Lumbar spine segmentation using a statistical multi-vertebrae anatomical shape+pose model

Standalone ultrasound-based highly visualized volumetric spine imaging for surgical navigation

Current navigation systems employing intraoperative CT have been applied in spinal interventions for accurate and visualized guidance. The consequential issue of radiation doses and surgical workflow disruption spotlighted ultrasound (US) as an alternative imaging modality. However, the challenge of anatomy interpretation left US-based navigation inadequate in visualization, resulting in the necessity of registration of preoperative images. Here we report a standalone ultrasound image-guided system (SUIGS) leveraging a purpose-made network to automatically extract bone features and reconstruct them into highly visualized volumetric images for spinal navigation. We showed the SUIGS highly visualized the bone markers with an imaging accuracy of 1.19 ± 0.85 mm in scanning tests on human volunteers. Through extensive testing on data from hospitalized patients containing atypical cases (spinal deformity, obesity), we confirmed that SUIGS generalizes across different individuals with a 100% success rate in aligning with preoperative CT. Furthermore, SUIGS yielded comparable results to three-dimensional fluoroscopy guidance in intraoperative intraspinal tumor localization and reduced the procedure to 8 min. This study explored and broadened the clinical application of standalone US navigation by providing intraoperative high-visualized volumetric spinal imaging, which is expected to increase the likelihood of surgeons adopting it in practice to reduce the occurrence of wrong-site surgery.

Semantics and instance interactive learning for labeling and segmentation of vertebrae in CT images

Automatically labeling and segmenting vertebrae in 3D CT images compose a complex multi-task problem. Current methods progressively conduct vertebra labeling and semantic segmentation, which typically include two separate models and may ignore feature interaction among different tasks. Although instance segmentation approaches with multi-channel prediction have been proposed to alleviate such issues, their utilization of semantic information remains insufficient. Additionally, another challenge for an accurate model is how to effectively distinguish similar adjacent vertebrae and model their sequential attribute. In this paper, we propose a Semantics and Instance Interactive Learning (SIIL) paradigm for synchronous labeling and segmentation of vertebrae in CT images. SIIL models semantic feature learning and instance feature learning, in which the former extracts spinal semantics and the latter distinguishes vertebral instances. Interactive learning involves semantic features to improve the separability of vertebral instances and instance features to help learn position and contour information, during which a Morphological Instance Localization Learning (MILL) module is introduced to align semantic and instance features and facilitate their interaction. Furthermore, an Ordinal Contrastive Prototype Learning (OCPL) module is devised to differentiate adjacent vertebrae with high similarity (via cross-image contrastive learning), and simultaneously model their sequential attribute (via a temporal unit). Extensive experiments on several datasets demonstrate that our method significantly outperforms other approaches in labeling and segmenting vertebrae. Our code is available at https://github.com/YuZhang-SMU/Vertebrae-Labeling-Segmentation.

Assessment of age-dependent sexual dimorphism in paediatric vertebral size and density using a statistical shape and statistical appearance modelling approach

This work focuses on the growth patterns of the human fourth lumbar vertebra (L4) in a paediatric population, with specific attention to sexual dimorphism. The study aims to understand morphological and density changes in the vertebrae through age-dependent statistical shape and statistical appearance models, which can describe full three-dimensional anatomy. Results show that the main growth patterns are associated with isotropic volumetric vertebral growth, a decrease in the relative size of the vertebral foramen, and an increase in the length of the transverse processes. Moreover, significant sexual dimorphism was demonstrated during puberty. We observe significant age and sex interaction in the anterior vertebral body height (P = 0.005), where females exhibited an earlier increase in rates of vertebral height evolution. Moreover, we also observe an increase in cross-sectional area (CSA) with age (P = 0.020), where the CSA is smaller in females than in males (significant sex effect P = 0.042). Finally, although no significant increase in trabecular bone density with age is observed (P = 0.363), a trend in the statistical appearance model suggests an increase in density with age.

VerFormer: Vertebrae-Aware Transformer for Automatic Spine Segmentation from CT Images

The accurate and efficient segmentation of the spine is important in the diagnosis and treatment of spine malfunctions and fractures. However, it is still challenging because of large inter-vertebra variations in shape and cross-image localization of the spine. In previous methods, convolutional neural networks (CNNs) have been widely applied as a vision backbone to tackle this task. However, these methods are challenged in utilizing the global contextual information across the whole image for accurate spine segmentation because of the inherent locality of the convolution operation. Compared with CNNs, the Vision Transformer (ViT) has been proposed as another vision backbone with a high capacity to capture global contextual information. However, when the ViT is employed for spine segmentation, it treats all input tokens equally, including vertebrae-related tokens and non-vertebrae-related tokens. Additionally, it lacks the capability to locate regions of interest, thus lowering the accuracy of spine segmentation. To address this limitation, we propose a novel Vertebrae-aware Vision Transformer (VerFormer) for automatic spine segmentation from CT images. Our VerFormer is designed by incorporating a novel Vertebrae-aware Global (VG) block into the ViT backbone. In the VG block, the vertebrae-related global contextual information is extracted by a Vertebrae-aware Global Query (VGQ) module. Then, this information is incorporated into query tokens to highlight vertebrae-related tokens in the multi-head self-attention module. Thus, this VG block can leverage global contextual information to effectively and efficiently locate spines across the whole input, thus improving the segmentation accuracy of VerFormer. Driven by this design, the VerFormer demonstrates a solid capacity to capture more discriminative dependencies and vertebrae-related context in automatic spine segmentation. The experimental results on two spine CT segmentation tasks demonstrate the effectiveness of our VG block and the superiority of our VerFormer in spine segmentation. Compared with other popular CNN- or ViT-based segmentation models, our VerFormer shows superior segmentation accuracy and generalization.

