Automated detection, 3D segmentation and analysis of high resolution spine MR images using statistical shape models

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.

Semi-supervised hybrid spine network for segmentation of spine MR images

Automatic segmentation of vertebral bodies (VBs) and intervertebral discs (IVDs) in 3D magnetic resonance (MR) images is vital in diagnosing and treating spinal diseases. However, segmenting the VBs and IVDs simultaneously is not trivial. Moreover, problems exist, including blurry segmentation caused by anisotropy resolution, high computational cost, inter-class similarity and intra-class variability, and data imbalances. We proposed a two-stage algorithm, named semi-supervised hybrid spine network (SSHSNet), to address these problems by achieving accurate simultaneous VB and IVD segmentation. In the first stage, we constructed a 2D semi-supervised DeepLabv3+ by using cross pseudo supervision to obtain intra-slice features and coarse segmentation. In the second stage, a 3D full-resolution patch-based DeepLabv3+ was built. This model can be used to extract inter-slice information and combine the coarse segmentation and intra-slice features provided from the first stage. Moreover, a cross tri-attention module was applied to compensate for the loss of inter-slice and intra-slice information separately generated from 2D and 3D networks, thereby improving feature representation ability and achieving satisfactory segmentation results. The proposed SSHSNet was validated on a publicly available spine MR image dataset, and remarkable segmentation performance was achieved. Moreover, results show that the proposed method has great potential in dealing with the data imbalance problem. Based on previous reports, few studies have incorporated a semi-supervised learning strategy with a cross attention mechanism for spine segmentation. Therefore, the proposed method may provide a useful tool for spine segmentation and aid clinically in spinal disease diagnoses and treatments. Codes are publicly available at: https://github.com/Meiyan88/SSHSNet.

Lumbar intervertebral disc segmentation for computer modeling and simulation

BACKGROUND AND OBJECTIVE

The present work had as its main objective the development of a method for localizing and automatically segmenting lumbar intervertebral discs (IVD) in 3D from magnetic resonance imaging (MRI), with the goal of supporting the generation of finite element (FE) models from actual lumbar spine anatomy, by providing accurate and personalized information on the shape of the patient's IVD. The extension of the method to allow performing separate segmentations of the IVD's two main structures - annulus fibrosus (AF) and nucleus pulposus (NP) - as well as automatically detecting degenerated IVD where this distinction is no longer possible was also an objective of the work.

METHODS

The method presented here evolves from 2D segmentations in the sagittal profile using Gabor filters towards 3D segmentations. It works by detecting the spine curves and intensity regions corresponding to IVD. As so, the 2D method from Zhu et al. (2013) was partially implemented, modified and adapted to 3D use, and then tested with eight spines from two separated online datasets. The 3D adaptation was achieved by using vertebral body segmentation masks to approximate the shape of the vertebrae and to adjust the spine curves accordingly.

RESULTS

The method showed average values of 85%, 83% and 96% for the Dice coefficient, sensitivity and specificity, respectively. The method correctly identified 65 of 68 (96%) IVD as either healthy or degenerated. The method's Dice coefficient is within the range of existing 3D IVD segmentation methods in the literature (81-92%). The method took on average 6-7 s to perform a full 3D segmentation, which is well within the range of the existing methods (2 s - 19 min).

CONCLUSIONS

The developed method can be used to generate accurate 3D models of the IVD based on MRI, with AF/NP distinction and detection of marked degeneration by comparing each IVD with the remaining spine levels. Further work shall improve the method towards distinguishing between specific levels of degeneration for clinically oriented FE modeling.

Artificial Intelligence in Spinal Imaging: Current Status and Future Directions

Spinal maladies are among the most common causes of pain and disability worldwide. Imaging represents an important diagnostic procedure in spinal care. Imaging investigations can provide information and insights that are not visible through ordinary visual inspection. Multiscale in vivo interrogation has the potential to improve the assessment and monitoring of pathologies thanks to the convergence of imaging, artificial intelligence (AI), and radiomic techniques. AI is revolutionizing computer vision, autonomous driving, natural language processing, and speech recognition. These revolutionary technologies are already impacting radiology, diagnostics, and other fields, where automated solutions can increase precision and reproducibility. In the first section of this narrative review, we provide a brief explanation of the many approaches currently being developed, with a particular emphasis on those employed in spinal imaging studies. The previously documented uses of AI for challenges involving spinal imaging, including imaging appropriateness and protocoling, image acquisition and reconstruction, image presentation, image interpretation, and quantitative image analysis, are then detailed. Finally, the future applications of AI to imaging of the spine are discussed. AI has the potential to significantly affect every step in spinal imaging. AI can make images of the spine more useful to patients and doctors by improving image quality, imaging efficiency, and diagnostic accuracy.

Spine-GFlow: A hybrid learning framework for robust multi-tissue segmentation in lumbar MRI without manual annotation

Most learning-based magnetic resonance image (MRI) segmentation methods rely on the manual annotation to provide supervision, which is extremely tedious, especially when multiple anatomical structures are required. In this work, we aim to develop a hybrid framework named Spine-GFlow that combines the image features learned by a CNN model and anatomical priors for multi-tissue segmentation in a sagittal lumbar MRI. Our framework does not require any manual annotation and is robust against image feature variation caused by different image settings and/or underlying pathology. Our contributions include: 1) a rule-based method that automatically generates the weak annotation (initial seed area), 2) a novel proposal generation method that integrates the multi-scale image features and anatomical prior, 3) a comprehensive loss for CNN training that optimizes the pixel classification and feature distribution simultaneously. Our Spine-GFlow has been validated on 2 independent datasets: HKDDC (containing images obtained from 3 different machines) and IVDM3Seg. The segmentation results of vertebral bodies (VB), intervertebral discs (IVD), and spinal canal (SC) are evaluated quantitatively using intersection over union (IoU) and the Dice coefficient. Results show that our method, without requiring manual annotation, has achieved a segmentation performance comparable to a model trained with full supervision (mean Dice 0.914 vs 0.916).

