Spinal Segmentation Research Articles

Spine and Individual Vertebrae Segmentation in Computed Tomography Images Using Geometric Flows and Shape Priors

The surgical treatment of injuries to the spine often requires the placement of pedicle screws. To prevent damage to nearby blood vessels and nerves, the individual vertebrae and their surrounding tissue must be precisely localized. To aid surgical planning in this context we present a clinically applicable geometric flow based method to segment the human spinal column from computed tomography (CT) scans. We first apply anisotropic diffusion and flux computation to mitigate the effects of region inhomogeneities and partial volume effects at vertebral boundaries in such data. The first pipeline of our segmentation approach uses a region-based geometric flow, requires only a single manually identified seed point to initiate, and runs efficiently on a multi-core central processing unit (CPU). A shape-prior formulation is employed in a separate second pipeline to segment individual vertebrae, using both region and boundary based terms to augment the initial segmentation. We validate our method on four different clinical databases, each of which has a distinct intensity distribution. Our approach obviates the need for manual segmentation, significantly reduces inter- and intra-observer differences, runs in times compatible with use in a clinical workflow, achieves Dice scores that are comparable to the state of the art, and yields precise vertebral surfaces that are well within the acceptable 2 mm mark for surgical interventions.

The measurement of Cobb angle based on spine X-ray images using multi-scale convolutional neural network.

Adolescent idiopathic scoliosis (AIS) is a structural spinal deformity mainly in the coronal plane and is among the most frequent deformities in children, adolescents, and young adults, with an overall prevalence of 0.47-5.2%. The Cobb angle is an objective measure to determine the progression of deformity and plays a critical role in the planning of surgical treatment. However, existing studies suggested that Cobb angle measurement is susceptible to inter- and intra-observer variability, as well as a high variability in the definition of the end vertebra. In this study, we proposed an automatic method for the spine vertebrae segmentation using Deeplab V3+, a powerful tool that has shown success in the image segmentation of other anatomical regions but spine, and Cobb angle measurement. The segmentation performance was compared to existing mainstay neural networks. Compared to U-Net, Residual U-Net and Dilated U-Net, our method using Deeplab V3+ showed the best performance in the Dice Similarity Coefficient (DSC), accuracy, sensitivity and Jaccard Index. An excellent correlation in the final Cobb angle calculation was achieved between the smallest distance point (SDP) method and two experts (> 0.95), with a small error in the angle estimation compared (MAE < 3°). The proposed method could provide a potential tool for the automatic estimation of the Cobb angle to improve the efficiency and accuracy of the treatment workflow for AIS.

Autonomous lumbar spine pedicle screw planning using machine learning: A validation study.

Introduction:Several techniques for pedicle screw placement have been described including freehand techniques, fluoroscopy assisted, computed tomography (CT) guidance, and robotics. Image-guided surgery offers the potential to combine the benefits of CT guidance without the added radiation. This study investigated the ability of a neural network to place lumbar pedicle screws with the correct length, diameter, and angulation autonomously within radiographs without the need for human involvement.Materials and Methods:The neural network was trained using a machine learning process. The method combines the previously reported autonomous spine segmentation solution with a landmark localization solution. The pedicle screw placement was evaluated using the Zdichavsky, Ravi, and Gertzbein grading systems.Results:In total, the program placed 208 pedicle screws between the L1 and S1 spinal levels. Of the 208 placed pedicle screws, 208 (100%) had a Zdichavsky Score 1A, 206 (99.0%) of all screws were Ravi Grade 1, and Gertzbein Grade A indicating no breech. The final two screws (1.0%) had a Ravi score of 2 (<2 mm breech) and a Gertzbein grade of B (<2 mm breech).Conclusion:The results of this experiment can be combined with an image-guided platform to provide an efficient and highly effective method of placing pedicle screws during spinal stabilization surgery.