Reconstruction of 3D lumbar spine models from incomplete segmentations using landmark detection

Patient-specific 3D spine models serve as a foundation for spinal treatment and surgery planning as well as analysis of loading conditions in biomechanical and biomedical research. Despite advancements in imaging technologies, the reconstruction of complete 3D spine models often faces challenges due to limitations in imaging modalities such as planar X-Ray and missing certain spinal structures, such as the spinal or transverse processes, in volumetric medical images and resulting segmentations. In this study, we present a novel accurate and time-efficient method to reconstruct complete 3D lumbar spine models from incomplete 3D vertebral bodies obtained from segmented magnetic resonance images (MRI). In our method, we use an affine transformation to align artificial vertebra models with patient-specific incomplete vertebrae. The transformation matrix is derived from vertebra landmarks, which are automatically detected on the vertebra endplates. The results of our evaluation demonstrate the high accuracy of the performed registration, achieving an average point-to-model distance of 1.95 mm. Additionally, in assessing the morphological properties of the vertebrae and intervertebral characteristics, our method demonstrated a mean absolute error (MAE) of 3.4° in the angles of functional spine units (FSUs), emphasizing its effectiveness in maintaining important spinal features throughout the transformation process of individual vertebrae. Our method achieves the registration of the entire lumbar spine, spanning segments L1 to L5, in just 0.14 seconds, showcasing its time-efficiency. Clinical relevance: the fast and accurate reconstruction of spinal models from incomplete input data such as segmentations provides a foundation for many applications in spine diagnostics, treatment planning, and the development of spinal healthcare solutions.

RASpine: Regional Attention Lateral Spinal Segmentation based on Anatomical Prior Knowledge

In the clinical diagnosis and treatment of spinal disorders, segmenting the spine from X-ray images provides clear visualization of the spinal structure and morphology. However, while existing spine segmentation methods perform well on anteroposterior X-ray images, their performance is poor on lateral X-rays. This is mainly due to the low contrast and severe occlusion of the thoracic vertebrae on lateral X-rays, resulting in overlapping vertebrae in segmentation results. To address this issue, this paper proposes a segmentation network called Region Attention and Spine Prior-based Network (RASpine). By utilizing the anatomical prior knowledge of non-overlapping regions between different vertebrae, an overlap detector is designed to identify overlapping parts of different vertebrae in the segmentation results. Moreover, a loss function is designed to penalize the overlapping regions, thereby avoiding overlapping segmentation results for the vertebrae. Finally, region attention is employed to enhance the segmentation accuracy in challenging regions. The proposed RASpine is trained, validated, and tested on a clinical dataset. Experimental results demonstrate that compared to existing mainstream medical image segmentation algorithms, RASpine effectively addresses the overlapping parts in lateral X-ray spine segmentation results and achieves more satisfactory performance in multiple evaluation metrics.

Comprehensive assessment of global spinal sagittal alignment and related normal spinal loads in a healthy population

Abnormal postoperative global sagittal alignment (GSA) is associated with an increased risk of mechanical complications after spinal surgery. Typical assessment of sagittal alignment relies on a few selected measures, disregarding global complexity and variability of the sagittal curvature. The normative range of spinal loads associated with GSA has not yet been considered in clinical evaluation. The study objectives were to develop a new GSA assessment method that holistically describes the inherent relationships within GSA and to estimate the related spinal loads. Vertebral endplates were annotated on radiographs of 85 non-pathological subjects. A Principal Component Analysis (PCA) was performed to derive a Statistical Shape Model (SSM). Associations between identified GSA variability modes and conventional alignment measures were assessed. Simulations of respective Shape Modes (SMs) were performed using an established musculoskeletal AnyBody model to estimate normal variation in cervico-thoraco-lumbar loads. The first six principal components explained 97.96% of GSA variance. The SSM provides the normative range of GSA and a visual representation of the main variability modes. Normal variation relative to the population mean in identified alignment features was found to influence spinal loads, e.g. the lower bound of the second shape mode (SM2-2σ) corresponds to an increase in L4L5-compression by 378.64 N (67.86%). Six unique alignment features were sufficient to describe GSA almost entirely, demonstrating the value of the proposed method for an objective and comprehensive analysis of GSA. The influence of these features on spinal loads provides a normative biomechanical reference, eventually guiding surgical planning of deformity correction in the future.

3D multi-scale feature extraction and recalibration network for spinal structure and lesion segmentation

BACKGROUND

Automatic segmentation has emerged as a promising technique for the diagnosis of spinal conditions.

PURPOSE

To design and evaluate a deep convolution network for segmenting the intervertebral disc, spinal canal, facet joint, and herniated disk on magnetic resonance imaging (MRI) scans.

MATERIAL AND METHODS

MRI scans of 70 patients with disc herniation were gathered and manually annotated by radiologists. A novel deep neural network was developed, comprising 3D squeeze-and-excitation blocks and multi-scale feature extraction blocks for automated segmentation of spinal structure and lesion. To address the issue of class imbalance, a weighted cross-entropy loss was introduced for training. In addition, semi-supervision segmentation was accomplished to reduce annotation labor cost.

RESULTS

The proposed model achieved 77.67% mean intersection over union, with 9.56% and 11.11% gains over typical V-Net and U-Net respectively, outperforming the other models in ablation experiments. In addition, the semi-supervision segmentation method was proven to work.

CONCLUSION

The 3D multi-scale feature extraction and recalibration network achieved an excellent segmentation performance of intervertebral disc, spinal canal, facet joint, and herniated disk, outperforming typical encoder-decoder networks.

A Survey on Artificial Intelligence in Pulmonary Imaging

Over the last decade, deep learning (DL) has contributed a paradigm shift in computer vision and image recognition creating widespread opportunities of using artificial intelligence in research as well as industrial applications. DL has been extensively studied in medical imaging applications, including those related to pulmonary diseases. Chronic obstructive pulmonary disease, asthma, lung cancer, pneumonia, and, more recently, COVID-19 are common lung diseases affecting nearly 7.4% of world population. Pulmonary imaging has been widely investigated toward improving our understanding of disease etiologies and early diagnosis and assessment of disease progression and clinical outcomes. DL has been broadly applied to solve various pulmonary image processing challenges including classification, recognition, registration, and segmentation. This paper presents a survey of pulmonary diseases, roles of imaging in translational and clinical pulmonary research, and applications of different DL architectures and methods in pulmonary imaging with emphasis on DL-based segmentation of major pulmonary anatomies such as lung volumes, lung lobes, pulmonary vessels, and airways as well as thoracic musculoskeletal anatomies related to pulmonary diseases.

