Spinopelvic measurements of sagittal balance with deep learning: systematic review and critical evaluation.

PURPOSE: To summarize and critically evaluate the existing studies for spinopelvic measurements of sagittal balance that are based on deep learning (DL). METHODS: Three databases (PubMed, WoS and Scopus) were queried for records using keywords related to DL and measurement of sagittal balance. After screening the resulting 529 records that were augmented with specific web search, 34 studies published between 2017 and 2022 were included in the final review, and evaluated from the perspective of the observed sagittal spinopelvic parameters, properties of spine image datasets, applied DL methodology and resulting measurement performance. RESULTS: Studies reported DL measurement of up to 18 different spinopelvic parameters, but the actual number depended on the image field of view. Image datasets were composed of lateral lumbar spine and whole spine X-rays, biplanar whole spine X-rays and lumbar spine magnetic resonance cross sections, and were increasing in size or enriched by augmentation techniques. Spinopelvic parameter measurement was approached either by landmark detection or structure segmentation, and U-Net was the most frequently applied DL architecture. The latest DL methods achieved excellent performance in terms of mean absolute error against reference manual measurements (~ 2° or ~ 1 mm). CONCLUSION: Although the application of relatively complex DL architectures resulted in an improved measurement accuracy of sagittal spinopelvic parameters, future methods should focus on multi-institution and multi-observer analyses as well as uncertainty estimation and error handling implementations for integration into the clinical workflow. Further advances will enhance the predictive analytics of DL methods for spinopelvic parameter measurement. LEVEL OF EVIDENCE I: Diagnostic: individual cross-sectional studies with the consistently applied reference standard and blinding.

A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation.

PURPOSE: To propose a fully automated deep learning (DL) framework for the vertebral morphometry and Cobb angle measurement from three-dimensional (3D) computed tomography (CT) images of the spine, and validate the proposed framework on an external database. METHODS: The vertebrae were first localized and segmented in each 3D CT image using a DL architecture based on an ensemble of U-Nets, and then automated vertebral morphometry in the form of vertebral body (VB) and intervertebral disk (IVD) heights, and spinal curvature measurements in the form of coronal and sagittal Cobb angles (thoracic kyphosis and lumbar lordosis) were performed using dedicated machine learning techniques. The framework was trained on 1725 vertebrae from 160 CT images and validated on an external database of 157 vertebrae from 15 CT images. RESULTS: The resulting mean absolute errors (± standard deviation) between the obtained DL and corresponding manual measurements were 1.17 ± 0.40 mm for VB heights, 0.54 ± 0.21 mm for IVD heights, and 3.42 ± 1.36° for coronal and sagittal Cobb angles, with respective maximal absolute errors of 2.51 mm, 1.64 mm, and 5.52°. Linear regression revealed excellent agreement, with Pearson's correlation coefficient of 0.943, 0.928, and 0.996, respectively. CONCLUSION: The obtained results are within the range of values, obtained by existing DL approaches without external validation. The results therefore confirm the scalability of the proposed DL framework from the perspective of application to external data, and time and computational resource consumption required for framework training.

A deep learning tool for fully automated measurements of sagittal spinopelvic balance from X-ray images: performance evaluation.