Segmentation and Identification of Vertebrae in CT Scans Using CNN, k-Means Clustering and k-NN

The accurate segmentation and identification of vertebrae presents the foundations for spine analysis including fractures, malfunctions and other visual insights. The large-scale vertebrae segmentation challenge (VerSe), organized as a competition at the Medical Image Computing and Computer Assisted Intervention (MICCAI), is aimed at vertebrae segmentation and labeling. In this paper, we propose a framework that addresses the tasks of vertebrae segmentation and identification by exploiting both deep learning and classical machine learning methodologies. The proposed solution comprises two phases: a binary fully automated segmentation of the whole spine, which exploits a 3D convolutional neural network, and a semi-automated procedure that allows locating vertebrae centroids using traditional machine learning algorithms. Unlike other approaches, the proposed method comes with the added advantage of no requirement for single vertebrae-level annotations to be trained. A dataset of 214 CT scans has been extracted from VerSe’20 challenge data, for training, validating and testing the proposed approach. In addition, to evaluate the robustness of the segmentation and labeling algorithms, 12 CT scans from subjects affected by severe, moderate and mild scoliosis have been collected from a local medical clinic. On the designated test set from Verse’20 data, the binary spine segmentation stage allowed to obtain a binary Dice coefficient of 89.17%, whilst the vertebrae identification one reached an average multi-class Dice coefficient of 90.09%. In order to ensure the reproducibility of the algorithms hereby developed, the code has been made publicly available.

Exploiting Global Structure Information to Improve Medical Image Segmentation.

In this paper, we propose a method to enhance the performance of segmentation models for medical images. The method is based on convolutional neural networks that learn the global structure information, which corresponds to anatomical structures in medical images. Specifically, the proposed method is designed to learn the global boundary structures via an autoencoder and constrain a segmentation network through a loss function. In this manner, the segmentation model performs the prediction in the learned anatomical feature space. Unlike previous studies that considered anatomical priors by using a pre-trained autoencoder to train segmentation networks, we propose a single-stage approach in which the segmentation network and autoencoder are jointly learned. To verify the effectiveness of the proposed method, the segmentation performance is evaluated in terms of both the overlap and distance metrics on the lung area and spinal cord segmentation tasks. The experimental results demonstrate that the proposed method can enhance not only the segmentation performance but also the robustness against domain shifts.

Spinal Cord MRI Segmentation Techniques and Algorithms: A Survey

Spinal Cord MRI Segmentation Techniques and Algorithms: A Survey

Deep neural network for automated simultaneous intervertebral disc (IVDs) identification and segmentation of multi-modal MR images

Background and objective: Lower back pain in humans has become a major risk. Classical approaches follow a non-invasive imaging technique for the assessment of spinal intervertebral disc (IVDs) abnormalities, where identification and segmentation of discs are done separately, making it a time-consuming phenomenon. This necessitates designing a robust automated and simultaneous IVDs identification and segmentation of multi-modality MRI images.Methods: We introduced a novel deep neural network architecture coined as ‘RIMNet’, a Region-to-Image Matching Network model, capable of performing an automated and simultaneous IVDs identification and segmentation of MRI images. The multi-modal input data is being fed to the network with a dropout strategy, by randomly disabling modalities in mini-batches. The performance accuracy as a function of the testing dataset was determined. The execution of the deep neural network model was evaluated by computing the IVDs Identification Accuracy, Dice coefficient, MDOC, Average Symmetric Surface Distance, Jaccard Coefficient, Hausdorff Distance and F1 Score.Results:Proposed model has attained 94% identification accuracy, dice coefficient value of 91.7±1% in segmentation and MDOC 90.2±1%. Our model also achieved 0.87±0.02 for Jaccard Coefficient, 0.54±0.04 for ASD and 0.62±0.02 mm Hausdorff Distance. The results have been validated and compared with other methodologies on dataset of MICCAI IVD 2018 challenge.Conclusions: Our proposed deep-learning methodology is capable of performing simultaneous identification and segmentation on IVDs MRI images of the human spine with high accuracy.

Automatic spinal cord segmentation from axial-view MRI slices using CNN with grayscale regularized active contour propagation

Accurate positioning of the responsible segment for patients with cervical spondylotic myelopathy (CSM) is clinically important not only to the surgery but also to reduce the incidence of surgical trauma and complications. Spinal cord segmentation is a crucial step in the positioning procedure. This study proposed a fully automated approach for spinal cord segmentation from 2D axial-view MRI slices of patients with CSM. The proposed method was trained and tested using clinical data from 20 CSM patients (359 images) acquired by the Peking University Third Hospital, with ground truth labeled by professional radiologists. The accuracy of the proposed method was evaluated using quantitative measures, the reliability metric as well as visual assessment. The proposed method yielded a Dice coefficient of 87.0%, Hausdorff distance of 9.7 mm, root-mean-square error of 5.9 mm. Higher conformance with ground truth was observed for the proposed method in comparison to the state-of-the-art algorithms. The results are also statistically significant with p-values calculated between state-of-the-art methods and the proposed methods.