Development, calibration and validation of a comprehensive customizable lumbar spine FE model for simulating fusion constructs

Instrumentation alters the biomechanics of the spine, and therefore prediction of all output quantities that have critical influence post-surgically is significant for engineering models to aid in clinical predictions. Geometrical morphological finite element models can bring down the development time and cost of custom intact and instrumented models and thus aids in the better inference of biomechanics of surgical instrumentation on patient-specific diseased spine segments. A comprehensive hexahedral morphological lumbosacral finite element model is developed in this work to predict the range of motions, disc pressures, and facet contact forces of the intact and instrumented spine. Facet contact forces are needed to predict the impact of fusion surgeries on adjacent facet contacts in bending, axial rotation, and extension motions. Extensive validation in major physiological loading regimes of the pure moment, pure compression, and combined loading is undertaken. In vitro, experimental corridor results from six different studies reported in the literature are compared and the generated model had statistically significant comparable values with these studies. Flexion, extension and bending moment rotation curves of all segments of the developed model were favourable and within two separately established experimental corridor windows as well as recent simulation results. Axial torque moment rotation curves were comparable to in vitro results for four out of five lumbar functional units. The facet contact force results also agreed with in vitro experimental results. The current model is also computationally efficient with respect to contemporary models since it uses significantly smaller number of elements without losing the accuracy in terms of response prediction. This model can further be used for predicting the impact of different instrumentation techniques on the lumbar vertebral column.

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

Vertebrae localization, segmentation and identification in CT images is key to numerous clinical applications. While deep learning strategies have brought to this field significant improvements over recent years, transitional and pathological vertebrae are still plaguing most existing approaches as a consequence of their poor representation in training datasets. Alternatively, proposed non-learning based methods take benefit of prior knowledge to handle such particular cases. In this work we propose to combine both strategies. To this purpose we introduce an iterative cycle in which individual vertebrae are recurrently localized, segmented and identified using deep-networks, while anatomic consistency is enforced using statistical priors. In this strategy, the transitional vertebrae identification is handled by encoding their configurations in a graphical model that aggregates local deep-network predictions into an anatomically consistent final result. Our approach achieves the state-of-the-art results on the VerSe20 challenge benchmark, and outperforms all methods on transitional vertebrae as well as the generalization to the VerSe19 challenge benchmark. Furthermore, our method can detect and report inconsistent spine regions that do not satisfy the anatomic consistency priors. Our code and model are openly available for research purposes.¹.

CT-Based Automatic Spine Segmentation Using Patch-Based Deep Learning

CT vertebral segmentation plays an essential role in various clinical applications, such as computer-assisted surgical interventions, assessment of spinal abnormalities, and vertebral compression fractures. Automatic CT vertebral segmentation is challenging due to the overlapping shadows of thoracoabdominal structures such as the lungs, bony structures such as the ribs, and other issues such as ambiguous object borders, complicated spine architecture, patient variability, and fluctuations in image contrast. Deep learning is an emerging technique for disease diagnosis in the medical field. This study proposes a patch-based deep learning approach to extract the discriminative features from unlabeled data using a stacked sparse autoencoder (SSAE). 2D slices from a CT volume are divided into overlapping patches fed into the model for training. A random under sampling (RUS)-module is applied to balance the training data by selecting a subset of the majority class. SSAE uses pixel intensities alone to learn high-level features to recognize distinctive features from image patches. Each image is subjected to a sliding window operation to express image patches using autoencoder high-level features, which are then fed into a sigmoid layer to classify whether each patch is a vertebra or not. We validate our approach on three diverse publicly available datasets: VerSe, CSI-Seg, and the Lumbar CT dataset. Our proposed method outperformed other models after configuration optimization by achieving 89.9% in precision, 90.2% in recall, 98.9% in accuracy, 90.4% in F-score, 82.6% in intersection over union (IoU), and 90.2% in Dice coefficient (DC). The results of this study demonstrate that our model’s performance consistency using a variety of validation strategies is flexible, fast, and generalizable, making it suited for clinical application.

Opportunistic Screening Techniques for Analysis of CT Scans

PURPOSE OF REVIEW

Opportunistic screening is a combination of techniques to identify subjects of high risk for osteoporotic fracture using routine clinical CT scans prescribed for diagnoses unrelated to osteoporosis. The two main components are automated detection of vertebral fractures and measurement of bone mineral density (BMD) in CT scans, in which a phantom for calibration of CT to BMD values is not used. This review describes the particular challenges of opportunistic screening and provides an overview and comparison of current techniques used for opportunistic screening. The review further outlines the performance of opportunistic screening.

RECENT FINDINGS

A wide range of technologies for the automatic detection of vertebral fractures have been developed and successfully validated. Most of them are based on artificial intelligence algorithms. The automated differentiation of osteoporotic from traumatic fractures and vertebral deformities unrelated to osteoporosis, the grading of vertebral fracture severity, and the detection of mild vertebral fractures is still problematic. The accuracy of automated fracture detection compared to classical radiological semi-quantitative Genant scoring is about 80%. Accuracy errors of alternative BMD calibration methods compared to simultaneous phantom-based calibration used in standard quantitative CT (QCT) range from below 5% to about 10%. The impact of contrast agents, frequently administered in clinical CT on the determination of BMD and on fracture risk determination is still controversial. Opportunistic screening, the identification of vertebral fracture and the measurement of BMD using clinical routine CT scans, is feasible but corresponding techniques still need to be integrated into the clinical workflow and further validated with respect to the prediction of fracture risk.

Multi-perspective region-based CNNs for vertebrae labeling in intraoperative long-length images

PURPOSE

Effective aggregation of intraoperative x-ray images that capture the patient anatomy from multiple view-angles has the potential to enable and improve automated image analysis that can be readily performed during surgery. We present multi-perspective region-based neural networks that leverage knowledge of the imaging geometry for automatic vertebrae labeling in Long-Film images - a novel tomographic imaging modality with an extended field-of-view for spine imaging.