PURPOSE: The purpose of this study is to evaluate the performance of a novel deep learning (DL) tool for fully automated measurements of the sagittal spinopelvic balance from X-ray images of the spine in comparison with manual measurements. METHODS: Ninety-seven conventional upright sagittal X-ray images from 55 subjects were retrospectively included in this study. Measurements of the parameters of the sagittal spinopelvic balance, i.e., the sacral slope (SS), pelvic tilt (PT), spinal tilt (ST), pelvic incidence (PI) and spinosacral angle (SSA), were obtained manually by identifying specific anatomical landmarks using the SurgiMap Spine software and by the fully automated DL tool. Statistical analysis was performed in terms of the mean absolute difference (MAD), standard deviation (SD) and Pearson correlation, while the paired t test was used to search for statistically significant differences between manual and automated measurements. RESULTS: The differences between reference manual measurements and those obtained automatically by the DL tool were, respectively, for SS, PT, ST, PI and SSA, equal to 5.0° (3.4°), 2.7° (2.5°), 1.2° (1.2°), 5.5° (4.2°) and 5.0° (3.5°) in terms of MAD (SD), with a statistically significant corresponding Pearson correlation of 0.73, 0.90, 0.95, 0.81 and 0.71. No statistically significant differences were observed between the two types of measurement (p value always above 0.05). CONCLUSION: The differences between measurements are in the range of the observer variability of manual measurements, indicating that the DL tool can provide clinically equivalent measurements in terms of accuracy but superior measurements in terms of cost-effectiveness, reliability and reproducibility.

Three-dimensional pelvic incidence is much higher in (thoraco)lumbar scoliosis than in controls.

PURPOSE: The pelvic incidence (PI) is used to describe the sagittal spino-pelvic alignment. In previous studies, radiographs were used, leading to less accuracy in establishing the three-dimensional (3D) spino-pelvic parameters. The purpose of this study is to analyze the differences in the 3D sagittal spino-pelvic alignment in adolescent idiopathic scoliosis (AIS) subjects and non-scoliotic controls. METHODS: Thirty-seven female AIS patients that underwent preoperative supine low-dose computed tomography imaging of the spine, hips and pelvis as part of their general workup were included and compared to 44 non-scoliotic age-matched female controls. A previously validated computerized method was used to measure the PI in 3D, as the angle between the line orthogonal to the inclination of the sacral endplate and the line connecting the center of the sacral endplate with the hip axis. RESULTS: The PI was on average 46.8° ± 12.4° in AIS patients and 41.3° ± 11.4° in controls (p = 0.025), with a higher PI in Lenke type 5 curves (50.6° ± 16.2°) as compared to controls (p = 0.042), whereas the Lenke type 1 curves (45.9° ± 12.2°) did not differ from controls (p = 0.141). CONCLUSION: Lenke type 5 curves show a significantly higher PI than controls, whereas the Lenke type 1 curves did not differ from controls. This suggests a role of pelvic morphology and spino-pelvic alignment in the pathogenesis of idiopathic scoliosis. Further longitudinal studies should explore the exact role of the PI in the initiation and progression of different AIS types. These slides can be retrieved under Electronic Supplementary Material.

Minimum cement volume for vertebroplasty.

PURPOSE: Percutaneous vertebroplasty is a widely used vertebral augmentation technique. It is a minimally invasive and low-risk procedure, but has some disadvantages with a relatively high number of bone cement leaks and adjacent vertebral fractures. The aim of this cadaveric study was to determine the minimum percentage of cement fill volume in vertebroplasty needed to restore vertebral stiffness and adjacent intradiscal pressure. METHODS: Thirteen thoracolumbar spine mobile segments were loaded to induce a vertebral fracture. After fracture vertebroplasty was performed, four times in the same fractured vertebra. The injected cement volume was 5 % of the fractured vertebral volume to reach 5, 10, 15 and 20 % of cement fill. Biomechanical testing was performed before the fracture, after the fracture and after each cement injection. RESULTS: After vertebral fracture compressive stiffness was reduced to 47 % of the pre-fracture value and was partially restored to 61 % after 10 % cement fill. With vertebroplasty intradiscal pressure gradually increased, depending on specimen position, from 48 to a total of 71 % at 15 % of cement fill. CONCLUSIONS: Compressive stiffness and intradiscal pressure increase with the percentage of cement fill. Fifteen per cent of cement fill was the limit beyond which no substantial increase in compressive stiffness or intradiscal pressure could be detected and is the minimum volume of cement we recommend for vertebroplasty. In the average thoracolumbar vertebra this means 4-6 ml of cement.

Evolution of the ischio-iliac lordosis during natural growth and its relation with the pelvic incidence.