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.

Vertebrae, IVD and spinal canal boundary extraction on MRI, utilizing CT-trained active shape models

PURPOSE

Vertebrae, intervertebral disc (IVD) and spinal canal (SC) displacements are in the root of several spinal cord pathologies. The localization and boundary extraction of these structures, along with the quantification of their displacements, provide valuable clues for assessing each pathological condition. In this work, we propose a computational method for boundary extraction of vertebrae, IVD and SC in magnetic resonance images (MRI).

METHOD

Vertebrae shape priors derived from computed tomography (CT) images are used to guide vertebrae, IVD and SC boundary extraction in MRI. This strategy is dictated by three considerations: (1) CT is the modality of choice for highlighting solid structures such as vertebrae, (2) vertebrae boundaries indirectly impose constraints on the boundaries of neighbouring structures (IVD and SC), and (3) it can be observed that edges are similarly located in CT and MR images; therefore, gradient profiles and shape priors learned by active shape models (ASMs) from CT are also valid in MRI.

RESULTS

Experimental comparisons on two MR image datasets demonstrate that the proposed approach obtains segmentation results, which are comparable to the state of the art. Moreover, the adopted bimodal strategy is validated by demonstrating that CT-derived shape priors lead to more accurate boundary extraction than MRI-derived shape priors, even in the case of MR image applications.

CONCLUSION

Unlike existing bimodal methods, the proposed one is not dependent on the availability of CT/MR image pairs, which are not usually acquired from the same patient. In addition, unlike state-of-the-art deep learning-based methods, it is not dependent on large amounts of training data. The proposed method requires a limited amount of user intervention.

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.

Axial-SpineGAN: simultaneous segmentation and diagnosis of multiple spinal structures on axial magnetic resonance imaging images

Providing a simultaneous segmentation and diagnosis of the spinal structures on axial magnetic resonance imaging (MRI) images has significant value for subsequent pathological analyses and clinical treatments. However, this task remains challenging, owing to the significant structural diversity, subtle differences between normal and abnormal structures, implicit borders, and insufficient training data. In this study, we propose an innovative network framework called 'Axial-SpineGAN' comprising a generator, discriminator, and diagnostor, aiming to address the above challenges, and to achieve simultaneous segmentation and disease diagnosis for discs, neural foramens, thecal sacs, and posterior arches on axial MRI images. The generator employs an enhancing feature fusion module to generate discriminative features, i.e. to address the challenges regarding the significant structural diversity and subtle differences between normal and abnormal structures. An enhancing border alignment module is employed to obtain an accurate pixel classification of the implicit borders. The discriminator employs an adversarial learning module to effectively strengthen the higher-order spatial consistency, and to avoid overfitting owing to insufficient training data. The diagnostor employs an automated diagnosis module to provide automated recognition of spinal diseases. Extensive experiments demonstrate that these modules have positive effects on improving the segmentation and diagnosis accuracies. Additionally, the results indicate that Axial-SpineGAN has the highest Dice similarity coefficient (94.9% ± 1.8%) in terms of the segmentation accuracy and highest accuracy rate (93.9% ± 2.6%) in terms of the diagnosis accuracy, thereby outperforming existing state-of-the-art methods. Therefore, our proposed Axial-SpineGAN is effective and potential as a clinical tool for providing an automated segmentation and disease diagnosis for multiple spinal structures on MRI images.

SpineParseNet: Spine Parsing for Volumetric MR Image by a Two-Stage Segmentation Framework With Semantic Image Representation

Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this article, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments.

Bimodal CT/MRI-Based Segmentation Method for Intervertebral Disc Boundary Extraction

Intervertebral disc (IVD) localization and segmentation have triggered intensive research efforts in the medical image analysis community, since IVD abnormalities are strong indicators of various spinal cord-related pathologies. Despite the intensive research efforts to address IVD boundary extraction based on MR images, the potential of bimodal approaches, which benefit from complementary information derived from both magnetic resonance imaging (MRI) and computed tomography (CT), has not yet been fully realized. Furthermore, most existing approaches rely on manual intervention or on learning, although sufficiently large and labelled 3D datasets are not always available. In this light, this work introduces a bimodal segmentation method for vertebrae and IVD boundary extraction, which requires a limited amount of intervention and is not based on learning. The proposed method comprises various image processing and analysis stages, including CT/MRI registration, Otsu-based thresholding and Chan–Vese-based segmentation. The method was applied on 98 expert-annotated pairs of CT and MR spinal cord images with varying slice thicknesses and pixel sizes, which were obtained from 7 patients using different scanners. The experimental results had a Dice similarity coefficient equal to 94.77(%) for CT and 86.26(%) for MRI and a Hausdorff distance equal to 4.4 pixels for CT and 4.5 pixels for MRI. Experimental comparisons with state-of-the-art CT and MRI segmentation methods lead to the conclusion that the proposed method provides a reliable alternative for vertebrae and IVD boundary extraction. Moreover, the segmentation results are utilized to perform a bimodal visualization of the spine, which could potentially aid differential diagnosis with respect to several spine-related pathologies.

A comparison of classifiers in biomedical signal processing as a decision support system in disc hernia diagnosis

The aim of this research was to investigate the best methodology for disc hernia diagnosis using foot force measurements from the designed platform. Based on the subjective neurological examination that examines muscle weakness on the nerve endings of the skin area on feet and concludes about origins of nerve roots between spine discs, a platform for objective recordings of the aforementioned muscle weakness has been designed. The dataset included 33 patients with pre-diagnosed L4/L5 and L5/S1 disc hernia on the left or the right side, confirmed with the MRI scanning and neurological exam. We have implemented 5 different classifiers that were found to be the most suitable for smaller dataset and investigated the accuracy of classification depending on the normalization method, linearity/non-linearity of the algorithm, and dataset splitting variation (32-1, 31-2, 30-3, 29-4 patients for training and testing, respectively). The classifier is able to distinguish between four different diagnoses L4/L5 on the left side, L4/L5 on the right side, L5/S1 on the left side and L5/S1 on the right side, as well as to recognize healthy subjects (without disc herniation). The results show that non-linear algorithms achieved better accuracy in comparison to tested linear classifiers, suggesting the expected non-linear connection between the foot force values and the level of disc herniation. Two algorithms with highest accuracy turned out to be Decision Tree and Naïve Bayes, depending on the normalization method. The system is also able to record and recognize improvements in muscle weakness after surgical operation and physical therapy.