METHOD

A multi-perspective network architecture was designed to exploit small view-angle disparities produced by a multi-slot collimator and consolidate information from overlapping image regions. A second network incorporates large view-angle disparities to jointly perform labeling on images from multiple views (viz., AP and lateral). A recurrent module incorporates contextual information and enforce anatomical order for the detected vertebrae. The three modules are combined to form the multi-view multi-slot (MVMS) network for labeling vertebrae using images from all available perspectives. The network was trained on images synthesized from 297 CT images and tested on 50 AP and 50 lateral Long-Film images acquired from 13 cadaveric specimens. Labeling performance of the multi-perspective networks was evaluated with respect to the number of vertebrae appearances and presence of surgical instrumentation.

RESULTS

The MVMS network achieved an F1 score of >96% and an average vertebral localization error of 3.3 mm, with 88.3% labeling accuracy on both AP and lateral images - (15.5% and 35.0% higher than conventional Faster R-CNN on AP and lateral views, respectively). Aggregation of multiple appearances of the same vertebra using the multi-slot network significantly improved the labeling accuracy (p < 0.05). Using the multi-view network, labeling accuracy on the more challenging lateral views was improved to the same level as that of the AP views. The approach demonstrated robustness to the presence of surgical instrumentation, commonly encountered in intraoperative images, and achieved comparable performance in images with and without instrumentation (88.9% vs. 91.2% labeling accuracy).

CONCLUSION

The MVMS network demonstrated effective multi-perspective aggregation, providing means for accurate, automated vertebrae labeling during spine surgery. The algorithms may be generalized to other imaging tasks and modalities that involve multiple views with view-angle disparities (e.g., bi-plane radiography). Predicted labels can help avoid adverse events during surgery (e.g., wrong-level surgery), establish correspondence with labels in preoperative modalities to facilitate image registration, and enable automated measurement of spinal alignment metrics for intraoperative assessment of spinal curvature.

SVseg: Stacked Sparse Autoencoder-Based Patch Classification Modeling for Vertebrae Segmentation

Precise vertebrae segmentation is essential for the image-related analysis of spine pathologies such as vertebral compression fractures and other abnormalities, as well as for clinical diagnostic treatment and surgical planning. An automatic and objective system for vertebra segmentation is required, but its development is likely to run into difficulties such as low segmentation accuracy and the requirement of prior knowledge or human intervention. Recently, vertebral segmentation methods have focused on deep learning-based techniques. To mitigate the challenges involved, we propose deep learning primitives and stacked Sparse autoencoder-based patch classification modeling for Vertebrae segmentation (SVseg) from Computed Tomography (CT) images. After data preprocessing, we extract overlapping patches from CT images as input to train the model. The stacked sparse autoencoder learns high-level features from unlabeled image patches in an unsupervised way. Furthermore, we employ supervised learning to refine the feature representation to improve the discriminability of learned features. These high-level features are fed into a logistic regression classifier to fine-tune the model. A sigmoid classifier is added to the network to discriminate the vertebrae patches from non-vertebrae patches by selecting the class with the highest probabilities. We validated our proposed SVseg model on the publicly available MICCAI Computational Spine Imaging (CSI) dataset. After configuration optimization, our proposed SVseg model achieved impressive performance, with 87.39% in Dice Similarity Coefficient (DSC), 77.60% in Jaccard Similarity Coefficient (JSC), 91.53% in precision (PRE), and 90.88% in sensitivity (SEN). The experimental results demonstrated the method’s efficiency and significant potential for diagnosing and treating clinical spinal diseases.

The lumbar region localization using bone anatomy feature graphs

The automatic localization of the lumbar region is essential for the diagnosis of lumbar diseases, the study of lumbar morphology, and the surgical planning. Although the existing researches have made great progress, it still faces several challenges. First, the various lumbar diseases and pathologies cause different abnormalities in the lumbar shape and appearance. Second, the numbers of lumbar vertebrae are irregular (some people have an additional vertebra L6). To tackle these challenges, we propose a novel lumbar region localization method based on bone anatomy feature graphs. Specifically, a feature graph (called LS) considering the anatomy of the sacrum and the lumbar vertebra is proposed to locate the inferior boundary of L5 or L6. A feature graph (called TL) considering the anatomy of the thoracic vertebra and the lumbar vertebra is proposed to locate the superior boundary of L1. Extensive experimental analysis is performed on a public available dataset xVertSeg and a private dataset which contains 197 CT scans. The localization results show that the proposed method is robust and can be applied to normal scans, scoliosis scans, deformity scans, hyperosteogeny scans, 6 lumbar vertebrae scans and lumbar implant scans. The Dice and Jaccard coefficients are 98.09 ± 0.84% and 96.27 ± 1.62% respectively. Graphical Abstract Lumbar Region Localization Framework.

Artificial Intelligence and Computer Vision in Low Back Pain: A Systematic Review

Chronic Low Back Pain (LBP) is a symptom that may be caused by several diseases, and it is currently the leading cause of disability worldwide. The increased amount of digital images in orthopaedics has led to the development of methods related to artificial intelligence, and to computer vision in particular, which aim to improve diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of computer vision in the diagnosis and treatment of LBP. A systematic research of PubMed electronic database was performed. The search strategy was set as the combinations of the following keywords: "Artificial Intelligence", "Feature Extraction", "Segmentation", "Computer Vision", "Machine Learning", "Deep Learning", "Neural Network", "Low Back Pain", "Lumbar". Results: The search returned a total of 558 articles. After careful evaluation of the abstracts, 358 were excluded, whereas 124 papers were excluded after full-text examination, taking the number of eligible articles to 76. The main applications of computer vision in LBP include feature extraction and segmentation, which are usually followed by further tasks. Most recent methods use deep learning models rather than digital image processing techniques. The best performing methods for segmentation of vertebrae, intervertebral discs, spinal canal and lumbar muscles achieve Sørensen-Dice scores greater than 90%, whereas studies focusing on localization and identification of structures collectively showed an accuracy greater than 80%. Future advances in artificial intelligence are expected to increase systems' autonomy and reliability, thus providing even more effective tools for the diagnosis and treatment of LBP.

VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.

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.

3D vertebrae labeling in spine CT: an accurate, memory-efficient (Ortho2D) framework

Purpose.Accurate localization and labeling of vertebrae in computed tomography (CT) is an important step toward more quantitative, automated diagnostic analysis and surgical planning. In this paper, we present a framework (called Ortho2D) for vertebral labeling in CT in a manner that is accurate and memory-efficient.Methods. Ortho2D uses two independent faster R-convolutional neural network networks to detect and classify vertebrae in orthogonal (sagittal and coronal) CT slices. The 2D detections are clustered in 3D to localize vertebrae centroids in the volumetric CT and classify the region (cervical, thoracic, lumbar, or sacral) and vertebral level. A post-process sorting method incorporates the confidence in network output to refine classifications and reduce outliers. Ortho2D was evaluated on a publicly available dataset containing 302 normal and pathological spine CT images with and without surgical instrumentation. Labeling accuracy and memory requirements were assessed in comparison to other recently reported methods. The memory efficiency of Ortho2D permitted extension to high-resolution CT to investigate the potential for further boosts to labeling performance.Results. Ortho2D achieved overall vertebrae detection accuracy of 97.1%, region identification accuracy of 94.3%, and individual vertebral level identification accuracy of 91.0%. The framework achieved 95.8% and 83.6% level identification accuracy in images without and with surgical instrumentation, respectively. Ortho2D met or exceeded the performance of previously reported 2D and 3D labeling methods and reduced memory consumption by a factor of ∼50 (at 1 mm voxel size) compared to a 3D U-Net, allowing extension to higher resolution datasets than normally afforded. The accuracy of level identification increased from 80.1% (for standard/low resolution CT) to 95.1% (for high-resolution CT).Conclusions. The Ortho2D method achieved vertebrae labeling performance that is comparable to other recently reported methods with significant reduction in memory consumption, permitting further performance boosts via application to high-resolution CT.

A comparison of Cartesian-only vs. Cartesian-spherical hybrid coordinates for statistical shape modeling in the lumbar spine

OBJECTIVE

The purpose of this study was to compare two methods for quantifying differences in geometric shapes of human lumbar vertebra using statistical shape modeling (SSM).

METHODS

A novel 3D implementation of a previously published 2D, nonlinear SSM was implemented and compared to a commonly used, Cartesian method of SSM. The nonlinear method, or Hybrid SSM, and Cartesian SSM were applied to lumbar vertebra shapes from a cohort of 18 full lumbar triangle meshes derived from CT scans. The comparison included traditional metrics for cumulative variance, generality, and specificity and results from application-based biomechanics using finite element simulation.

RESULTS

The Hybrid SSM has less compactness - likely due to the increased number of mathematical constraints in the SSM formulation. Similar results were found between methods for specificity and generality. Compared to the previously validated, manually-segmented FE model, both SSM methods produced similar and agreeable results.

CONCLUSION

Visual, statistical, and biomechanical findings did not convincingly support the superiority of the Hybrid SSM over the simpler Cartesian SSM.

SIGNIFICANCE

This work suggests that, of the two methods compared, the Cartesian SSM is adequate to capture the variations in shape of the posterior spinal structures for biomechanical modeling applications.

A novel segmentation method for cervical vertebrae based on PointNet++ and converge segmentation

BACKGROUND

Cervical spine instability is the key pathogenic factor for cervical spondylosis, which may easily cause cervical spinal cord nerve compression, numbness, weakness, and even paralysis of the limbs. The reconstruction of the internal fixation of the cervical spine is of great therapeutic significance, but is a high-risk and difficult procedure that requires precise planning. The high similarities between vertebrae may interfere with automatic operation planning; therefore, the segmentation of vertebrae is of great significance.

METHODS

Our segmentation algorithm has 3 parts. Firstly, an adaptive threshold filter to segment the cervical vertebra tissue structure form CT images. Secondly, segmentation of single vertebrae based on PointNet++ is introduced to segmentation cervical spine. Finally, converge segmentation which is based on edge information is utilized to clearly distinguish the edges of the two vertebrae to enhance the accuracy segmentation result.

RESULTS

Our approach improved the accuracy of the system up to 96.15%, and achieved the highest reported average score based on this dataset. We compared the results of the CNN and PointNet methods on a separate dataset of 240 CT scans with 18 classes and achieved a significantly higher performance for any given vertebra. Our experiments illustrated the promise and robustness of recent PointNet++-based segmentation of medical images.

CONCLUSION

The proposed method has better classification performance for segmentation cervical spine images, which segment a three-dimensional vertebral body directly and effectively. Furthermore, the precise segmentation of a single vertebral body can be used in automatic biomechanical analysis, computer-aided diagnosis and other aspects, so as to improve the level of automation in the treatment of cervical spondylosis.

Deep Learning Using Isotroping, Laplacing, Eigenvalues Interpolative Binding, and Convolved Determinants with Normed Mapping for Large-Scale Image Retrieval

Convolutional neural networks (CNN) are relational with grid-structures and spatial dependencies for two-dimensional images to exploit location adjacencies, color values, and hidden patterns. Convolutional neural networks use sparse connections at high-level sensitivity with layered connection complying indiscriminative disciplines with local spatial mapping footprints. This fact varies with architectural dependencies, insight inputs, number and types of layers and its fusion with derived signatures. This research focuses this gap by incorporating GoogLeNet, VGG-19, and ResNet-50 architectures with maximum response based Eigenvalues textured and convolutional Laplacian scaled object features with mapped colored channels to obtain the highest image retrieval rates over millions of images from versatile semantic groups and benchmarks. Time and computation efficient formulation of the presented model is a step forward in deep learning fusion and smart signature capsulation for innovative descriptor creation. Remarkable results on challenging benchmarks are presented with a thorough contextualization to provide insight CNN effects with anchor bindings. The presented method is tested on well-known datasets including ALOT (250), Corel-1000, Cifar-10, Corel-10000, Cifar-100, Oxford Buildings, FTVL Tropical Fruits, 17-Flowers, Fashion (15), Caltech-256, and reported outstanding performance. The presented work is compared with state-of-the-art methods and experimented over tiny, large, complex, overlay, texture, color, object, shape, mimicked, plain and occupied background, multiple objected foreground images, and marked significant accuracies.