PURPOSE: Human fully upright ambulation, with fully extended hips and knees, and the body's center of gravity directly above the hips, is unique in nature, and distinguishes humans from all other mammalians. This bipedalism is made possible by the development of a lordosis between the ischium and ilium; it allows to ambulate in this unique bipedal manner, without sacrificing forceful extension of the legs. This configuration in space introduces unique biomechanical forces with relevance for a number of spinal conditions. The aim of this study was to quantify the development of this lordosis between ischium and ilium in the normal growing and adult spine and to evaluate its correlation with the well-known clinical parameter, pelvic incidence. METHODS: Consecutive series of three-dimensional computed tomography scans of the abdomen of 189 children and 310 adults without spino-pelvic pathologies were used. Scan indications were trauma screening or acute abdominal pathology. Using previously validated image processing techniques, femoral heads, center of the sacral endplate and the axes of the ischial bones were semi-automatically identified. A true sagittal view of the pelvis was automatically reconstructed, on which ischio-iliac angulation and pelvic incidence were calculated. The ischio-iliac angle was defined as the angle between the axes of the ischial bones and the line from the midpoint of the sacral endplate to the center of the femoral heads. RESULTS: A wide natural variation of the ischio-iliac angle (3°-46°) and pelvic incidence (14°-77°) was observed. Pearson's analysis demonstrated a significant correlation between the ischio-iliac angle and pelvic incidence (r = 0.558, P < 0.001). Linear regression analysis revealed that ischio-iliac angle, as well as pelvic incidence, increases during childhood (+7° and +10°, respectively) and becomes constant after adolescence. CONCLUSIONS: The development of the ischio-iliac lordosis is unique in nature, is in harmonious continuity with the highly individual lumbar lordosis and defines the way the human spine is biomechanically loaded. The practical parameter that reflects this is the pelvic incidence; both values increase during growth and remain stable in adulthood.

vOARiability: Interobserver and intermodality variability analysis in OAR contouring from head and neck CT and MR images.

BACKGROUND: Accurate and consistent contouring of organs-at-risk (OARs) from medical images is a key step of radiotherapy (RT) cancer treatment planning. Most contouring approaches rely on computed tomography (CT) images, but the integration of complementary magnetic resonance (MR) modality is highly recommended, especially from the perspective of OAR contouring, synthetic CT and MR image generation for MR-only RT, and MR-guided RT. Although MR has been recognized as valuable for contouring OARs in the head and neck (HaN) region, the accuracy and consistency of the resulting contours have not been yet objectively evaluated. PURPOSE: To analyze the interobserver and intermodality variability in contouring OARs in the HaN region, performed by observers with different level of experience from CT and MR images of the same patients. METHODS: In the final cohort of 27 CT and MR images of the same patients, contours of up to 31 OARs were obtained by a radiation oncology resident (junior observer, JO) and a board-certified radiation oncologist (senior observer, SO). The resulting contours were then evaluated in terms of interobserver variability, characterized as the agreement among different observers (JO and SO) when contouring OARs in a selected modality (CT or MR), and intermodality variability, characterized as the agreement among different modalities (CT and MR) when OARs were contoured by a selected observer (JO or SO), both by the Dice coefficient (DC) and 95-percentile Hausdorff distance (HD 95 $_{95}$ ). RESULTS: The mean (±standard deviation) interobserver variability was 69.0 ± 20.2% and 5.1 ± 4.1 mm, while the mean intermodality variability was 61.6 ± 19.0% and 6.1 ± 4.3 mm in terms of DC and HD 95 $_{95}$ , respectively, across all OARs. Statistically significant differences were only found for specific OARs. The performed MR to CT image registration resulted in a mean target registration error of 1.7 ± 0.5 mm, which was considered as valid for the analysis of intermodality variability. CONCLUSIONS: The contouring variability was, in general, similar for both image modalities, and experience did not considerably affect the contouring performance. However, the results indicate that an OAR is difficult to contour regardless of whether it is contoured in the CT or MR image, and that observer experience may be an important factor for OARs that are deemed difficult to contour. Several of the differences in the resulting variability can be also attributed to adherence to guidelines, especially for OARs with poor visibility or without distinctive boundaries in either CT or MR images. Although considerable contouring differences were observed for specific OARs, it can be concluded that almost all OARs can be contoured with a similar degree of variability in either the CT or MR modality, which works in favor of MR images from the perspective of MR-only and MR-guided RT.

