Automatic measurement of the Cobb angle for adolescent idiopathic scoliosis using convolutional neural network.
Ontology highlight
ABSTRACT:
SUBMITTER: Maeda Y
PROVIDER: S-EPMC10477263 | biostudies-literature | 2023 Sep
REPOSITORIES: biostudies-literature
Publications
Automatic measurement of the Cobb angle for adolescent idiopathic scoliosis using convolutional neural network.
Maeda Yoshihiro Y Nagura Takeo T Nakamura Masaya M Watanabe Kota K
Scientific reports 20230904 1
This study proposes a convolutional neural network method for automatic vertebrae detection and Cobb angle (CA) measurement on X-ray images for scoliosis. 1021 full-length X-ray images of the whole spine of patients with adolescent idiopathic scoliosis (AIS) were used for training and segmentation. The proposed AI algorithm's results were compared with those of the manual method by six doctors using the intraclass correlation coefficient (ICC). The ICCs recorded by six doctors and AI were excell ...[more]
Similar Datasets
Project description:Adolescent idiopathic scoliosis (AIS) is a prevalent spinal deformity occurring during peripubertal growth period that affects 1-4% of adolescents globally without clear etiopathogenetic mechanism. Low bone mineral density is an independent and significant prognostic factor for curve progression. Currently, the cause underlying low bone mass in AIS remains elusive. Osteocytes play an important role in bone metabolism and mineral homeostasis, but its role in AIS has not been studied. In the present study, iliac bone tissues were harvested from 21 patients with AIS (mean age of 14.3 ± 2.20 yr old) with a mean Cobb angle of 55.6 ± 10.61° and 13 non-AIS controls (mean age of 16.5 ± 4.79 yr old) intraoperatively. Acid-etched scanning electron microscopy (SEM) images of AIS demonstrated abnormal osteocytes that were more rounded and cobblestone-like in shape and were aligned in irregular clusters with shorter and disorganized canaliculi. Further quantitative analysis with FITC-Imaris technique showed a significant reduction in the canalicular number and length as well as an increase in lacunar volume and area in AIS. SEM with energy-dispersive X-ray spectroscopy analysis demonstrated a lower calcium-to-phosphorus ratio at the perilacunar/canalicular region. Moreover, microindentaion results revealed lower values of Vickers hardness and elastic modulus in AIS when compared with controls. In addition, in the parallel study of 99 AIS (27 with severe Cobb angle of 65.8 ± 14.1° and 72 with mild Cobb angle of 26.6 ± 9.1°) with different curve severity, the serum osteocalcin level was found to be significantly and negatively associated with the Cobb angle. In summary, the findings in this series of studies demonstrated the potential link of abnormal osteocyte lacuno-canalicular network structure and function to the observed abnormal bone mineralization in AIS, which may shed light on etiopathogenesis of AIS.-Chen, H., Zhang, J., Wang, Y., Cheuk, K.-Y., Hung, A. L. H., Lam, T.-P., Qiu, Y., Feng, J. Q., Lee, W. Y. W., Cheng, J. C. Y. Abnormal lacuno-canalicular network and negative correlation between serum osteocalcin and Cobb angle indicate abnormal osteocyte function in adolescent idiopathic scoliosis.
| S-EPMC6894095 | biostudies-literature
Project description:The Cobb angle value is a critical parameter for evaluating adolescent idiopathic scoliosis (AIS) patients. This study aimed to evaluate a software's validity and absolute reliability to determine the Cobb angle in AIS digital X-rays, with two different degrees of experienced observers. Four experts and four novice evaluators measured 35 scoliotic curves with the software on three separate occasions, one month apart. The observers re-measured the same radiographic studies on three separate occasions three months later but on conventional X-ray films. The differences between the mean bias errors (MBE) within the experience groups were statistically significant between the experts (software) and novices (manual) (p < 0.001) and between the novices (software) and novices (manual) (p = 0.005). When measured with the software, the intra-group error in the expert group was MBE = 1.71 ± 0.61° and the intraclass correlation coefficient (ICC (2,1)) = 0.986, and in the novice group, MBE = 1.9 ± 0.67° and ICC (2,1) = 0.97. There was almost a perfect concordance among the two measurement methods, ICC (2,1) = 0.998 and minimum detectable change (MCD95) < 0.4°. Control of the intrinsic error sources enabled obtaining inter- and intra-observer MDC95 < 0.5° in the two experience groups and with the two measurement methods. The computer-aided software TraumaMeter increases the validity and reliability of Cobb angle measurements concerning manual measurement.
