall higher accuracy compared to ANTs and STAPLE, two previously validated atlas-based segmentation methods. Also, the framework proposed in this study showed similar Dice accuracy and better Hausdorff distance measure to that obtained using DeepMedic Convolutional Neural Network structure, a well-known deep learning network for 3-D medical image segmentation. The automatic segmentation method proposed in this study can provide fast and accurate quantification of adipose and muscle tissues, which have important health and functional implications in the SCI population.

Quantifying skeletal muscle volume and shape in humans using MRI: A systematic review of validity and reliability

AIMS

The aim of this study was to report the metrological qualities of techniques currently used to quantify skeletal muscle volume and 3D shape in healthy and pathological muscles.

METHODS

A systematic review was conducted (Prospero CRD42018082708). PubMed, Web of Science, Cochrane and Scopus databases were searched using relevant keywords and inclusion/exclusion criteria. The quality of the articles was evaluated using a customized scale.

RESULTS

Thirty articles were included, 6 of which included pathological muscles. Most evaluated lower limb muscles. Partially or completely automatic and manual techniques were assessed in 10 and 24 articles, respectively. Manual slice-by-slice segmentation reliability was good-to-excellent (n = 8 articles) and validity against dissection was moderate to good(n = 1). Manual slice-by-slice segmentation was used as a gold-standard method in the other articles. Reduction of the number of manually segmented slices (n = 6) provided good to excellent validity if a sufficient number of appropriate slices was chosen. Segmentation on one slice (n = 11) increased volume errors. The Deformation of a Parametric Specific Object (DPSO) method (n = 5) decreased the number of manually-segmented slices required for any chosen level of error. Other automatic techniques combined with different statistical shape or atlas/images-based methods (n = 4) had good validity. Some particularities were highlighted for specific muscles. Except for manual slice by slice segmentation, reliability has rarely been reported.

CONCLUSIONS

The results of this systematic review help the choice of appropriate segmentation techniques, according to the purpose of the measurement. In healthy populations, techniques that greatly simplified the process of manual segmentation yielded greater errors in volume and shape estimations. Reduction of the number of manually segmented slices was possible with appropriately chosen segmented slices or with DPSO. Other automatic techniques showed promise, but data were insufficient for their validation. More data on the metrological quality of techniques used in the cases of muscle pathology are required.

MRI adipose tissue and muscle composition analysis-a review of automation techniques

MRI is becoming more frequently used in studies involving measurements of adipose tissue and volume and composition of skeletal muscles. The large amount of data generated by MRI calls for automated analysis methods. This review article presents a summary of automated and semi-automated techniques published between 2013 and 2017. Technical aspects and clinical applications for MRI-based adipose tissue and muscle composition analysis are discussed based on recently published studies. The conclusion is that very few clinical studies have used highly automated analysis methods, despite the rapidly increasing use of MRI for body composition analysis. Possible reasons for this are that the availability of highly automated methods has been limited for non-imaging experts, and also that there is a limited number of studies investigating the reproducibility of automated methods for MRI-based body composition analysis.

A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation

Magnetic resonance imaging (MRI) is the non-invasive modality of choice for body tissue composition analysis due to its excellent soft-tissue contrast and lack of ionizing radiation. However, quantification of body composition requires an accurate segmentation of fat, muscle, and other tissues from MR images, which remains a challenging goal due to the intensity overlap between them. In this study, we propose a fully automated, data-driven image segmentation platform that addresses multiple difficulties in segmenting MR images such as varying inhomogeneity, non-standardness, and noise, while producing a high-quality definition of different tissues. In contrast to most approaches in the literature, we perform segmentation operation by combining three different MRI contrasts and a novel segmentation tool, which takes into account variability in the data. The proposed system, based on a novel affinity definition within the fuzzy connectivity image segmentation family, prevents the need for user intervention and reparametrization of the segmentation algorithms. In order to make the whole system fully automated, we adapt an affinity propagation clustering algorithm to roughly identify tissue regions and image background. We perform a thorough evaluation of the proposed algorithm's individual steps as well as comparison with several approaches from the literature for the main application of muscle/fat separation. Furthermore, whole-body tissue composition and brain tissue delineation were conducted to show the generalization ability of the proposed system. This new automated platform outperforms other state-of-the-art segmentation approaches both in accuracy and efficiency.