MRI-SegFlow: a novel unsupervised deep learning pipeline enabling accurate vertebral segmentation of MRI images

Most deep learning based vertebral segmentation methods require laborious manual labelling tasks. We aim to establish an unsupervised deep learning pipeline for vertebral segmentation of MR images. We integrate the sub-optimal segmentation results produced by a rule-based method with a unique voting mechanism to provide supervision in the training process for the deep learning model. Preliminary validation shows a high segmentation accuracy achieved by our method without relying on any manual labelling.The clinical relevance of this study is that it provides an efficient vertebral segmentation method with high accuracy. Potential applications are in automated pathology detection and vertebral 3D reconstructions for biomechanical simulations and 3D printing, facilitating clinical decision making, surgical planning and tissue engineering.

The state-of-the-art in ultrasound-guided spine interventions

During the last two decades, intra-operative ultrasound (iUS) imaging has been employed for various surgical procedures of the spine, including spinal fusion and needle injections. Accurate and efficient registration of pre-operative computed tomography or magnetic resonance images with iUS images are key elements in the success of iUS-based spine navigation. While widely investigated in research, iUS-based spine navigation has not yet been established in the clinic. This is due to several factors including the lack of a standard methodology for the assessment of accuracy, robustness, reliability, and usability of the registration method. To address these issues, we present a systematic review of the state-of-the-art techniques for iUS-guided registration in spinal image-guided surgery (IGS). The review follows a new taxonomy based on the four steps involved in the surgical workflow that include pre-processing, registration initialization, estimation of the required patient to image transformation, and a visualization process. We provide a detailed analysis of the measurements in terms of accuracy, robustness, reliability, and usability that need to be met during the evaluation of a spinal IGS framework. Although this review is focused on spinal navigation, we expect similar evaluation criteria to be relevant for other IGS applications.

A comparative study on position and paramedian neuraxial access on healthy volunteers using three-dimensional models registered to lumbar spine ultrasound

PURPOSE

Optimizing patient position and needle puncture site are important factors for successful neuraxial anesthesia. Two paramedian approaches are commonly utilized and we sought to determine whether variations of the seated position would increase the chance of puncture success.

METHODS

We simulated paramedian needle passes on three-dimensional lumbar spine models registered to volumetric ultrasound data acquired from ten healthy volunteers in three different positions: 1) prone; 2) seated with thoracic and lumbar flexion; and 3) seated as in position 2, but with a 10° dorsal tilt. Simulated paramedian needle passes from the right side performed on validated models were used to determine L2-3 and L3-4 neuraxial target size and success. We selected two paramedian puncture sites according to standard anesthesia textbook descriptions: 10 mm lateral and 10 mm caudal from inferior edge of the superior spinous process as described by Miller, and 10 mm lateral from the superior edge of the inferior spinous process as described by Barash.

RESULTS

A significant increase in the area available for dural puncture was found in the L2-3 (61-62 mm²) and L3-4 (76-79 mm²) vertebral levels for all seated positions relative to the prone position (P < 0.001). Similarly, a significant increase in the total number of successful punctures was found in the L2-3 (77-79) and L3-4 (119-120) vertebral levels for all seated positions relative to the prone position (P < 0.001). No differences were found between seated positions. The Barash puncture site achieved a higher number of successful punctures than the Miller puncture site in both the L2-3 (19) and L3-4 (84) vertebral levels (P < 0.001).

CONCLUSION

An added dorsal table tilt did not increase puncture success in the seated position. The landmarks for puncture site described by Barash resulted in significantly more successful punctures compared with those described by Miller in all positions.

Modeling and Analysis of Ultrasound Elastographic Axial Strains for Spine Fracture Identification

This study reports the first use of ultrasound (US) elastography for imaging spinal fractures by assessing the mechanical response of the soft tissue at the posterior vertebra boundary to a uniaxial compression in rabbit ex vivo samples. Three-dimensional finite-element (FE) models of the vertebra-soft tissue complex in rabbit samples are generated and analyzed to evaluate the distribution of the axial normal and shear strains at the vertebra-soft tissue interface. Experiments on the same samples are performed to corroborate simulation findings. Results of this study indicate that the distribution of the axial strains manifests as distinct patterns around intact and fractured vertebrae. Numerical characteristics of the axial strain's spatial distribution are further used to construct two shape descriptors to make inferences on spinal abnormalities: 1) axial normal strain asymmetry for assessing the presence of fractures and 2) principal orientation of axial shear strain concentration regions (shear zones) for measurement of spinous process dislocation. This study demonstrates that axial normal strain and axial shear strain maps obtained via US elastography can provide a new means to detect spine fractures and abnormalities in the selected ex vivo animal models. Spinal fracture detection is important for the assessment of spinal cord injuries and stability. However, identification of spinal fractures using US is currently challenging. Our results show that features resulting from strain elastograms can serve as a useful adjunct to B-mode images in identifying spine fractures in the selected animal samples, and this information could be helpful in clinical settings.

Mechanics of Psoas Tendon Snapping. A Virtual Population Study

Internal snapping of the psoas tendon is a frequently reported condition, especially in young adolescents involved in sports. It is defined as an increased tendon excursion over bony or soft tissue prominence causing local irritation and inflammation of the tendon leading to groin pain and often is accompanied by an audible snap. Due to the lack of detailed dynamic visualization means, the exact mechanism of the condition remains poorly understood and different theories have been postulated related to the etiology and its location about the hip. In the present study we simulated psoas tendon behavior in a virtual population of 40,000 anatomies and compared tendon movement during combined abduction, flexion and external rotation and back to neutral extension and adduction. At risk phenotyopes for tendon snapping were defined as the morphologies presenting with excess tendon movement. There were little differences in tendon movement between the male and female models. In both populations, abnormal tendon excursion correlated with changes in mainly the femoral anatomy (male r = 0.72, p < 0.001, female r = 0.66, p < 0.001): increased anteversion and valgus as well as a decreasing femoral offset and ischiofemoral distance. The observed combination of shape components correlating with excess tendon movement in essence presented with a medial positioning of the minor trochanter. This finding suggest that psoas snapping and ischiofemoral impingement are possibly two presentations of a similar underlying rotational dysplasia of the femur.