| S-EPMC9027061 | biostudies-literature
Project description:Background: The Cobb angle is critical in assessing adolescent idiopathic scoliosis (AIS) patients. This study aimed to evaluate the error in selecting the upper- and lower-end vertebrae on AIS digital X-rays by experienced and novice observers and its correlation with the error in measuring the Cobb angle and determining the length of the scoliotic curves. Methods: Using the TraumaMeter v.873 software, eight raters independently evaluated 68 scoliotic curves. Results: The error percentage in the upper-end vertebra selection was higher than for the lower-end vertebra (44.7%, CI95% 41.05-48.3 compared to 35%, CI95% 29.7-40.4). The mean bias error (MBE) was 0.45 (CI95% 0.38-0.52) for the upper-end vertebra and 0.35 (CI% 0.69-0.91) for the lower-end vertebra. The percentage of errors in the choice of the end vertebrae was lower for the experienced than for the novices. There was a positive correlation (r = 0.673, p = 0.000) between the error in selecting the end vertebrae and determining the length of the scoliotic curves. Conclusions: We can conclude that errors in selecting end vertebrae are common among experienced and novice observers, with a greater error frequency for the upper-end vertebrae. Contrary to the consensus, the accuracy of determining the length of the scoliotic curve is limited by the Cobb method's reliance on the correct selection of the end vertebrae.
| S-EPMC11313236 | biostudies-literature
Project description:IntroductionThe Schroth method is one of the most common physiotherapeutic scoliosis-specific exercises intervention applied in adolescent idiopathic scoliosis (AIS). This method consists of three-dimensional correction of the specific curve pattern of the patient using a combination of sensorimotor, postural, and corrective breathing exercises. The aim of this systematic review and meta-analysis was to analyse the effects of the Schroth method in isolation on Cobb angle, quality of life, and trunk rotation angle compared to no intervention or other conservative treatments in patients with AIS.Evidence acquisitionPubMed, Physiotherapy Evidence Database, Scopus, Cochrane Library, and Web of Science databases were searched. Studies were included if they were randomized controlled trials that compared the effects of the Schroth method in isolation to conservative interventions or no intervention. The quality of the studies was assessed with the PEDro Scale, and the risk of bias with the Cochrane Collaboration tool. Two independent assessors extracted data through a standardized form. Meta-analyses were conducted using fixed or random effects models according to the heterogeneity assessed with I2 coefficient. Data on outcomes of interest were extracted by a researcher using RevMan 5.4 software.Evidence synthesisA total of 317 studies were screened. Six were included in the meta-analysis involving 144 patients with AIS. The methodological quality of the included studies ranged from high to low. Schroth method in isolation showed significant improvements in Cobb angle (mean difference [MD] =-3.18º; 95% CI: -4.30, -2.07; I2: 0%), quality of life (MD=0.28; 95% CI: 0.18, 0.38; I2: 0%) and trunk rotation angle (MD=-2.12º; 95% CI: -3.44, -0.80; I2: 71%) in the short-term.ConclusionsThe Schroth method in isolation is effective for reducing the Cobb angle and the trunk rotation angle and for improving the QoL in the short-term compared to no intervention or other conservative therapies in AIS, but the improvement in Cobb angle did not exceed the minimum clinically important difference.
| S-EPMC10170402 | biostudies-literature
Project description:BACKGROUND:Supine imaging modalities provide valuable 3D information on scoliotic anatomy, but the altered spine geometry between the supine and standing positions affects the Cobb angle measurement. Previous studies report a mean 7°-10° Cobb angle increase from supine to standing, but none have reported the effect of endplate pre-selection or whether other parameters affect this Cobb angle difference. METHODS:Cobb angles from existing coronal radiographs were compared to those on existing low-dose CT scans taken within three months of the reference radiograph for a group of females with adolescent idiopathic scoliosis. Reformatted coronal CT images were used to measure supine Cobb angles with and without endplate pre-selection (end-plates selected from the radiographs) by two observers on three separate occasions. Inter and intra-observer measurement variability were assessed. Multi-linear regression was used to investigate whether there was a relationship between supine to standing Cobb angle change and eight variables: patient age, mass, standing Cobb angle, Risser sign, ligament laxity, Lenke type, fulcrum flexibility and time delay between radiograph and CT scan. RESULTS:Fifty-two patients with right thoracic Lenke Type 1 curves and mean age 14.6 years (SD 1.8) were included. The mean Cobb angle on standing radiographs was 51.9° (SD 6.7). The mean Cobb angle on supine CT images without pre-selection of endplates was 41.1° (SD 6.4). The mean Cobb angle on supine CT images with endplate pre-selection was 40.5° (SD 6.6). Pre-selecting vertebral endplates increased the mean Cobb change by 0.6° (SD 2.3, range -9° to 6°). When free to do so, observers chose different levels for the end vertebrae in 39% of cases. Multi-linear regression revealed a statistically significant relationship between supine to standing Cobb change and fulcrum flexibility (p = 0.001), age (p = 0.027) and standing Cobb angle (p < 0.001). The 95% confidence intervals for intra-observer and inter-observer measurement variability were 3.1° and 3.6°, respectively. CONCLUSIONS:Pre-selecting vertebral endplates causes minor changes to the mean supine to standing Cobb change. There is a statistically significant relationship between supine to standing Cobb change and fulcrum flexibility such that this difference can be considered a potential alternative measure of spinal flexibility.