Lumbar intervertebral disc characterization through quantitative MRI analysis: An automatic voxel-based relaxometry approach

Purpose

To develop an automated pipeline based on convolutional neural networks to segment lumbar intervertebral discs and characterize their biochemical composition using voxel‐based relaxometry, and establish local associations with clinical measures of disability, muscle changes, and other symptoms of lower back pain.

Methods

This work proposes a new methodology using MRI (n = 31, across the spectrum of disc degeneration) that combines deep learning–based segmentation, atlas‐based registration, and statistical parametric mapping for voxel‐based analysis of T_1ρ and T₂ relaxation time maps to characterize disc degeneration and its associated disability.

Results

Across degenerative grades, the segmentation algorithm produced accurate, high‐confidence segmentations of the lumbar discs in two independent data sets. Manually and automatically extracted mean disc T_1ρ and T₂ relaxation times were in high agreement for all discs with minimal bias. On a voxel‐by‐voxel basis, imaging‐based degenerative grades were strongly negatively correlated with T_1ρ and T₂, particularly in the nucleus. Stratifying patients by disability grades revealed significant differences in the relaxation maps between minimal/moderate versus severe disability: The average T_1ρ relaxation maps from the minimal/moderate disability group showed clear annulus nucleus distinction with a visible midline, whereas the severe disability group had lower average T_1ρ values with a homogeneous distribution.

Conclusion

This work presented a scalable pipeline for fast, automated assessment of disc relaxation times, and voxel‐based relaxometry that overcomes limitations of current region of interest–based analysis methods and may enable greater insights and associations between disc degeneration, disability, and lower back pain.

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.

Combining convolutional neural networks and star convex cuts for fast whole spine vertebra segmentation in MRI

BACKGROUND AND OBJECTIVE

We propose an automatic approach for fast vertebral body segmentation in three-dimensional magnetic resonance images of the whole spine. Previous works are limited to the lower thoracolumbar section and often take minutes to compute, which is problematic in clinical routine, for study data sets with numerous subjects or when the cervical or upper thoracic spine is to be analyzed.

METHODS

We address these limitations by a novel graph cut formulation based on vertebra patches extracted along the spine. For each patch, our formulation incorporates appearance and shape information derived from a task-specific convolutional neural network as well as star-convexity constraints that ensure a topologically correct segmentation of each vertebra. When segmenting vertebrae individually, ambiguities will occur due to overlapping segmentations of adjacent vertebrae. We tackle this problem by novel non-overlap constraints between neighboring patches based on so-called encoding swaps. The latter allow us to obtain a globally optimal multi-label segmentation of all vertebrae in polynomial time.

RESULTS

We validated our approach on two data sets. The first contains T₁- and T₂-weighted whole spine images of 64 subjects with varying health conditions. The second comprises 23 T₂-weighted thoracolumbar images of young healthy adults and is publicly available. Our method yielded Dice coefficients of 93.8  ±  2.6% and 96.0  ±  1.0% for both data sets with a run time of 1.35  ±  0.08 s and 0.90  ±  0.03 s per vertebra on consumer hardware. A complete whole spine segmentation took 32.4 ± 1.92 s on average.

CONCLUSIONS

Our results are superior to those of previous works at a fraction of their run time, which illustrates the efficiency and effectiveness of our whole spine segmentation approach.

Artificial intelligence and machine learning in spine research

Artificial intelligence (AI) and machine learning (ML) techniques are revolutionizing several industrial and research fields like computer vision, autonomous driving, natural language processing, and speech recognition. These novel tools are already having a major impact in radiology, diagnostics, and many other fields in which the availability of automated solution may benefit the accuracy and repeatability of the execution of critical tasks. In this narrative review, we first present a brief description of the various techniques that are being developed nowadays, with special focus on those used in spine research. Then, we describe the applications of AI and ML to problems related to the spine which have been published so far, including the localization of vertebrae and discs in radiological images, image segmentation, computer-aided diagnosis, prediction of clinical outcomes and complications, decision support systems, content-based image retrieval, biomechanics, and motion analysis. Finally, we briefly discuss major ethical issues related to the use of AI in healthcare, namely, accountability, risk of biased decisions as well as data privacy and security, which are nowadays being debated in the scientific community and by regulatory agencies.

Is the location of the signal intensity weighted centroid a reliable measurement of fluid displacement within the disc?

Degenerated discs have shorter T2-relaxation time and lower MR signal. The location of the signal-intensity-weighted-centroid reflects the water distribution within a region-of-interest (ROI). This study compared the reliability of the location of the signal-intensity-weighted-centroid to mean signal intensity and area measurements. L4-L5 and L5-S1 discs were measured on 43 mid-sagittal T2-weighted 3T MRI images in adults with back pain. One rater analysed images twice and another once, blinded to measurements. Discs were semi-automatically segmented into a whole disc, nucleus, anterior and posterior annulus. The coordinates of the signal-intensity-weighted-centroid for all regions demonstrated excellent intraclass-correlation-coefficients for intra- (0.99-1.00) and inter-rater reliability (0.97-1.00). The standard error of measurement for the Y-coordinates of the signal-intensity-weighted-centroid for all ROIs were 0 at both levels and 0 to 2.7 mm for X-coordinates. The mean signal intensity and area for the whole disc and nucleus presented excellent intra-rater reliability with intraclass-correlation-coefficients from 0.93 to 1.00, and 0.92 to 1.00 for inter-rater reliability. The mean signal intensity and area had lower reliability for annulus ROIs, with intra-rater intraclass-correlation-coefficient from 0.5 to 0.76 and inter-rater from 0.33 to 0.58. The location of the signal-intensity-weighted-centroid is a reliable biomarker for investigating the effects of disc interventions.

