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.
Automated and semi-automated detection and segmentation of spinal and vertebral structures from computed tomography (CT) images is a challenging task due to a relatively high degree of anatomical ...complexity, presence of unclear boundaries and articulation of vertebrae with each other, as well as due to insufficient image spatial resolution, partial volume effects, presence of image artifacts, intensity variations and low signal-to-noise ratio. In this paper, we describe a novel framework for automated spine and vertebrae detection and segmentation from 3-D CT images. A novel optimization technique based on interpolation theory is applied to detect the location of the whole spine in the 3-D image and, using the obtained location of the whole spine, to further detect the location of individual vertebrae within the spinal column. The obtained vertebra detection results represent a robust and accurate initialization for the subsequent segmentation of individual vertebrae, which is performed by an improved shape-constrained deformable model approach. The framework was evaluated on two publicly available CT spine image databases of 50 lumbar and 170 thoracolumbar vertebrae. Quantitative comparison against corresponding reference vertebra segmentations yielded an overall mean centroid-to-centroid distance of 1.1 mm and Dice coefficient of 83.6% for vertebra detection, and an overall mean symmetric surface distance of 0.3 mm and Dice coefficient of 94.6% for vertebra segmentation. The results indicate that by applying the proposed automated detection and segmentation framework, vertebrae can be successfully detected and accurately segmented in 3-D from CT spine images.
Izhodišča: Sagitalna orientacija medenice je pomemben element sagitalnega ravnovesja, kvantitativno pa jo lahko opredelimo na podlagi merjenja geometrijskih parametrov medenice, in sicer naklona ...križnične končne ploskve (SS), nagiba medenice (PT) in naklona medenice (PI). V tem članku predstavljamo rezultate popolnoma samodejnega računalniško podprtega merjenja parametrov sagitalne orientacije medenice na podlagi rentgenskih slik ter testiramo hipotezo, da ni statistično pomembnih razlik med dobljenimi in referenčnimi ročnimi meritvami.Metode: Samodejno računalniško podprto merjenje parametrov sagitalne orientacije medenice temelji na najnovejših tehnologijah iz področja obdelave in analize medicinskih slik, in sicer na konvolucijskih nevronskih mrežah kot posebni obliki tehnik globokega učenja. Na podlagi teh tehnologij se v sagitalni rentgenski sliki medenice najprej samodejno določijo območja zanimanja (križnična končna ploskev ter kolčni sklepni glavi), nato pa se znotraj teh območij določijo značilne točke, in sicer anteriorni rob, središče in posteriorni rob križnične končne ploskve, na katere se kasneje prilega premica, ter središči obeh kolčnih sklepnih glav s pripadajočo sredinsko točko, ki predstavlja os medenice. Na podlagi osi medenice ter premice vzdolž križnične končne ploskve in njenega središča lahko končno izračunamo SS, PT in PI.Rezultati: Merjenje je bilo retrospektivno opravljeno na sagitalnih rentgenskih slikah medenice 38 oseb (15 moških in 23 žensk; povprečna starost 71,1 let). Statistična analiza referenčnih ročnih in samodejnih računalniško podprtih meritev parametrov sagitalne orientacije medenice je pokazala na relativno dobro ujemanje in majhno odstopanje. Za SS, PT in PI je bila povprečna absolutna razlika (standardni odklon) namreč 5,2º (3,8º), 2,2º (2,0º) in 5,1º (4,4º), korelacijski koeficient 0,73, 0,94 in 0,82 (p < 10-6), ničelna hipoteza pa je bila na podlagi parnega t-testa vedno potrjena (p > 0,05).Zaključek: Rezultati so pokazali, da ni statistično pomembnih razlik med referenčnimi ročnimi ter samodejnimi računalniško podprtimi meritvami parametrov sagitalne orientacije medenice. Poleg tega so odstopanja od referenčnih ročnih meritev znotraj ponovljivosti in zanesljivosti samega ročnega določanja teh parametrov, zato je z samodejnim računalniško podprtim merjenjem mogoče natančno določiti parametre sagitalne orientacije medenice. Vsekakor pa pregleda in potrjevanja tako izmerjenih vrednosti ne smemo popolnoma opustiti, saj so lahko odstopanja v določenih primerih precej velika, predvsem zaradi naravne biološke variabilnosti človeške anatomije ter lastnosti rentgenskega slikanja.
Computerized segmentation of pathological structures in medical images is challenging, as, in addition to unclear image boundaries, image artifacts, and traces of surgical activities, the shape of ...pathological structures may be very different from the shape of normal structures. Even if a sufficient number of pathological training samples are collected, statistical shape modeling cannot always capture shape features of pathological samples as they may be suppressed by shape features of a considerably larger number of healthy samples. At the same time, landmarking can be efficient in analyzing pathological structures but often lacks robustness. In this paper, we combine the advantages of landmark detection and deformable models into a novel supervised multi-energy segmentation framework that can efficiently segment structures with pathological shape. The framework adopts the theory of Laplacian shape editing, that was introduced in the field of computer graphics, so that the limitations of statistical shape modeling are avoided. The performance of the proposed framework was validated by segmenting fractured lumbar vertebrae from 3-D computed tomography images, atrophic corpora callosa from 2-D magnetic resonance (MR) cross-sections and cancerous prostates from 3D MR images, resulting respectively in a Dice coefficient of 84.7 ± 5.0%, 85.3 ± 4.8% and 78.3 ± 5.1%, and boundary distance of 1.14 ± 0.49mm, 1.42 ± 0.45mm and 2.27 ± 0.52mm. The obtained results were shown to be superior in comparison to existing deformable model-based segmentation algorithms.