Reinforcement learning-based anatomical maps for pancreas subregion and duct segmentation.

BACKGROUND: The pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging application. PURPOSE: In this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three-dimensional (3D) computed tomography (CT) images. METHODS: A multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U-Net architectures to obtain the final segmentation results. RESULTS: To evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U-Net, Attention U-Net, and shifted windowing (Swin) U-Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL-based framework. For the pancreatic duct, the RL-based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets. CONCLUSIONS: The resulting accuracy of the proposed RL-based segmentation framework demonstrates an improvement against segmentation with standard U-Net architectures.

HaN-Seg: The head and neck organ-at-risk CT and MR segmentation challenge.

BACKGROUND AND PURPOSE: To promote the development of auto-segmentation methods for head and neck (HaN) radiation treatment (RT) planning that exploit the information of computed tomography (CT) and magnetic resonance (MR) imaging modalities, we organized HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challenge. MATERIALS AND METHODS: The challenge task was to automatically segment 30 organs-at-risk (OARs) of the HaN region in 14 withheld test cases given the availability of 42 publicly available training cases. Each case consisted of one contrast-enhanced CT and one T1-weighted MR image of the HaN region of the same patient, with up to 30 corresponding reference OAR delineation masks. The performance was evaluated in terms of the Dice similarity coefficient (DSC) and 95-percentile Hausdorff distance (HD95), and statistical ranking was applied for each metric by pairwise comparison of the submitted methods using the Wilcoxon signed-rank test. RESULTS: While 23 teams registered for the challenge, only seven submitted their methods for the final phase. The top-performing team achieved a DSC of 76.9 % and a HD95 of 3.5 mm. All participating teams utilized architectures based on U-Net, with the winning team leveraging rigid MR to CT registration combined with network entry-level concatenation of both modalities. CONCLUSION: This challenge simulated a real-world clinical scenario by providing non-registered MR and CT images with varying fields-of-view and voxel sizes. Remarkably, the top-performing teams achieved segmentation performance surpassing the inter-observer agreement on the same dataset. These results set a benchmark for future research on this publicly available dataset and on paired multi-modal image segmentation in general.

HaN-Seg: The head and neck organ-at-risk CT and MR segmentation dataset.

PURPOSE: For the cancer in the head and neck (HaN), radiotherapy (RT) represents an important treatment modality. Segmentation of organs-at-risk (OARs) is the starting point of RT planning, however, existing approaches are focused on either computed tomography (CT) or magnetic resonance (MR) images, while multimodal segmentation has not been thoroughly explored yet. We present a dataset of CT and MR images of the same patients with curated reference HaN OAR segmentations for an objective evaluation of segmentation methods. ACQUISITION AND VALIDATION METHODS: The cohort consists of HaN images of 56 patients that underwent both CT and T1-weighted MR imaging for image-guided RT. For each patient, reference segmentations of up to 30 OARs were obtained by experts performing manual pixel-wise image annotation. By maintaining the distribution of patient age and gender, and annotation type, the patients were randomly split into training Set 1 (42 cases or 75%) and test Set 2 (14 cases or 25%). Baseline auto-segmentation results are also provided by training the publicly available deep nnU-Net architecture on Set 1, and evaluating its performance on Set 2. DATA FORMAT AND USAGE NOTES: The data are publicly available through an open-access repository under the name HaN-Seg: The Head and Neck Organ-at-Risk CT & MR Segmentation Dataset. Images and reference segmentations are stored in the NRRD file format, where the OAR filenames correspond to the nomenclature recommended by the American Association of Physicists in Medicine, and OAR and demographics information is stored in separate comma-separated value  files. POTENTIAL APPLICATIONS: The HaN-Seg: The Head and Neck Organ-at-Risk CT & MR Segmentation Challenge is launched in parallel with the dataset release to promote the development of automated techniques for OAR segmentation in the HaN. Other potential applications include out-of-challenge algorithm development and benchmarking, as well as external validation of the developed algorithms.