Simultaneous Volumetric Segmentation of Vertebral Bodies and Intervertebral Discs on Fat-Water MR Images

Fat-water magnetic resonance (MR) images allow automated noninvasive analysis of morphological properties and fat fractions of vertebral bodies (VBs) and intervertebral discs (IVDs) that constitute an important part of human biomechanical systems. In this paper, we propose a fully automated approach for simultaneously segmenting multiple VBs and IVDs on fat-water MR images without prior localization or geometry estimation. This method involved a hierarchical random forest (HRF) classifier and a hierarchical conditional random field (HCRF) that encoded a multi-resolution image pyramid based on a set of multiscale local and contextual features. The HRF classifier employed penalized multivariate linear discriminants and SMOTEBagging to handle limited and imbalanced training data with large feature dimension. The HCRF estimated optimum labels according to their spatial and hierarchical consistencies by using the layer-wise significant features determined over the trained HRF classifier. To handle variable sample numbers at different resolutions, resolution-specific hyperparameters were used. This method was trained and evaluated for segmenting 15 thoracic and lumbar VBs and their IVDs on fat-water MR images of a subset of a large cohort data set. It was further evaluated for segmenting seven IVDs of the lower spine on fat-water images of a public grand challenge. These evaluations revealed the comparable accuracy of this method with the state-of-the-art while requiring less computational burden due to a simultaneous localization and segmentation.

Automatic Spine Tissue Segmentation from MRI Data Based on Cascade of Boosted Classifiers and Active Appearance Model

The study introduces a novel method for automatic segmentation of vertebral column tissue from MRI images. The paper describes a method that combines multiple stages of Machine Learning techniques to recognize and separate different tissues of the human spine. For the needs of this paper, 50 MRI examinations presenting lumbosacral spine of patients with low back pain were selected. After the initial filtration, automatic vertebrae recognition using Cascade Classifier takes place. Afterwards the main segmentation process using the patch based Active Appearance Model is performed. Obtained results are interpolated using centripetal Catmull–Rom splines. The method was tested on previously unseen vertebrae images segmented manually by 5 physicians. A test validating algorithm convergence per iteration was performed and the Intraclass Correlation Coefficient was calculated. Additionally, the 10-fold cross-validation analysis has been done. Presented method proved to be comparable to the physicians (FF = 90.19 ± 1.01%). Moreover results confirmed a proper algorithm convergence. Automatically segmented area correlated well with manual segmentation for single measurements (r¯=0.8336) and for average measurements (r¯=0.9068) with p = 0.05. The 10-fold cross-validation analysis (FF = 91.37 ± 1.13%) confirmed a good model generalization resulting in practical performance.

Vertebral body segmentation in wide range clinical routine spine MRI data

BACKGROUND AND OBJECTIVE

In this work we propose a 3D vertebral body segmentation approach for clinical magnetic resonance (MR) spine imaging. So far, vertebrae segmentation approaches in MR spine imaging are either limited to particular MR imaging sequences or require minutes to compute, which can be hindering in clinical routine. The major contribution of our work is a reasonably precise segmentation result, within seconds and with minimal user interaction, for spine MR imaging commonly used in clinical routine. Our focus lies on the applicability towards a large variety of clinical MR imaging sequences, dealing with low image quality, high anisotropy and spine pathologies.

METHODS

Our method starts with a intensity correction step to deal with bias field artifacts and a minimal user-assisted initialization. Next, appearance-based vertebral body probability maps guide a subsequent hybrid level-set segmentation.

RESULTS

We tested our method on different MR imaging sequences from 48 subjects. Overall, our evaluation set contains 63 datasets including 419 vertebral bodies, which differ in age, sex and presence of spine pathologies. This is the largest set of reference segmentations of clinical routine spine MR imaging so far. We achieved a Dice coefficient of 86.0%, a mean Euclidean surface distance error of 1.59 ± 0.24 mm and a Hausdorff distance of 6.86 mm.

CONCLUSIONS

These results illustrate the robustness of our segmentation approach towards the variety of MR image data, which is a pivotal aspect for clinical usefulness and reliable diagnosis.

A Semi-automated Approach to Improve the Efficiency of Medical Imaging Segmentation for Haptic Rendering

The Sensimmer platform represents our ongoing research on simultaneous haptics and graphics rendering of 3D models. For simulation of medical and surgical procedures using Sensimmer, 3D models must be obtained from medical imaging data, such as magnetic resonance imaging (MRI) or computed tomography (CT). Image segmentation techniques are used to determine the anatomies of interest from the images. 3D models are obtained from segmentation and their triangle reduction is required for graphics and haptics rendering. This paper focuses on creating 3D models by automating the segmentation of CT images based on the pixel contrast for integrating the interface between Sensimmer and medical imaging devices, using the volumetric approach, Hough transform method, and manual centering method. Hence, automating the process has reduced the segmentation time by 56.35% while maintaining the same accuracy of the output at ±2 voxels.