Research on multi-path dense networks for MRI spinal segmentation.

Accurate and robust segmentation of anatomical structures from magnetic resonance images is valuable in many computer-aided clinical tasks. Traditional codec networks are not satisfactory because of their low accuracy of edge segmentation, the low recognition rate of the target, and loss of detailed information. To address these problems, this study proposes a series of improved models for semantic segmentation and progressively optimizes them from the three aspects of convolution module, codec unit, and feature fusion. Instead of the standard convolution structure, we apply a new type of convolution module for the feature extraction. The networks integrate a multi-path method to obtain richer-detail edge information. Finally, a dense network is utilized to strengthen the ability of the feature fusion and integrate more different-level information. The evaluation of the Accuracy, Dice coefficient, and Jaccard index led to values of 0.9855, 0.9185, and 0.8507, respectively. These metrics of the best network increased by 1.0%, 4.0%, and 6.1%, respectively. Boundary F1-Score reached 0.9124 indicating that the proposed networks can segment smaller targets to obtain smoother edges. Our methods obtain more key information than traditional methods and achieve superiority in segmentation performance.

Automatic lumbar spinal MRI image segmentation with a multi-scale attention network.

Lumbar spinal stenosis (LSS) is a lumbar disease with a high incidence in recent years. Accurate segmentation of the vertebral body, lamina and dural sac is a key step in the diagnosis of LSS. This study presents an lumbar spine magnetic resonance imaging image segmentation method based on deep learning. In addition, we define the quantitative evaluation methods of two clinical indicators (that is the anteroposterior diameter of the spinal canal and the cross-sectional area of the dural sac) to assist LSS diagnosis. To improve the segmentation performance, a dual-branch multi-scale attention module is embedded into the network. It contains multi-scale feature extraction based on three 3 × 3 convolution operators and vital information selection based on attention mechanism. In the experiment, we used lumbar datasets from the spine surgery department of Shengjing Hospital of China Medical University to evaluate the effect of the method embedded the dual-branch multi-scale attention module. Compared with other state-of-the-art methods, the average dice similarity coefficient was improved from 0.9008 to 0.9252 and the average surface distance was decreased from 6.40 to 2.71 mm.

Visualization of Human Spine Biomechanics for Spinal Surgery.

We propose a visualization application, designed for the exploration of human spine simulation data. Our goal is to support research in biomechanical spine simulation and advance efforts to implement simulation-backed analysis in surgical applications. Biomechanical simulation is a state-of-the-art technique for analyzing load distributions of spinal structures. Through the inclusion of patient-specific data, such simulations may facilitate personalized treatment and customized surgical interventions. Difficulties in spine modelling and simulation can be partly attributed to poor result representation, which may also be a hindrance when introducing such techniques into a clinical environment. Comparisons of measurements across multiple similar anatomical structures and the integration of temporal data make commonly available diagrams and charts insufficient for an intuitive and systematic display of results. Therefore, we facilitate methods such as multiple coordinated views, abstraction and focus and context to display simulation outcomes in a dedicated tool. By linking the result data with patient-specific anatomy, we make relevant parameters tangible for clinicians. Furthermore, we introduce new concepts to show the directions of impact force vectors, which were not accessible before. We integrated our toolset into a spine segmentation and simulation pipeline and evaluated our methods with both surgeons and biomechanical researchers. When comparing our methods against standard representations that are currently in use, we found increases in accuracy and speed in data exploration tasks. in a qualitative review, domain experts deemed the tool highly useful when dealing with simulation result data, which typically combines time-dependent patient movement and the resulting force distributions on spinal structures.

Opportunistic Osteoporosis Screening Reveals Low Bone Density in Patients With Screw Loosening After Lumbar Semi-Rigid Instrumentation: A Case-Control Study.