Special Section Guest Editorial: Advances in High-Dimensional Medical Image Processing.

Guest Editors Ivana Isgum, Bennett A. Landman, and Tomaz Vrtovec introduce the JMI Special Section on Advances in High-Dimensional Medical Image Processing.

Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification.

Morphological abnormalities of the femoroacetabular (hip) joint are among the most common human musculoskeletal disorders and often develop asymptomatically at early easily treatable stages. In this paper, we propose an automated framework for landmark-based detection and quantification of hip abnormalities from magnetic resonance (MR) images. The framework relies on a novel idea of multi-landmark environment analysis with reinforcement learning. In particular, we merge the concepts of the graphical lasso and Morris sensitivity analysis with deep neural networks to quantitatively estimate the contribution of individual landmark and landmark subgroup locations to the other landmark locations. Convolutional neural networks for image segmentation are utilized to propose the initial landmark locations, and landmark detection is then formulated as a reinforcement learning (RL) problem, where each landmark-agent can adjust its position by observing the local MR image neighborhood and the locations of the most-contributive landmarks. The framework was validated on T1-, T2- and proton density-weighted MR images of 260 patients with the aim to measure the lateral center-edge angle (LCEA), femoral neck-shaft angle (NSA), and the anterior and posterior acetabular sector angles (AASA and PASA) of the hip, and derive the quantitative abnormality metrics from these angles. The framework was successfully tested using the UNet and feature pyramid network (FPN) segmentation architectures for landmark proposal generation, and the deep Q-network (DeepQN), deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and actor-critic policy gradient (A2C) RL networks for landmark position optimization. The resulting overall landmark detection error of 1.5 mm and angle measurement error of 1.4° indicates a superior performance in comparison to existing methods. Moreover, the automatically estimated abnormality labels were in 95% agreement with those generated by an expert radiologist.

Determination of axial vertebral rotation in MR images: comparison of four manual and a computerized method.

Axial vertebral rotation (AVR) of 14 normal and 14 scoliotic vertebrae from magnetic resonance (MR) images was determined by three observers using four manual methods and a computerized method, which were based on the evaluation of vertebral symmetry in two dimensions (2D) and in three dimensions (3D). The method of Aaro and Dahlborn proved to be the manual method with the highest intra-observer (1.7 degrees SD) and inter-observer (1.2 degrees SD) reliabilities, and was also most in agreement with the computerized method (1.3 degrees SD, 1.0 degrees MAD). The computerized method yielded higher intra-observer (1.3 degrees SD) and inter-observer (1.4 degrees SD) reliabilities than the manual methods, indicating it to be an efficient alternative for repeatable and reliable AVR measurements.

Auto-segmentation of organs at risk for head and neck radiotherapy planning: From atlas-based to deep learning methods.