Multi-Parameter Ensemble Learning for Automated Vertebral Body Segmentation in Heterogeneously Acquired Clinical MR Images

The development of quantitative imaging biomarkers in medicine requires automatic delineation of relevant anatomical structures using available imaging data. However, this task is complicated in clinical medicine due to the variation in scanning parameters and protocols, even within a single medical center. Existing literature on automatic image segmentation using MR data is based on the analysis of highly homogenous images obtained using a fixed set of pulse sequence parameters (TR/TE). Unfortunately, algorithms that operate on fixed scanning parameters do not avail themselves to real-world daily clinical use due to the existing variation in scanning parameters and protocols. Thus, it is necessary to develop algorithmic techniques that can address the challenge of MR image segmentation using real clinical data. Toward this goal, we developed a multi-parametric ensemble learning technique to automatically detect and segment lumbar vertebral bodies using MR images of the spine. We use spine imaging data to illustrate our techniques since low back pain is an extremely common condition and a typical spine clinic evaluates patients that have been referred with a wide range of scanning parameters. This method was designed with special emphasis on robustness so that it can perform well despite the inherent variation in scanning protocols. Specifically, we show how a single multi-parameter ensemble model trained with manually labeled T2 scans can autonomously segment vertebral bodies on scans with echo times varying between 24 and 147 ms and relaxation times varying between 1500 and 7810 ms. Furthermore, even though the model was trained using T2-MR imaging data, it can accurately segment vertebral bodies on T1-MR and CT, further demonstrating the robustness and versatility of our methodology. We believe that robust segmentation techniques, such as the one presented here, are necessary for translating computer assisted diagnosis into everyday clinical practice.

A multi-resolution approach for spinal metastasis detection using deep Siamese neural networks

Spinal metastasis, a metastatic cancer of the spine, is the most common malignant disease in the spine. In this study, we investigate the feasibility of automated spinal metastasis detection in magnetic resonance imaging (MRI) by using deep learning methods. To accommodate the large variability in metastatic lesion sizes, we develop a Siamese deep neural network approach comprising three identical subnetworks for multi-resolution analysis and detection of spinal metastasis. At each location of interest, three image patches at three different resolutions are extracted and used as the input to the networks. To further reduce the false positives (FPs), we leverage the similarity between neighboring MRI slices, and adopt a weighted averaging strategy to aggregate the results obtained by the Siamese neural networks. The detection performance is evaluated on a set of 26 cases using a free-response receiver operating characteristic (FROC) analysis. The results show that the proposed approach correctly detects all the spinal metastatic lesions while producing only 0.40 FPs per case. At a true positive (TP) rate of 90%, the use of the aggregation reduces the FPs from 0.375 FPs per case to 0.207 FPs per case, a nearly 44.8% reduction. The results indicate that the proposed Siamese neural network method, combined with the aggregation strategy, provide a viable strategy for the automated detection of spinal metastasis in MRI images.

Statistical shape models of cuboid, navicular and talus bones

BACKGROUND

The aim was to develop statistical shape models of the main human tarsal bones that would result in novel representations of cuboid, navicular and talus.

METHODS

Fifteen right and 15 left retrospectively collected computed tomography data sets from male individuals, aged from 17 to 63 years, with no known foot pathology were collected. Data were gathered from 30 different subjects. A process of model building includes image segmentation, unifying feature position, mathematical shape description and obtaining statistical shape geometry.

RESULTS

Orthogonal decomposition of bone shapes utilising spherical harmonics was employed providing means for unique parametric representation of each bone. Cross-validated classification results based on parametric spherical harmonics representation showed high sensitivity and high specificity greater than 0.98 for all considered bones.

CONCLUSIONS

The statistical shape models of cuboid, navicular and talus created in this work correspond to anatomically accurate atlases that have not been previously considered. The study indicates high clinical potential of statistical shape modelling in the characterisation of tarsal bones. Those novel models can be applied in medical image analysis, orthopaedics and biomechanics in order to provide support for preoperative planning, better diagnosis or implant design.

Registration of MRI to intraoperative radiographs for target localization in spinal interventions

Decision support to assist in target vertebra localization could provide a useful aid to safe and effective spine surgery. Previous solutions have shown 3D-2D registration of preoperative CT to intraoperative radiographs to reliably annotate vertebral labels for assistance during level localization. We present an algorithm (referred to as MR-LevelCheck) to perform 3D-2D registration based on a preoperative MRI to accommodate the increasingly common clinical scenario in which MRI is used instead of CT for preoperative planning. Straightforward adaptation of gradient/intensity-based methods appropriate to CT-to-radiograph registration is confounded by large mismatch and noncorrespondence in image intensity between MRI and radiographs. The proposed method overcomes such challenges with a simple vertebrae segmentation step using vertebra centroids as seed points (automatically defined within existing workflow). Forwards projections are computed using segmented MRI and registered to radiographs via gradient orientation (GO) similarity and the CMA-ES (covariance-matrix-adaptation evolutionary-strategy) optimizer. The method was tested in an IRB-approved study involving 10 patients undergoing cervical, thoracic, or lumbar spine surgery following preoperative MRI. The method successfully registered each preoperative MRI to intraoperative radiographs and maintained desirable properties of robustness against image content mismatch and large capture range. Robust registration performance was achieved with projection distance error (PDE) (median  ±  IQR)  =  4.3  ±  2.6 mm (median  ±  IQR) and 0% failure rate. Segmentation accuracy for the continuous max-flow method yielded dice coefficient  =  88.1  ±  5.2, accuracy  =  90.6  ±  5.7, RMSE  =  1.8  ±  0.6 mm, and contour affinity ratio (CAR)  =  0.82  ±  0.08. Registration performance was found to be robust for segmentation methods exhibiting RMSE  <3 mm and CAR  >0.50. The MR-LevelCheck method provides a potentially valuable extension to a previously developed decision support tool for spine surgery target localization by extending its utility to preoperative MRI while maintaining characteristics of accuracy and robustness.

Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge

The evaluation of changes in Intervertebral Discs (IVDs) with 3D Magnetic Resonance (MR) Imaging (MRI) can be of interest for many clinical applications. This paper presents the evaluation of both IVD localization and IVD segmentation methods submitted to the Automatic 3D MRI IVD Localization and Segmentation challenge, held at the 2015 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2015) with an on-site competition. With the construction of a manually annotated reference data set composed of 25 3D T2-weighted MR images acquired from two different studies and the establishment of a standard validation framework, quantitative evaluation was performed to compare the results of methods submitted to the challenge. Experimental results show that overall the best localization method achieves a mean localization distance of 0.8 mm and the best segmentation method achieves a mean Dice of 91.8%, a mean average absolute distance of 1.1 mm and a mean Hausdorff distance of 4.3 mm, respectively. The strengths and drawbacks of each method are discussed, which provides insights into the performance of different IVD localization and segmentation methods.