Thigh muscle segmentation of chemical shift encoding-based water-fat magnetic resonance images: The reference database MyoSegmenTUM

Magnetic resonance imaging (MRI) can non-invasively assess muscle anatomy, exercise effects and pathologies with different underlying causes such as neuromuscular diseases (NMD). Quantitative MRI including fat fraction mapping using chemical shift encoding-based water-fat MRI has emerged for reliable determination of muscle volume and fat composition. The data analysis of water-fat images requires segmentation of the different muscles which has been mainly performed manually in the past and is a very time consuming process, currently limiting the clinical applicability. An automatization of the segmentation process would lead to a more time-efficient analysis. In the present work, the manually segmented thigh magnetic resonance imaging database MyoSegmenTUM is presented. It hosts water-fat MR images of both thighs of 15 healthy subjects and 4 patients with NMD with a voxel size of 3.2x2x4 mm³ with the corresponding segmentation masks for four functional muscle groups: quadriceps femoris, sartorius, gracilis, hamstrings. The database is freely accessible online at https://osf.io/svwa7/?view_only=c2c980c17b3a40fca35d088a3cdd83e2. The database is mainly meant as ground truth which can be used as training and test dataset for automatic muscle segmentation algorithms. The segmentation allows extraction of muscle cross sectional area (CSA) and volume. Proton density fat fraction (PDFF) of the defined muscle groups from the corresponding images and quadriceps muscle strength measurements/neurological muscle strength rating can be used for benchmarking purposes.

Advanced body composition assessment: from body mass index to body composition profiling

This paper gives a brief overview of common non-invasive techniques for body composition analysis and a more in-depth review of a body composition assessment method based on fat-referenced quantitative MRI. Earlier published studies of this method are summarized, and a previously unpublished validation study, based on 4753 subjects from the UK Biobank imaging cohort, comparing the quantitative MRI method with dual-energy X-ray absorptiometry (DXA) is presented. For whole-body measurements of adipose tissue (AT) or fat and lean tissue (LT), DXA and quantitative MRIs show excellent agreement with linear correlation of 0.99 and 0.97, and coefficient of variation (CV) of 4.5 and 4.6 per cent for fat (computed from AT) and LT, respectively, but the agreement was found significantly lower for visceral adipose tissue, with a CV of >20 per cent. The additional ability of MRI to also measure muscle volumes, muscle AT infiltration and ectopic fat, in combination with rapid scanning protocols and efficient image analysis tools, makes quantitative MRI a powerful tool for advanced body composition assessment.

Automated muscle segmentation from CT images of the hip and thigh using a hierarchical multi-atlas method

PURPOSE

Patient-specific quantitative assessments of muscle mass and biomechanical musculoskeletal simulations require segmentation of the muscles from medical images. The objective of this work is to automate muscle segmentation from CT data of the hip and thigh.

METHOD

We propose a hierarchical multi-atlas method in which each hierarchy includes spatial normalization using simpler pre-segmented structures in order to reduce the inter-patient variability of more complex target structures.

RESULTS

The proposed hierarchical method was evaluated with 19 muscles from 20 CT images of the hip and thigh using the manual segmentation by expert orthopedic surgeons as ground truth. The average symmetric surface distance was significantly reduced in the proposed method (1.53 mm) in comparison with the conventional method (2.65 mm).

CONCLUSION

We demonstrated that the proposed hierarchical multi-atlas method improved the accuracy of muscle segmentation from CT images, in which large inter-patient variability and insufficient contrast were involved.

Validation of an active shape model-based semi-automated segmentation algorithm for the analysis of thigh muscle and adipose tissue cross-sectional areas

Objective

To validate a semi-automated method for thigh muscle and adipose tissue cross-sectional area (CSA) segmentation from MRI.

Materials and methods

An active shape model (ASM) was trained using 113 MRI CSAs from the Osteoarthritis Initiative (OAI) and combined with an active contour model and thresholding-based post-processing steps. This method was applied to 20 other MRIs from the OAI and to baseline and follow-up MRIs from a 12-week lower-limb strengthening or endurance training intervention (n = 35 females). The agreement of semi-automated vs. previous manual segmentation was assessed using the Dice similarity coefficient and Bland-Altman analyses. Longitudinal changes observed in the training intervention were compared between semi-automated and manual segmentations.

Results

High agreement was observed between manual and semi-automated segmentations for subcutaneous fat, quadriceps and hamstring CSAs. With strength training, both the semi-automated and manual segmentation method detected a significant reduction in adipose tissue CSA and a significant gain in quadriceps, hamstring and adductor CSAs. With endurance training, a significant reduction in adipose tissue CSAs was observed with both methods.

Conclusion

The semi-automated approach showed high agreement with manual segmentation of thigh muscle and adipose tissue CSAs and showed longitudinal training effects similar to that observed using manual segmentation.

Electronic supplementary material

The online version of this article (doi:10.1007/s10334-017-0622-3) contains supplementary material, which is available to authorized users.