| S-EPMC4193912 | biostudies-literature
Project description:The angle of progression (AoP) for assessing fetal head (FH) descent during labor is measured from the standard plane of transperineal ultrasound images as the angle between a line through the long axis of pubic symphysis (PS) and a second line from the right end of PS tangentially to the contour of the FH. This paper presents a multitask network with a shared feature encoder and three task-special decoders for standard plane recognition (Task1), image segmentation (Task2) of PS and FH, and endpoint detection (Task3) of PS. Based on the segmented FH and two endpoints of PS from standard plane images, we determined the right FH tangent point that passes through the right endpoint of PS and then computed the AoP using the above three points. In this paper, the efficient channel attention unit is introduced into the shared feature encoder for improving the robustness of layer region encoding, while an attention fusion module is used to promote cross-branch interaction between the encoder for Task2 and that for Task3, and a shape-constrained loss function is designed for enhancing the robustness to noise based on the convex shape-prior. We use Pearson's correlation coefficient and the Bland-Altman graph to assess the degree of agreement. The dataset includes 1964 images, where 919 images are nonstandard planes, and the other 1045 images are standard planes including PS and FH. We achieve a classification accuracy of 92.26%, and for the AoP calculation, an absolute mean (STD) value of the difference in AoP (∆AoP) is 3.898° (3.192°), the Pearson's correlation coefficient between manual and automated AoP was 0.964 and the Bland-Altman plot demonstrates they were statistically significant (P < 0.05). In conclusion, our approach can achieve a fully automatic measurement of AoP with good efficiency and may help labor progress in the future.
| S-EPMC9462992 | biostudies-literature
Project description:ObjectivesSeverity of degenerative scoliosis (DS) is assessed by measuring the Cobb angle on anteroposterior radiographs. However, MRI images are often available to study the degenerative spine. This retrospective study aims to develop and evaluate the reliability of a novel automatic method that measures coronal Cobb angles on lumbar MRI in DS patients.Materials and methodsVertebrae and intervertebral discs were automatically segmented using a 3D AI algorithm, trained on 447 lumbar MRI series. The segmentations were used to calculate all possible angles between the vertebral endplates, with the largest being the Cobb angle. The results were validated with 50 high-resolution sagittal lumbar MRI scans of DS patients, in which three experienced readers measured the Cobb angle. Reliability was determined using the intraclass correlation coefficient (ICC).ResultsThe ICCs between the readers ranged from 0.90 (95% CI 0.83-0.94) to 0.93 (95% CI 0.88-0.96). The ICC between the maximum angle found by the algorithm and the average manually measured Cobb angles was 0.83 (95% CI 0.71-0.90). In 9 out of the 50 cases (18%), all readers agreed on both vertebral levels for Cobb angle measurement. When using the algorithm to extract the angles at the vertebral levels chosen by the readers, the ICCs ranged from 0.92 (95% CI 0.87-0.96) to 0.97 (95% CI 0.94-0.98).ConclusionThe Cobb angle can be accurately measured on MRI using the newly developed algorithm in patients with DS. The readers failed to consistently choose the same vertebral level for Cobb angle measurement, whereas the automatic approach ensures the maximum angle is consistently measured.Clinical relevance statementOur AI-based algorithm offers reliable Cobb angle measurement on routine MRI for degenerative scoliosis patients, potentially reducing the reliance on conventional radiographs, ensuring consistent assessments, and therefore improving patient care.Key points• While often available, MRI images are rarely utilized to determine the severity of degenerative scoliosis. • The presented MRI Cobb angle algorithm is more reliable than humans in patients with degenerative scoliosis. • Radiographic imaging for Cobb angle measurements is mitigated when lumbar MRI images are available.