Segmentation of joint and musculoskeletal tissue in the study of arthritis

As the most frequent cause of physical disability, musculoskeletal diseases such as arthritis and osteoporosis have a great social and economical impact. Quantitative magnetic resonance imaging (MRI) biomarkers are important tools that allow clinicians to better characterize, monitor, and even predict musculoskeletal disease progression. Post-processing pipelines often include image segmentation. Manually identifying the border of the region of interest (ROI) is a difficult and time-consuming task. Manual segmentation is also affected by inter- and intrauser variability, thus limiting standardization. Fully automatic or semi-automatic methods that minimize the user interaction are highly desirable. Unfortunately, an ultimate, highly reliable and extensively evaluated solution for joint and musculoskeletal tissue segmentation has not yet been proposed, and many clinical studies still adopt fully manual procedures. Moreover, the clinical translation of several promising quantitative MRI techniques is highly affected by the lack of an established, fast, and accurate segmentation method. The goal of this review is to present some of the techniques proposed in recent literature that have been adopted in clinical studies for joint and musculoskeletal tissue analyses in arthritis patients. The most widely used MRI sequences and image processing algorithms employed to accomplish segmentation challenges will be discussed in this paper.

A method of localization and segmentation of intervertebral discs in spine MRI based on Gabor filter bank

BACKGROUND

Spine magnetic resonance image (MRI) plays a very important role in the diagnosis of various spinal diseases, such as disc degeneration, scoliosis, and osteoporosis. Accurate localization and segmentation of the intervertebral disc (IVD) in spine MRI can help accelerate the diagnosis time and assist in the treatment by providing quantitative parameters. In this paper, a method based on Gabor filter bank is proposed for IVD localization and segmentation.

METHODS

First, the structural features of IVDs are extracted using a Gabor filter bank. Second, the Gabor features of spine are calculated and spinal curves are detected. Third, the Gabor feature images (GFI) of IVDs are calculated and adjusted according to the spinal curves. Fourth, the IVDs are localized by clustering analysis with GFI. Finally, an optimum grayscale-based algorithm with self-adaptive threshold, combined with the localization results and Gabor features of the spine, is performed for IVDs segmentation.

RESULTS

The proposed method is verified by an MRI dataset consisting of 278 IVDs from 37 patients. The accuracy of localization is 98.23 % and the dice similarity index for segmentation evaluation is 0.9237.

CONCLUSIONS

The proposed Gabor filter based method is effective for IVD localization and segmentation. It would be useful in computer-aided diagnosis of IVD diseases and computer-assisted spine surgery.

A Nondestructive Method to Distinguish the Internal Constituent Architecture of the Intervertebral Discs Using 9.4 Tesla Magnetic Resonance Imaging

STUDY DESIGN

An in vitro study of the intervertebral disc (IVD) structure using 9.4T magnetic resonance imaging (MRI).

OBJECTIVE

Investigate the potential of ultrahigh-field strength MRI for higher quality 3-dimensional (3D) volumetric MRI datasets of the IVD to better distinguish structural details.

SUMMARY OF BACKGROUND DATA

MRI has the advantages of being nondestructive and 3D in comparison to most techniques used to obtain the structural details of biological tissues, however, its poor image quality at higher resolution is a limiting factor. Ultrahigh-field MRI could improve the imaging of biological tissues but the current understanding of its application for spinal tissue is limited.

METHODS

2 ovine spinal segments (C7-T1, T2-T3) containing the IVD were separately imaged using 2 sequences; 3D spin echo (multislice-multiecho) pulse sequence for the C7-T1 sample and 3D gradient echo (fast-low-angle-shot) pulse sequence for the T2-T3 sample. The C7-T1 sample was subsequently decalcified and imaged again using the same scanning parameters. Histological sections obtained from the decalcified sample were stained followed by digital scanning. Observations from corresponding MRI slices and histological sections were compared as a method of confirmation of morphology captured under MRI. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and relative-contrast values were calculated for quantitative evaluation of image quality.

RESULTS

Measurements from histology sections and corresponding MRI slices matched well. Both sequences revealed finer details of the IVD structure. Under the spin echo sequence, the annulus lamellae architecture was distinguishable and the SNR and CNR values were higher. The relative contrast was considerably higher between high (nucleus) and low (bone) signal constituents, but between the nucleus and the annulus the relative contrast was low. Under the gradient echo sequence, although the relative contrasts between constituents were poor, the fiber orientation was clearly manifested.

CONCLUSION

The obtained positive results demonstrate the potential of ultrahigh-field strength MRI to nondestructively capture the IVD structure.

LEVEL OF EVIDENCE

N/A.

VolHOG: a volumetric object recognition approach based on bivariate histograms of oriented gradients for vertebra detection in cervical spine MRI

PURPOSE

The automatic recognition of vertebrae in volumetric images is an important step toward automatic spinal diagnosis and therapy support systems. There are many applications such as the detection of pathologies and segmentation which would benefit from automatic initialization by the detection of vertebrae. One possible application is the initialization of local vertebral segmentation methods, eliminating the need for manual initialization by a human operator. Automating the initialization process would optimize the clinical workflow. However, automatic vertebra recognition in magnetic resonance (MR) images is a challenging task due to noise in images, pathological deformations of the spine, and image contrast variations.

METHODS

This work presents a fully automatic algorithm for 3D cervical vertebra detection in MR images. We propose a machine learning method for cervical vertebra detection based on new features combined with a linear support vector machine for classification. An algorithm for bivariate gradient orientation histogram generation from three-dimensional raster image data is introduced which allows us to describe three-dimensional objects using the authors' proposed bivariate histograms.