A scalable approach to T2-MRI colon segmentation

The study of the colonic volume is a procedure with strong relevance to gastroenterologists. Depending on the clinical protocols, the volume analysis has to be performed on MRI of the unprepared colon without contrast administration. In such circumstances, existing measurement procedures are cumbersome and time-consuming for the specialists. The algorithm presented in this paper permits a quasi-automatic segmentation of the unprepared colon on T2-weighted MRI scans. The segmentation algorithm is organized as a three-stage pipeline. In the first stage, a custom tubularity filter is run to detect colon candidate areas. The specialists provide a list of points along the colon trajectory, which are combined with tubularity information to calculate an estimation of the colon medial path. In the second stage, we delimit the region of interest by applying custom segmentation algorithms to detect colon neighboring regions and the fat capsule containing abdominal organs. Finally, within the reduced search space, segmentation is performed via 3D graph-cuts in a three-stage multigrid approach. Our algorithm was tested on MRI abdominal scans, including different acquisition resolutions, and its results were compared to the colon ground truth segmentations provided by the specialists. The experiments proved the accuracy, efficiency, and usability of the algorithm, while the variability of the scan resolutions contributed to demonstrate the computational scalability of the multigrid architecture. The system is fully applicable to the colon measurement clinical routine, being a substantial step towards a fully automated segmentation.

Deformable multisurface segmentation of the spine for orthopedic surgery planning and simulation

Purpose: We describe a shape-aware multisurface simplex deformable model for the segmentation of healthy as well as pathological lumbar spine in medical image data. Approach: This model provides an accurate and robust segmentation scheme for the identification of intervertebral disc pathologies to enable the minimally supervised planning and patient-specific simulation of spine surgery, in a manner that combines multisurface and shape statistics-based variants of the deformable simplex model. Statistical shape variation within the dataset has been captured by application of principal component analysis and incorporated during the segmentation process to refine results. In the case where shape statistics hinder detection of the pathological region, user assistance is allowed to disable the prior shape influence during deformation. Results: Results demonstrate validation against user-assisted expert segmentation, showing excellent boundary agreement and prevention of spatial overlap between neighboring surfaces. This section also plots the characteristics of the statistical shape model, such as compactness, generalizability and specificity, as a function of the number of modes used to represent the family of shapes. Final results demonstrate a proof-of-concept deformation application based on the open-source surgery simulation Simulation Open Framework Architecture toolkit. Conclusions: To summarize, we present a deformable multisurface model that embeds a shape statistics force, with applications to surgery planning and simulation.

A novel robust kernel principal component analysis for nonlinear statistical shape modeling from erroneous data

Statistical Shape Models (SSMs) have achieved considerable success in medical image segmentation. A high quality SSM is able to approximate the main plausible variances of a given anatomical structure to guide segmentation. However, it is technically challenging to derive such a quality model because: (1) the distribution of shape variance is often nonlinear or multi-modal which cannot be modeled by standard approaches assuming Gaussian distribution; (2) as the quality of annotations in training data usually varies, heavy corruption will degrade the quality of the model as a whole. In this work, these challenges are addressed by introducing a generic SSM that is able to model nonlinear distribution and is robust to outliers in training data. Without losing generality and assuming a sparsity in nonlinear distribution, a novel Robust Kernel Principal Component Analysis (RKPCA) for statistical shape modeling is proposed with the aim of constructing a low-rank nonlinear subspace where outliers are discarded. The proposed approach is validated on two different datasets: a set of 30 public CT kidney pairs and a set of 49 MRI ankle bones volumes. Experimental results demonstrate a significantly better performance on outlier recovery and a higher quality of the proposed model as well as lower segmentation errors compared to the state-of-the-art techniques.

Biomechanically driven intraoperative spine registration during navigated anterior vertebral body tethering

The integration of pre-operative biomechanical planning with intra-operative imaging for navigated corrective spine surgery may improve surgical outcomes, as well as the accuracy and safety of manoeuvres such as pedicle screw insertion and cable tethering, as these steps are performed empirically by the surgeon. However, registration of finite element models (FEMs) of the spine remains challenging due to changes in patient positioning and imaging modalities. The purpose of this study was to develop and validate a new method registering a preoperatively constructed patient-specific FEM aimed to plan and assist anterior vertebral body tethering (AVBT) of scoliotic patients, to intraoperative cone beam computed tomography (CBCT) during navigated AVBT procedures. Prior to surgery, the 3D reconstruction of the patient's spine was obtained using biplanar radiographs, from which a patient-specific FEM was derived. The surgical plan was generated by first simulating the standing to intraoperative decubitus position change, followed by the AVBT correction techniques. Intraoperatively, a CBCT was acquired and an automatic segmentation method generated the 3D model for a series of vertebrae. Following a rigid initialization, a multi-level registration simulation using the FEM and the targeted positions of the corresponding reconstructed vertebrae from the CBCT allows for the refinement of the alignment between modalities. The method was tested with 18 scoliotic cases with a mean thoracic Cobb angle of 47°  ±  7° having already undergone AVBT. The translation error of the registered FEM vertebrae to the segmented CBCT spine was 1.4  ±  1.2 mm, while the residual orientation error was 2.7°  ±  2.6°, 2.8°  ±  2.4° and 2.5°  ±  2.8° in the coronal, sagittal, and axial planes, respectively. The average surface-to-surface distance was 1.5  ±  1.2 mm. The proposed method is a first attempt to use a patient-specific biomechanical FEM for navigated AVBT, allowing to optimize surgical strategies and screw placement during surgery.