| S-EPMC11364572 | biostudies-literature
Project description:Spinal deformities, including adolescent idiopathic scoliosis (AIS) and adult spinal deformity (ASD), affect many patients. The measurement of the Cobb angle on coronal radiographs is essential for their diagnosis and treatment planning. To enhance the precision of Cobb angle measurements for both AIS and ASD, we developed three distinct artificial intelligence (AI) algorithms: AIS/ASD-trained AI (trained with both AIS and ASD cases); AIS-trained AI (trained solely on AIS cases); ASD-trained AI (trained solely on ASD cases). We used 1612 whole-spine radiographs, including 1029 AIS and 583 ASD cases with variable postures, as teaching data. We measured the major and two minor curves. To assess the accuracy, we used 285 radiographs (159 AIS and 126 ASD) as a test set and calculated the mean absolute error (MAE) and intraclass correlation coefficient (ICC) between each AI algorithm and the average of manual measurements by four spine experts. The AIS/ASD-trained AI showed the highest accuracy among the three AI algorithms. This result suggested that learning across multiple diseases rather than disease-specific training may be an efficient AI learning method. The presented AI algorithm has the potential to reduce errors in Cobb angle measurements and improve the quality of clinical practice.
| S-EPMC11297987 | biostudies-literature
Project description:The practicability of deep learning techniques has been demonstrated by their successful implementation in varied fields, including diagnostic imaging for clinicians. In accordance with the increasing demands in the healthcare industry, techniques for automatic prediction and detection are being widely researched. Particularly in dentistry, for various reasons, automated mandibular canal detection has become highly desirable. The positioning of the inferior alveolar nerve (IAN), which is one of the major structures in the mandible, is crucial to prevent nerve injury during surgical procedures. However, automatic segmentation using Cone beam computed tomography (CBCT) poses certain difficulties, such as the complex appearance of the human skull, limited number of datasets, unclear edges, and noisy images. Using work-in-progress automation software, experiments were conducted with models based on 2D SegNet, 2D and 3D U-Nets as preliminary research for a dental segmentation automation tool. The 2D U-Net with adjacent images demonstrates higher global accuracy of 0.82 than naïve U-Net variants. The 2D SegNet showed the second highest global accuracy of 0.96, and the 3D U-Net showed the best global accuracy of 0.99. The automated canal detection system through deep learning will contribute significantly to efficient treatment planning and to reducing patients' discomfort by a dentist. This study will be a preliminary report and an opportunity to explore the application of deep learning to other dental fields.
| S-EPMC7109125 | biostudies-literature
Project description:Adolescent Idiopathic Scoliosis (AIS) is the most common orthopedic condition requiring surgery, affecting 4% of adolescents. There is currently no proven method or prognostic test to identify symptomatic patients at risk of developing severe scoliosis who could benefit from growth-guided devices or minimally invasive non-fusion instrumentation surgeries. These innovative treatments must be performed at an early disease stage in younger patients to benefit from their growth potential. In this prospective cross-sectional study, we investigated the clinical utility of circulating microRNAs (miRNAs), an important class of small non-coding RNA, as biomarkers to predict the risk of developing severe scoliosis in AIS. Blood samples and clinical data were collected from 116 AIS patients who were followed until skeletal maturity and stratified according to their clinical outcome. Genome-wide expression profiling of miRNAs was performed with plasma obtained at the time of diagnosis of AIS (mean age of 13.3 ± 1.7 years with a mean Cobb angle of 24.4° ± 12.4°). This approach led to the identification of 15 circulating miRNAs that are upregulated in AIS patients who developed a severe scoliosis (Cobb angle ≥45°) at skeletal maturity compared to moderate and mild scoliosis groups (Cobb angle between 25°-44° and <25° respectively). After optimization and the application of Random Forest Models a panel of six miRNAs (miR-1-3p, miR-19a-3p, miR-19b-3p, miR-133b, miR-143-3p, and miR-148b-3p) out of 15 led us to develop an algorithm predicting the risk of developing a severe scoliosis with great accuracy (100%), sensitivity (100%) and specificity (100%). Having a scoliosis predictive bioassay and decision-making tools to predict curve progression in order to find the best treatment plan will undoubtedly transform the orthopedic care system in the field of pediatric scoliosis by integrating innovative precision medicine approaches. In addition, investigation of genes targeted by these miRNAs could fill our gaps in our understanding of AIS pathogenesis and reveal new actionable targets.
2025-01-12 | GSE286204 | GEO