RESULTS

A detailed performance evaluation on 21 T2-weighted MR images of the cervical vertebral region is given. A single model for cervical vertebrae C3-C7 is generated and evaluated. The results show that the generic model performs equally well for each of the cervical vertebrae C3-C7. The algorithm's performance is also evaluated on images containing various levels of artificial noise. The results indicate that the proposed algorithm achieves good results despite the presence of severe image noise.

CONCLUSIONS

The proposed detection method delivers accurate locations of cervical vertebrae in MR images which can be used in diagnosis and therapy. In order to achieve absolute comparability with the results of future work, the authors are following an open data approach by making the image dataset used in their performance evaluation available to the public.

Statistical Interspace Models (SIMs): Application to Robust 3D Spine Segmentation

Statistical shape models (SSM) are used to introduce shape priors in the segmentation of medical images. However, such models require large training datasets in the case of multi-object structures, since it is required to obtain not only the individual shape variations but also the relative position and orientation among objects. A solution to overcome this limitation is to model each individual shape independently. However, this approach does not take into account the relative position, orientations and shapes among the parts of an articulated object, which may result in unrealistic geometries, such as with object overlaps. In this article, we propose a new Statistical Model, the Statistical Interspace Model (SIM), which provides information about the interaction of all the individual structures by modeling the interspace between them. The SIM is described using relative position vectors between pair of points that belong to different objects that are facing each other. These vectors are divided into their magnitude and direction, each of these groups modeled as independent manifolds. The SIM was included in a segmentation framework that contains an SSM per individual object. This framework was tested using three distinct types of datasets of CT images of the spine. Results show that the SIM completely eliminated the inter-process overlap while improving the segmentation accuracy.

Statistical shape model reconstruction with sparse anomalous deformations: Application to intervertebral disc herniation

Many medical image processing techniques rely on accurate shape modeling of anatomical features. The presence of shape abnormalities challenges traditional processing algorithms based on strong morphological priors. In this work, a sparse shape reconstruction from a statistical shape model is presented. It combines the advantages of traditional statistical shape models (defining a 'normal' shape space) and previously presented sparse shape composition (providing localized descriptors of anomalies). The algorithm was incorporated into our image segmentation and classification software. Evaluation was performed on simulated and clinical MRI data from 22 sciatica patients with intervertebral disc herniation, containing 35 herniated and 97 normal discs. Moderate to high correlation (R=0.73) was achieved between simulated and detected herniations. The sparse reconstruction provided novel quantitative features describing the herniation morphology and MRI signal appearance in three dimensions (3D). The proposed descriptors of local disc morphology resulted to the 3D segmentation accuracy of 1.07±1.00mm (mean absolute vertex-to-vertex mesh distance over the posterior disc region), and improved the intervertebral disc classification from 0.888 to 0.931 (area under receiver operating curve). The results show that the sparse shape reconstruction may improve computer-aided diagnosis of pathological conditions presenting local morphological alterations, as seen in intervertebral disc herniation.

Validity and reliability of computerized measurement of lumbar intervertebral disc height and volume from magnetic resonance images

BACKGROUND CONTEXT

Magnetic resonance (MR) examinations of morphologic characteristics of intervertebral discs (IVDs) have been used extensively for biomechanical studies and clinical investigations of the lumbar spine. Traditionally, the morphologic measurements have been performed using time- and expertise-intensive manual segmentation techniques not well suited for analyses of large-scale studies..

PURPOSE

The purpose of this study is to introduce and validate a semiautomated method for measuring IVD height and mean sagittal area (and volume) from MR images to determine if it can replace the manual assessment and enable analyses of large MR cohorts.

STUDY DESIGN/SETTING

This study compares semiautomated and manual measurements and assesses their reliability and agreement using data from repeated MR examinations.

METHODS

Seven healthy asymptomatic males underwent 1.5-T MR examinations of the lumbar spine involving sagittal T2-weighted fast spin-echo images obtained at baseline, pre-exercise, and postexercise conditions. Measures of the mean height and the mean sagittal area of lumbar IVDs (L1-L2 to L4-L5) were compared for two segmentation approaches: a conventional manual method (10-15 minutes to process one IVD) and a specifically developed semiautomated method (requiring only a few mouse clicks to process each subject).

RESULTS

Both methods showed strong test-retest reproducibility evaluated on baseline and pre-exercise examinations with strong intraclass correlations for the semiautomated and manual methods for mean IVD height (intraclass correlation coefficient [ICC]=0.99, 0.98) and mean IVD area (ICC=0.98, 0.99), respectively. A bias (average deviation) of 0.38 mm (4.1%, 95% confidence interval 0.18-0.59 mm) was observed between the manual and semiautomated methods for the IVD height, whereas there was no statistically significant difference for the mean IVD area (0.1%±3.5%). The semiautomated and manual methods both detected significant exercise-induced changes in IVD height (0.20 and 0.28 mm) and mean IVD area (5.7 and 8.3 mm(2)), respectively.

CONCLUSIONS

The presented semiautomated method provides an alternative to time- and expertise-intensive manual procedures for analysis of larger, cross-sectional, interventional, and longitudinal MR studies for morphometric analyses of lumbar IVDs.

Automated segmentation and analysis of normal and osteoarthritic knee menisci from magnetic resonance images--data from the Osteoarthritis Initiative

OBJECTIVE

To validate an automatic scheme for the segmentation and quantitative analysis of the medial meniscus (MM) and lateral meniscus (LM) in magnetic resonance (MR) images of the knee.

METHOD

We analysed sagittal water-excited double-echo steady-state MR images of the knee from a subset of the Osteoarthritis Initiative (OAI) cohort. The MM and LM were automatically segmented in the MR images based on a deformable model approach. Quantitative parameters including volume, subluxation and tibial-coverage were automatically calculated for comparison (Wilcoxon tests) between knees with variable radiographic osteoarthritis (rOA), medial and lateral joint space narrowing (mJSN, lJSN) and pain. Automatic segmentations and estimated parameters were evaluated for accuracy using manual delineations of the menisci in 88 pathological knee MR examinations at baseline and 12 months time-points.