Radiotherapy (RT) is one of the basic treatment modalities for cancer of the head and neck (H&N), which requires a precise spatial description of the target volumes and organs at risk (OARs) to deliver a highly conformal radiation dose to the tumor cells while sparing the healthy tissues. For this purpose, target volumes and OARs have to be delineated and segmented from medical images. As manual delineation is a tedious and time-consuming task subjected to intra/interobserver variability, computerized auto-segmentation has been developed as an alternative. The field of medical imaging and RT planning has experienced an increased interest in the past decade, with new emerging trends that shifted the field of H&N OAR auto-segmentation from atlas-based to deep learning-based approaches. In this review, we systematically analyzed 78 relevant publications on auto-segmentation of OARs in the H&N region from 2008 to date, and provided critical discussions and recommendations from various perspectives: image modality - both computed tomography and magnetic resonance image modalities are being exploited, but the potential of the latter should be explored more in the future; OAR - the spinal cord, brainstem, and major salivary glands are the most studied OARs, but additional experiments should be conducted for several less studied soft tissue structures; image database - several image databases with the corresponding ground truth are currently available for methodology evaluation, but should be augmented with data from multiple observers and multiple institutions; methodology - current methods have shifted from atlas-based to deep learning auto-segmentation, which is expected to become even more sophisticated; ground truth - delineation guidelines should be followed and participation of multiple experts from multiple institutions is recommended; performance metrics - the Dice coefficient as the standard volumetric overlap metrics should be accompanied with at least one distance metrics, and combined with clinical acceptability scores and risk assessments; segmentation performance - the best performing methods achieve clinically acceptable auto-segmentation for several OARs, however, the dosimetric impact should be also studied to provide clinically relevant endpoints for RT planning.

A review of methods for quantitative evaluation of axial vertebral rotation.

Quantitative evaluation of axial vertebral rotation is essential for the determination of reference values in normal and pathological conditions and for understanding the mechanisms of the progression of spinal deformities. However, routine quantitative evaluation of axial vertebral rotation is difficult and error-prone due to the limitations of the observer, characteristics of the observed vertebral anatomy and specific imaging properties. The scope of this paper is to review the existing methods for quantitative evaluation of axial vertebral rotation from medical images along with all relevant publications, which may provide a valuable resource for studying the existing methods or developing new methods and evaluation strategies. The reviewed methods are divided into the methods for evaluation of axial vertebral rotation in 2D images and the methods for evaluation of axial vertebral rotation in 3D images. Key evaluation issues and future considerations, supported by the results of the overview, are also discussed.

A review of methods for quantitative evaluation of spinal curvature.

The aim of this paper is to provide a complete overview of the existing methods for quantitative evaluation of spinal curvature from medical images, and to summarize the relevant publications, which may not only assist in the introduction of other researchers to the field, but also be a valuable resource for studying the existing methods or developing new methods and evaluation strategies. Key evaluation issues and future considerations, supported by the results of the overview, are also discussed.

Computer-assisted pedicle screw trajectory planning using CT-inferred bone density: A demonstration against surgical outcomes.

PURPOSE: Image-guided spine surgery and preoperative computer-assisted planning provide spine surgeons with tools to improve the safety, accuracy, and reliability of pedicle screw placement. The purpose of this study is to demonstrate a computer-assisted pedicle screw placement planning tool in comparison to screws as delivered by a spine surgeon. METHODS: We describe a novel computer-assisted tool for preoperative pedicle screw placement planning in computed tomography (CT) images, designed with respect to the vertebral shape and structure, and augmented with respect to the considerations of surgical practice. The approach is based on three-dimensional (3D) modeling of the vertebral body and pedicles, and planning of the pedicle screw size and insertion trajectory by maximizing the screw fastening strength, evaluated through CT-inferred bone density maps. The approach is augmented by yielding screw plans consistent with the straight-forward surgical technique of aligning screws parallel to vertebral endplates, and the screw entry points following the spinal curvature to facilitate rod attachment. For a cohort of 25 patients, placement plans were retrospectively obtained for 204 pedicle screws with the computer-assisted tool from preoperative CT images, while reference trajectories of inserted pedicle screws were reconstructed in 3D from postoperative biplanar radiographs. RESULTS: The best performing version of the computer-assisted tool achieved clinically acceptable preoperative pedicle screw placement plans in 96.6% of the cases, while the comparison to the postoperative reconstructions resulted in 3.4 ± 2.5 mm for the screw entry point location, 2.7 ± 1.6 mm for the screw crossing point location, and 7.4 ± 5.3∘ for the screw sagittal inclination (mean absolute difference ± standard deviation). CONCLUSION: Quantitative comparison revealed that the preoperative placement plans are consistent with the postoperative results, and that the computer-assisted tool integrating bone density and surgical constraints can successfully incorporate important aspects of pedicle screw placement. The results therefore confirm the accuracy of the tool prior to being integrated in an image-guidance system.