ObjectiveDecreased bone mineral density (BMD) impairs screw purchase in trabecular bone and can cause screw loosening following spinal instrumentation. Existing computed tomography (CT) scans could be used for opportunistic osteoporosis screening for decreased BMD. Purpose of this case-control study was to investigate the association of opportunistically assessed BMD with the outcome after spinal surgery with semi-rigid instrumentation for lumbar degenerative instability.MethodsWe reviewed consecutive patients that had primary surgery with semi-rigid instrumentation in our hospital. Patients that showed screw loosening in follow-up imaging qualified as cases. Patients that did not show screw loosening or—if no follow-up imaging was available (n = 8)—reported benefit from surgery ≥ 6 months after primary surgery qualified as controls. Matching criteria were sex, age, and surgical construct. Opportunistic BMD screening was performed at L1 to L4 in perioperative CT scans by automatic spine segmentation and using asynchronous calibration. Processing steps of this deep learning-driven approach can be reproduced using the freely available online-tool Anduin (https://anduin.bonescreen.de). Area under the curve (AUC) was calculated for BMD as a predictor of screw loosening.ResultsForty-six elderly patients (69.9 ± 9.1 years)—23 cases and 23 controls—were included. The majority of surgeries involved three spinal motion segments (n = 34). Twenty patients had low bone mass and 13 had osteoporotic BMD. Cases had significantly lower mean BMD (86.5 ± 29.5 mg/cm³) compared to controls (118.2 ± 32.9 mg/cm³, p = 0.001), i.e. patients with screw loosening showed reduced BMD. Screw loosening was best predicted by a BMD < 81.8 mg/cm³ (sensitivity = 91.3%, specificity = 56.5%, AUC = 0.769, p = 0.002).ConclusionPrevalence of osteoporosis or low bone mass (BMD ≤ 120 mg/cm³) was relatively high in this group of elderly patients undergoing spinal surgery. Screw loosening was associated with BMD close to the threshold for osteoporosis (< 80 mg/cm³). Opportunistic BMD screening is feasible using the presented approach and can guide the surgeon to take measures to prevent screw loosening and to increase favorable outcomes.

Automatic multiclass intramedullary spinal cord tumor segmentation on MRI with deep learning

Spinal cord tumors lead to neurological morbidity and mortality. Being able to obtain morphometric quantification (size, location, growth rate) of the tumor, edema, and cavity can result in improved monitoring and treatment planning. Such quantification requires the segmentation of these structures into three separate classes. However, manual segmentation of three-dimensional structures is time consuming, tedious and prone to intra- and inter-rater variability, motivating the development of automated methods. Here, we tailor a model adapted to the spinal cord tumor segmentation task. Data were obtained from 343 patients using gadolinium-enhanced T1-weighted and T2-weighted MRI scans with cervical, thoracic, and/or lumbar coverage. The dataset includes the three most common intramedullary spinal cord tumor types: astrocytomas, ependymomas, and hemangioblastomas. The proposed approach is a cascaded architecture with U-Net-based models that segments tumors in a two-stage process: locate and label. The model first finds the spinal cord and generates bounding box coordinates. The images are cropped according to this output, leading to a reduced field of view, which mitigates class imbalance. The tumor is then segmented. The segmentation of the tumor, cavity, and edema (as a single class) reached 76.7 ± 1.5% of Dice score and the segmentation of tumors alone reached 61.8 ± 4.0% Dice score. The true positive detection rate was above 87% for tumor, edema, and cavity. To the best of our knowledge, this is the first fully automatic deep learning model for spinal cord tumor segmentation. The multiclass segmentation pipeline is available in the Spinal Cord Toolbox (https://spinalcordtoolbox.com/). It can be run with custom data on a regular computer within seconds.

Semi-automated spine and intervertebral disk detection and segmentation from whole spine MR images

Intervertebral disks are found between the vertebrae in the spine from the second cervical vertebra to the sacrum. Intervertebral disks permit various movements of the vertebral column to keep it flexible and to absorb vertical shock. The spine can be exposed to several types of compression forces that can adversely affect disk function and cause diseases or disorders, such as herniated disks. Mainly to diagnose these disorders we use Magnetic Resonance Imaging (MRI), since it's the preferred method for extracting the spinal information needed. In this paper, a Computer Aided Diagnosis (CAD) system for intervertebral disk detection and segmentation, using sagittal MR images of the whole spine has been proposed. The system consists of three major steps as follows: spine region extraction, intervertebral disk detection, and intervertebral disk segmentation. A 6th order polynomial Iterative Randomized Hough Transform (IRHT) approach is used to segment the spine sub-image from a whole spine T1/T2-weighted MR image in a relatively short time. Finally, an elliptical Hough Transform (HT) is used to detect the intervertebral disks from the segmented spine image. The proposed system used a whole spine images dataset consisting of 31 spine T1/T2 MR images. The accuracy measures of intervertebral disk detection and disk segmentation are 94.65% and 90%, respectively. The results show that the proposed system is robust and accurate for spine segmentation and intervertebral disks detection with high performance. Finally, the proposed system is a useful tool for radiologists in detecting as well as segmenting intervertebral disk in whole spine MR images.