RESULTS

The median (95% confidence-interval (CI)) Dice similarity index (DSI) (2 ∗|Auto ∩ Manual|/(|Auto|+|Manual|)∗ 100) between manual and automated segmentations for the MM and LM volumes were 78.3% (75.0-78.7), 83.9% (82.1-83.9) at baseline and 75.3% (72.8-76.9), 83.0% (81.6-83.5) at 12 months. Pearson coefficients between automatic and manual segmentation parameters ranged from r = 0.70 to r = 0.92. MM in rOA/mJSN knees had significantly greater subluxation and smaller tibial-coverage than no-rOA/no-mJSN knees. LM in rOA knees had significantly greater volumes and tibial-coverage than no-rOA knees.

CONCLUSION

Our automated method successfully segmented the menisci in normal and osteoarthritic knee MR images and detected meaningful morphological differences with respect to rOA and joint space narrowing (JSN). Our approach will facilitate analyses of the menisci in prospective MR cohorts such as the OAI for investigations into pathophysiological changes occurring in early osteoarthritis (OA) development.

3D lumbar spine intervertebral disc segmentation and compression simulation from MRI using shape-aware models

PURPOSE

More accurate and robust image segmentations are needed for identification of spine pathologies and to assist with spine surgery planning and simulation. A framework for 3D segmentation of healthy and herniated intervertebral discs from T2-weighted magnetic resonance imaging was developed that exploits weak shape priors encoded in simplex mesh active surface models.

METHODS

Weak shape priors inherent in simplex mesh deformable models have been exploited to automatically segment intervertebral discs. An ellipsoidal simplex template mesh was initialized within the disc image boundary through affine landmark-based registration and was allowed to deform according to image gradient forces. Coarse-to-fine multi-resolution approach was adopted in conjunction with decreasing shape memory forces to accurately capture the disc boundary. User intervention is allowed to turn off the shape feature and guide model deformation when the internal simplex shape memory influence hinders detection of pathology. A resulting surface mesh was utilized for disc compression simulation under gravitational and weight loads using Simulation Open Framework Architecture. For testing, 16 healthy discs were automatically segmented, and five pathological discs were segmented with minimal supervision.

RESULTS

Segmentation results were validated against expert guided segmentation and demonstrate mean absolute shape distance error of <1 mm. Healthy intervertebral disc compression simulation resulted in a bulging disc under vertical pressure of 100 N/cm(2).

CONCLUSION

This study presents the application of a simplex active surface model featuring weak shape priors for 3D segmentation of healthy as well as herniated discs. A framework was developed that enables the application of shape priors in the healthy part of disc anatomy, with user intervention when the priors were inapplicable. The surface-mesh-based segmentation method is part of a processing pipeline for anatomical modelling to support interactive surgery simulation.

Statistical shape and appearance models in osteoporosis

Statistical models (SMs) of shape (SSM) and appearance (SAM) have been acquiring popularity in medical image analysis since they were introduced in the early 1990s. They have been primarily used for segmentation, but they are also a powerful tool for 3D reconstruction and classification. All these tasks may be required in the osteoporosis domain, where fracture detection and risk estimation are key to reducing the mortality and/or morbidity of this bone disease. In this article, we review the different applications of SSMs and SAMs in the context of osteoporosis, and it concludes with a discussion of their advantages and disadvantages for this application.

Cortical shell unwrapping for vertebral body abnormality detection on computed tomography

The vertebral body is the main axial load-bearing structure of the spinal vertebra. Assessment of acute injury and chronic deformity of the vertebral body is difficult to assess accurately and quantitatively by simple visual inspection. We propose a cortical shell unwrapping method to examine the vertebral body for injury such as fractures and degenerative osteophytes. The spine is first segmented and partitioned into vertebrae. Then the cortical shell of the vertebral body is extracted using deformable dual-surface models. The cortical shell is then unwrapped onto a 2D map and the complex 3D detection problem is effectively converted to a pattern recognition problem on a 2D plane. Characteristic features adapted for different applications are computed and sent to a committee of support vector machines for classification. The system was evaluated on two applications, one for fracture detection on trauma CT datasets and the other on degenerative osteophyte assessment on sodium fluoride PET/CT. The fracture CAD achieved 93.6% sensitivity at 3.2 false positive per patient and the degenerative osteophyte CAD achieved 82% sensitivity at 4.7 false positive per patient.

Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images

BACKGROUND AND OBJECTIVES

Advances in MRI hardware and sequences are continually increasing the amount and complexity of data such as those generated in high-resolution three-dimensional (3D) scanning of the spine. Efficient informatics tools offer considerable opportunities for research and clinically based analyses of magnetic resonance studies. In this work, we present and validate a suite of informatics tools for automated detection of degenerative changes in lumbar intervertebral discs (IVD) from both 3D isotropic and routine two-dimensional (2D) clinical T2-weighted MRI.

MATERIALS AND METHODS

An automated segmentation approach was used to extract morphological (traditional 2D radiological measures and novel 3D shape descriptors) and signal appearance (extracted from signal intensity histograms) features. The features were validated against manual reference, compared between 2D and 3D MRI scans and used for quantification and classification of IVD degeneration across magnetic resonance datasets containing IVD with early and advanced stages of degeneration.

RESULTS AND CONCLUSIONS

Combination of the novel 3D-based shape and signal intensity features on 3D (area under receiver operating curve (AUC) 0.984) and 2D (AUC 0.988) magnetic resonance data deliver a significant improvement in automated classification of IVD degeneration, compared to the combination of previously used 2D radiological measurement and signal intensity features (AUC 0.976 and 0.983, respectively). Further work is required regarding the usefulness of 2D and 3D shape data in relation to clinical scores of lower back pain. The results reveal the potential of the proposed informatics system for computer-aided IVD diagnosis from MRI in large-scale research studies and as a possible adjunct for clinical diagnosis.