Quantitative analysis of spinal curvature in 3D: application to CT images of normal spine.

The purpose of this study is to present a framework for quantitative analysis of spinal curvature in 3D. In order to study the properties of such complex 3D structures, we propose two descriptors that capture the characteristics of spinal curvature in 3D. The descriptors are the geometric curvature (GC) and curvature angle (CA), which are independent of the orientation and size of spine anatomy. We demonstrate the two descriptors that characterize the spinal curvature in 3D on 30 computed tomography (CT) images of normal spine and on a scoliotic spine. The descriptors are determined from 3D vertebral body lines, which are obtained by two different methods. The first method is based on the least-squares technique that approximates the manually identified vertebra centroids, while the second method searches for vertebra centroids in an automated optimization scheme, based on computer-assisted image analysis. Polynomial functions of the fourth and fifth degree were used for the description of normal and scoliotic spinal curvature in 3D, respectively. The mean distance to vertebra centroids was 1.1 mm (+/-0.6 mm) for the first and 2.1 mm (+/-1.4 mm) for the second method. The distributions of GC and CA values were obtained along the 30 images of normal spine at each vertebral level and show that maximal thoracic kyphosis (TK), thoracolumbar junction (TJ) and maximal lumbar lordosis (LL) on average occur at T3/T4, T12/L1 and L4/L5, respectively. The main advantage of GC and CA is that the measurements are independent of the orientation and size of the spine, thus allowing objective intra- and inter-subject comparisons. The positions of maximal TK, TJ and maximal LL can be easily identified by observing the GC and CA distributions at different vertebral levels. The obtained courses of the GC and CA for the scoliotic spine were compared to the distributions of GC and CA for the normal spines. The significant difference in values indicates that the descriptors of GC and CA may be used to detect and quantify scoliotic spinal curvatures. The proposed framework may therefore improve the understanding of spine anatomy and aid in the clinical quantitative evaluation of spinal deformities.

A computerized method for evaluating scoliotic deformities using elliptical pattern recognition in X-ray spine images.

BACKGROUND AND OBJECTIVE: Several studies have evaluated the reproducibility of the Cobb angle for measuring the degree of scoliotic deformities from X-ray spine images, and proposed different geometric models for describing the spinal curvature. The ellipse was shown to be an adequate geometric form, but was not yet applied for the identification and quantification of scoliotic curvatures. The purpose of this study is therefore to propose and validate a novel computerized methodology for the detection of elliptical patterns from X-ray images to evaluate the extent of the underlying scoliotic deformity. METHODS: For anteroposterior each X-ray spine image, the spine curve is first reconstructed from vertebral centroids. The ellipse that best fits to the obtained spine curve is the found within a least square and genetic algorithm optimization framework. The geometric parameters of the resulting best fit ellipse are finally used to define an index that quantifies the spinal curvature. RESULTS: The proposed methodology was validated on three synthetic images and then successfully applied to 20 clinical anteroposterior X-ray spine images of patients with a different degree of scoliotic deformity, with the resulting maximal relative error of 3% for the synthetic images and an overall error of 0.5 ±â€¯0.4 mm (mean ±â€¯standard deviation) for the clinical cases. CONCLUSIONS: The results indicate that the proposed computerized methodology is able to reliably reproduce scoliotic curvatures using the geometric parameters of the underlying ellipses. In comparison to conventional approaches, the proposed methodology potentially produces less errors, requires a relatively low observer interaction, takes into account all vertebrae within the observed scoliotic deformity, and allows for both qualitative and quantitative evaluations that may complement the diagnosis, study and treatment of scoliosis.