N-Net: 3D Fully Convolution Network-Based Vertebrae Segmentation from CT Spinal Images

Accurate vertebrae segmentation from CT spinal images is crucial for the clinical tasks of diagnosis, surgical planning, and post-operative assessment. This paper describes an [Formula: see text]-shaped 3D fully convolution network (FCN) for vertebrae segmentation: [Formula: see text]-net. In this network, a global structure guidance pathway is designed for fusing the high-level semantic features with the global structure information. Moreover, the residual structure and the skip connection are introduced into traditional 3D FCN framework. These schemes can significantly improve the accuracy of vertebrae segmentation. Experimental results demonstrate the effectiveness and robustness of our method. A high average DICE score of 0.9499 [Formula: see text] 0.02 can be obtained, which is better than those of existing methods.

Iterative fully convolutional neural networks for automatic vertebra segmentation and identification

Precise segmentation and anatomical identification of the vertebrae provides the basis for automatic analysis of the spine, such as detection of vertebral compression fractures or other abnormalities. Most dedicated spine CT and MR scans as well as scans of the chest, abdomen or neck cover only part of the spine. Segmentation and identification should therefore not rely on the visibility of certain vertebrae or a certain number of vertebrae. We propose an iterative instance segmentation approach that uses a fully convolutional neural network to segment and label vertebrae one after the other, independently of the number of visible vertebrae. This instance-by-instance segmentation is enabled by combining the network with a memory component that retains information about already segmented vertebrae. The network iteratively analyzes image patches, using information from both image and memory to search for the next vertebra. To efficiently traverse the image, we include the prior knowledge that the vertebrae are always located next to each other, which is used to follow the vertebral column. The network concurrently performs multiple tasks, which are segmentation of a vertebra, regression of its anatomical label and prediction whether the vertebra is completely visible in the image, which allows to exclude incompletely visible vertebrae from further analyses. The predicted anatomical labels of the individual vertebrae are additionally refined with a maximum likelihood approach, choosing the overall most likely labeling if all detected vertebrae are taken into account. This method was evaluated with five diverse datasets, including multiple modalities (CT and MR), various fields of view and coverages of different sections of the spine, and a particularly challenging set of low-dose chest CT scans. For vertebra segmentation, the average Dice score was 94.9 ± 2.1% with an average absolute symmetric surface distance of 0.2 ± 10.1mm. The anatomical identification had an accuracy of 93%, corresponding to a single case with mislabeled vertebrae. Vertebrae were classified as completely or incompletely visible with an accuracy of 97%. The proposed iterative segmentation method compares favorably with state-of-the-art methods and is fast, flexible and generalizable.

Comparison of Patient Position and Midline Lumbar Neuraxial Access Via Statistical Model Registration to Ultrasound

Patient positioning and needle puncture site are important for lumbar neuraxial anesthesia. We sought to identify optimal patient positioning and puncture sites with a novel ultrasound registration. We registered a statistical model to volumetric ultrasound data acquired from volunteers (n = 10) in three positions: (i) prone; (ii) seated with thoracic and lumbar flexion; and (iii) seated as in position ii, with a 10° dorsal tilt. We determined injection target size and penetration success by simulating lumbar injections on validated registered models. Injection window and target area sizes in seated positions were significantly larger than those in prone positions by 65% in L2-3 and 130% in L3-4; a 10° tilt had no significant effect on target sizes between seated positions. In agreement with computed tomography studies, simulated L2-3 and L3-4 injections had the highest success at the 50% and 75% midline puncture sites, respectively, measured from superior to inferior spinous process. We conclude that our registration to ultrasound technique is a potential tool for tolerable determination of puncture site success in vivo.

Automatic Deep Feature Learning via Patch-Based Deep Belief Network for Vertebrae Segmentation in CT Images

Precise automatic vertebra segmentation in computed tomography (CT) images is important for the quantitative analysis of vertebrae-related diseases but remains a challenging task due to high variation in spinal anatomy among patients. In this paper, we propose a deep learning approach for automatic CT vertebra segmentation named patch-based deep belief networks (PaDBNs). Our proposed PaDBN model automatically selects the features from image patches and then measures the differences between classes and investigates performance. The region of interest (ROI) is obtained from CT images. Unsupervised feature reduction contrastive divergence algorithm is applied for weight initialization, and the weights are optimized by layers in a supervised fine-tuning procedure. The discriminative learning features obtained from the steps above are used as input of a classifier to obtain the likelihood of the vertebrae. Experimental results demonstrate that the proposed PaDBN model can considerably reduce computational cost and produce an excellent performance in vertebra segmentation in terms of accuracy compared with state-of-the-art methods.

Automatic Global Level Set Approach for Lumbar Vertebrae CT Image Segmentation

Vertebrae computed tomography (CT) image automatic segmentation is an essential step for Image-guided minimally invasive spine surgery. However, most of state-of-the-art methods still require human intervention due to the inherent limitations of vertebrae CT image, such as topological variation, irregular boundaries (double boundary, weak boundary), and image noise. Therefore, this paper intentionally designed an automatic global level set approach (AGLSA), which is capable of dealing with these issues for lumbar vertebrae CT image segmentation. Unlike the traditional level set methods, we firstly propose an automatically initialized level set function (AILSF) that comprises hybrid morphological filter (HMF) and Gaussian mixture model (GMM) to automatically generate a smooth initial contour which is precisely adjacent to the object boundary. Secondly, a regularized level set formulation is introduced to overcome the weak boundary leaking problem, which utilizes the region correlation of histograms inside and outside the level set contour as a global term. Ultimately, a gradient vector flow (GVF) based edge-stopping function is employed to guarantee a fast convergence rate of the level set evolution and to avoid level set function oversegmentation at the same time. Our proposed approach has been tested on 115 vertebrae CT volumes of various patients. Quantitative comparisons validate that our proposed AGLSA is more accurate in segmenting lumbar vertebrae CT images with irregular boundaries and more robust to various levels of salt-and-pepper noise.