Minimum detectable spinal cord atrophy with automatic segmentation: Investigations using an open-access dataset of healthy participants

Spinal cord atrophy is a well-known biomarker in multiple sclerosis (MS) and other diseases. It is measured by segmenting the spinal cord on an MRI image and computing the average cross-sectional area (CSA) over a few slices. Introduced about 25 years ago, this procedure is highly sensitive to the quality of the segmentation and is prone to rater-bias. Recently, fully-automated spinal cord segmentation methods, which remove the rater-bias and enable the automated analysis of large populations, have been introduced. A lingering question related to these automated methods is: How reliable are they at detecting atrophy? In this study, we evaluated the precision and accuracy of automated atrophy measurements by simulating scan-rescan experiments.Spinal cord MRI data from the open-access spine-generic project were used. The dataset aggregates 42 sites worldwide and consists of 260 healthy subjects and includes T1w and T2w contrasts. To simulate atrophy, each volume was globally rescaled at various scaling factors. Moreover, to simulate patient repositioning, random rigid transformations were applied. Using the DeepSeg algorithm from the Spinal Cord Toolbox, the spinal cord was segmented and vertebral levels were identified. Then, the average CSA between C3-C5 vertebral levels was computed for each Monte Carlo sample, allowing us to derive measures of atrophy, intra/inter-subject variability, and sample-size calculations.The minimum sample size required to detect an atrophy of 2% between unpaired study arms, commonly seen in MS studies, was 467 +/− 13.9 using T1w and 467 +/− 3.2 using T2w images. The minimum sample size to detect a longitudinal atrophy (between paired study arms) of 0.8% was 60 +/− 25.1 using T1w and 10 +/− 1.2 using T2w images. At the intra-subject level, the estimated CSA, observed in this study, showed good precision compared to other studies with COVs (across Monte Carlo transformations) of 0.8% for T1w and 0.6% for T2w images.While these sample sizes seem small, we would like to stress that these results correspond to a “best case” scenario, in that the dataset used here was of particularly good quality and the model for simulating atrophy does not encompass all the variability met in real-life datasets. The simulated atrophy and scan-rescan variability may over-simplify the biological reality. The proposed framework is open-source and available at https://csa-atrophy.readthedocs.io/.

Supervised Contrastive Embedding for Medical Image Segmentation

Deep segmentation networks generally consist of an encoder to extract features from an input image and a decoder to restore them to the original input size to produce segmentation results. In an ideal setting, the trained encoder should possess the semantic embedding capability, which maps a pair of features close to each other when they belong to the same class, and maps them distantly if they correspond to different classes. Recent deep segmentation networks do not directly deal with the embedding behavior of the encoder. Accordingly, we cannot expect that the features embedded by the encoder will have the semantic embedding property. If the model can be trained to have the embedding ability, it will further enhance the performance as restoring from those features is much easier for the decoder. To this end, we propose supervised contrastive embedding, which employs feature-wise contrastive loss for the feature map to enhance the segmentation performance on medical images. We also introduce a boundary-aware sampling strategy, which focuses on the features corresponding to image patches located at the boundary area of the ground-truth annotations. Through extensive experiments on lung segmentation in chest radiographs, liver segmentation in computed tomography, and brain tumor and spinal cord gray matter segmentation in magnetic resonance images, it is demonstrated that the proposed method helps to improve the segmentation performance of popular U-Net, U-Net++, and DeepLabV3+ architectures. Furthermore, it is confirmed that the robustness on domain shifts can be enhanced for segmentation models by the proposed contrastive embedding.

Spinal cord segmentation and injury detection using a Crow Search-Rider optimization algorithm.