Highlights • The first multi-center milestone comparative study for vertebra segmentation methods. • Objectively evaluate the performance of state-of-the-art vertebra segmentation algorithms. • ...Construct a publicly available annotated reference data set for spine labeling and segmentation.
Background: Sagittal pelvic alignment is an important aspect of the sagittal balance that can be quantitatively assessed by measuring pelvic geometrical parameters, i.e. the sacral slope (SS), pelvic ...tilt (PT) and pelvic incidence (PI). In this paper we present the results of a completely automated computer-assisted measurement of the parameters of sagittal pelvic alignment from radiographic images, and test the hypothesis stating that there are no statistically significant differences between the obtained and reference manual measurements. Methods: Automated computer-assisted measurements of the sagittal pelvic alignment parameters are based on the latest technologies in the field of medical image processing and analysis, namely on the convolutional neural networks as a special group of deep learning techniques. In each sagittal radiographic image of the pelvis, regions of interest (sacral endplate and both femoral heads) are first automatically defined, and then distinctive points are detected within these regions, i.e. the anterior edge, the center and the posterior edge of the sacral endplate, to which a line is fitted at a later stage, and the centers of both femoral heads with the corresponding midpoint representing the hip axis. From the hip axis, and the line along the sacral endplate and its center point we can finally compute SS, PT and PI. Results: Measurements were retrospectively performed on sagittal radiographic images of the pelvis from 38 subjects (15 males and 23 females; mean age 71.1 years). Statistical analysis of reference manual and automated computer-assisted measurements of the sagittal pelvic alignment parameters revealed a relatively good agreement and low variability. Respectively for SS, PT and PI, the mean absolute difference (standard deviation) was namely 5.2º (3.8º), 2.2º (2.0º) and 5.1º (4.4º), the correlation coefficient was 0.73, 0.94 and 0.82 (p < 10-6), and the paired t-test always confirmed the null hypothesis (p > 0.05). Conclusion: The results showed that there are no statistically significant differences between the reference manual and automated computer-assisted measurements of the sagittal pelvic alignment parameters. Moreover, the deviation from reference manual measurements is within the repeatability and reliability of manual parameter measurements, and therefore the parameters of sagittal pelvic alignment can be accurately determined by the automated computer-assisted measurement. Nevertheless, verification and confirmation of measured values cannot be completely omitted, as the deviation can be for specific cases quite large, especially due to the natural biological variability of the human anatomy and properties of radiographic imaging.
•Establish a standard framework with 25 manually annotated 3D T2 MRI data for an objective comparison of intervertebral disc (IVD) localization and segmentation methods.•Investigate strengths and ...limitations of a representative selection of the state-of-the-art IVD localization and segmentation methods with a challenge setup.•Results achieved by the best algorithms in this study set new frontiers for IVD localization and segmentation from MR data.
Display omitted
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.
Abstract Gradual degeneration of intervertebral discs of the lumbar spine is one of the most common causes of low back pain. Although conservative treatment for low back pain may provide relief to ...most individuals, surgical intervention may be required for individuals with significant continuing symptoms, which is usually performed by replacing the degenerated intervertebral disc with an artificial implant. For designing implants with good bone contact and continuous force distribution, the morphology of the intervertebral disc space and vertebral body endplates is of considerable importance. In this study, we propose a method for parametric modeling of the intervertebral disc space in three dimensions (3D) and show its application to computed tomography (CT) images of the lumbar spine. The initial 3D model of the intervertebral disc space is generated according to the superquadric approach and therefore represented by a truncated elliptical cone, which is initialized by parameters obtained from 3D models of adjacent vertebral bodies. In an optimization procedure, the 3D model of the intervertebral disc space is incrementally deformed by adding parameters that provide a more detailed morphometric description of the observed shape, and aligned to the observed intervertebral disc space in the 3D image. By applying the proposed method to CT images of 20 lumbar spines, the shape and pose of each of the 100 intervertebral disc spaces were represented by a 3D parametric model. The resulting mean (±standard deviation) accuracy of modeling was 1.06 ± 0.98 mm in terms of radial Euclidean distance against manually defined ground truth points, with the corresponding success rate of 93% (i.e. 93 out of 100 intervertebral disc spaces were modeled successfully). As the resulting 3D models provide a description of the shape of intervertebral disc spaces in a complete parametric form, morphometric analysis was straightforwardly enabled and allowed the computation of the corresponding heights, widths and volumes, as well as of other geometric features that in detail describe the shape of intervertebral disc spaces.
Cobbov kot, ki se je sprva uveljavil kot glavni diagnostični parameter za stopnjo razvitosti skoliozę, pozneje pa tudi za druge tipe deformaci hrbtenice, se ponavadi meri na dvodimenzionalnih čelnih ...rentgenskih slikah. Zaradi točnejših meritev obstaja težnja po merjenju Cobbovega kota v tridimenzionalnih (3D) slikah, kot so npr. slike, pridobljene s tehniko računalniške tomografije ali magnetne resonance, ali v 3D modelih, rekonstruiranih iz 3D slik. V tem članku predlagamo polavtomatsko metodo za oceno 3D Cobbovega kota iz trikotniške mreže 3D modela hrbtenice, kjer ročno izbranima vretencema zgornjega in spodnjega konca deformacije hrbtenice najprej določimo središče telesa. Prek središča telesa nato označimo trikotniška lica zgornje in spodnje krovne plošče vretenca, ki določata ravnini, prek katerih se izmeri Cobbov kot. Metodo smo preizkusili na 60 trikotniških mrežah skoliotičnih hrbtenic pri 17 različnih velikostih trikotniških lic. Pri modelih, kjer je bil rob trikotniškega lica krajši od 6 mm, je bila metoda robustna in točna, in sicer s povprečno napako 3,0° in standardnim odklonom 2,2° v primerjavi z referenčními meritvami.