The damage in the spinal cord due to vertebral fractures may result in loss of sensation and muscle function either permanently or temporarily. The neurological condition of the patient can be improved only with the early detection and the treatment of the injury in the spinal cord. This paper proposes a spinal cord segmentation and injury detection system based on the proposed Crow search-Rider Optimization-based DCNN (CS-ROA DCNN) method, which can detect the injury in the spinal cord in an effective manner. Initially, the segmentation of the CT image of the spinal cord is performed using the adaptive thresholding method, followed by which the localization of the disc is performed using the Sparse FCM clustering algorithm (Sparse-FCM). The localized discs are subjected to a feature extraction process, where the features necessary for the classification process are extracted. The classification process is done using DCNN trained using the proposed CS-ROA, which is the integration of the Crow Search Algorithm (CSA) and Rider Optimization Algorithm (ROA). The experimentation is performed using the evaluation metrics, such as accuracy, sensitivity, and specificity. The proposed method achieved the high accuracy, sensitivity, and specificity of 0.874, 0.8961, and 0.8828, respectively that shows the effectiveness of the proposed CS-ROA DCNN method in spinal cord injury detection.

Medical image processing with contextual style transfer

With recent advances in deep learning research, generative models have achieved great achievements and play an increasingly important role in current industrial applications. At the same time, technologies derived from generative methods are also under a wide discussion with researches, such as style transfer, image synthesis and so on. In this work, we treat generative methods as a possible solution to medical image augmentation. We proposed a context-aware generative framework, which can successfully change the gray scale of CT scans but almost without any semantic loss. By producing target images that with specific style / distribution, we greatly increased the robustness of segmentation model after adding generations into training set. Besides, we improved 2– 4% pixel segmentation accuracy over original U-NET in terms of spine segmentation. Lastly, we compared generations produced by networks when using different feature extractors (Vgg, ResNet and DenseNet) and made a detailed analysis on their performances over style transfer.

Temporal Trends in Cervical Spine Curvature of South Korean Adults Assessed by Deep Learning System Segmentation, 2006-2018

The loss of the physiologic cervical lordotic curve is a common degenerative disorder known to be associated with abnormal spinal alignment. However, the changing trends among sex and age groups has not yet been well established. To analyze the temporal trends in cervical curvature across sex and age groups using an automated deep learning system (DLS). A retrospective cross-sectional study was conducted using lateral cervical radiographs of 13 691 individuals from January 1, 2006, to December 31, 2018. The degree of anterior vertical curvature was approximated by a DLS approach and convexity measurement method. This population-based study used the Yonsei University College of Medicine Severance Hospital, Seoul, South Korea, cohort database to identify 13 691 consecutive adults (≥18 years of age) who underwent standing lateral radiography in inpatient and outpatient settings. The prevalence of kyphotic and straight cervical curve as well as the trends of degree of cervical curvature in 2006 to 2018 among sex and age groups were determined. The DLS performance was validated with quantitative metrics and compared with interobserver and intraobserver variations. Automatic cervical spine segmentation was identified from lateral radiographs of 13 691 individuals (mean [SD] age, 49.9 [15.3] years; 8051 women [58.8%]). From 2006 to 2018, the decrease in the lordotic curve was significant across both sexes and age groups younger than 70 years, with the decrease more pronounced in women and successively younger generations (female, -0.05; 95% CI, -0.06 to -0.04; 18-29 years of age, -0.06; 95% CI, -0.08 to -0.04; 30-39 years of age, -0.06; 95% CI, -0.08 to -0.04; and 40-49 years of age, -0.05; 95% CI, -0.06 to -0.03; all P < .001). The prevalence of straight and kyphotic curvature had a significant increasing trend for both sexes and young generations, in which individuals 18 to 29 years of age generally had the highest prevalence rates during the study cycle (in 2018, kyphosis, 16.7%; 95% CI, 10.8%-22.5%; straight, 45.5%; 95% CI, 37.7%-53.3%). Similar trends were observed with longitudinal analysis of repeated measures of individuals, with more pronounced decreases in lordotic curvature observed among women and young adults. This study suggests a significant, increasing loss of normal cervical lordotic curvature for both sexes and young adults that is greater in progressively younger cohorts and women. Further research is necessary to evaluate associations between neck pain and loss of cervical curvature and address the need for active promotion and practical interventions aimed at neck posture correction.

Deep learning spine segmentation to get accurate and relevant BMD and TBS values: The OsteoLaus study

Deep learning spine segmentation to get accurate and relevant BMD and TBS values: The OsteoLaus study