A Survey of Methods and Technologies Used for Diagnosis of Scoliosis

Measurement of distances and locations of thoracic and lumbar vertebral bodies from CT scans in cases of spinal deformation

BACKGROUND

Spinal deformations, except for acute injuries, are among the most frequent reasons for visiting an orthopaedic specialist and musculoskeletal treatment in adults and adolescents. Data on the morphology and anatomical structures of the spine are therefore of interest to orthopaedics, physicians, and medical scientists alike, in the broad field from diagnosis to therapy and in research.

METHODS

Along the course of developing supplementary methods that do not require the use of ionizing radiation in the assessment of scoliosis, twenty CT scans from females and males with various severity of spinal deformations and body shape have been analysed with respect to the transverse distances between the vertebral body and the spinous process end tip and the skin, respectively, at thoracic and lumbar vertebral levels. Further, the locations of the vertebral bodies have been analysed in relation to the patient's individual body shape and shown together with those from other patients by normalization to the area encompassed by the transverse body contour.

RESULTS

While the transverse distance from the vertebral body to the skin varies between patients, the distances from the vertebral body to the spinous processes end tips tend to be rather similar across different patients of the same gender. Tables list the arithmetic mean distances for all thoracic and lumbar vertebral levels and for different regions upon grouping into mild, medium, and strong spinal deformation and according to the range of spinal deformation.

CONCLUSIONS

The distances, the clustering of the locations of the vertebral bodies as a function of the vertebral level, and the trends therein could in the future be used in context with biomechanical modeling of a patient's individual spinal deformation in scoliosis assessment using 3D body scanner images during follow-up examinations.

Unsupervised local center of mass based scoliosis spinal segmentation and Cobb angle measurement

Scoliosis is a medical condition in which a person's spine has an abnormal curvature and Cobb angle is a measurement used to evaluate the severity of a spinal curvature. Presently, automatic Existing Cobb angle measurement techniques require huge dataset, time-consuming, and needs significant effort. So, it is important to develop an unsupervised method for the measurement of Cobb angle with good accuracy. In this work, an unsupervised local center of mass (LCM) technique is proposed to segment the spine region and further novel Cobb angle measurement method is proposed for accurate measurement. Validation of the proposed method was carried out on 2D X-ray images from the Saudi Arabian population. Segmentation results were compared with GMM-Based Hidden Markov Random Field (GMM-HMRF) segmentation method based on sensitivity, specificity, and dice score. Based on the findings, it can be observed that our proposed segmentation method provides an overall accuracy of 97.3% whereas GMM-HMRF has an accuracy of 89.19%. Also, the proposed method has a higher dice score of 0.54 compared to GMM-HMRF. To further evaluate the effectiveness of the approach in the Cobb angle measurement, the results were compared with Senior Scoliosis Surgeon at Multispecialty Hospital in Saudi Arabia. The findings indicated that the segmentation of the scoliotic spine was nearly flawless, and the Cobb angle measurements obtained through manual examination by the expert and the algorithm were nearly identical, with a discrepancy of only ± 3 degrees. Our proposed method can pave the way for accurate spinal segmentation and Cobb angle measurement among scoliosis patients by reducing observers' variability.

Assessment of idiopathic scoliosis among adolescents and associated factors in Palestine

PURPOSE

This study aimed to investigate adolescent idiopathic scoliosis (AIS) and its related risk factors, including body mass index (BMI), physical activity (PA), gender, time of the first menstrual cycle, transportation, backpack weight and the way of carrying a backpack.

DESIGN AND METHOD

a cross-sectional quantitative design was utilized. A convenient sample of adolescent students in grades seven through ten was included in the study. A self-reported questionnaire with three sections: demographic data; physical data including height, weight and PA; and Adam's forward bend test to determine each student's spine's Cobb angle by measuring the angle of trunk rotation using a scoliometer. The data were analyzed using SPSS version 25, with confidence intervals of 95%.

RESULTS

A total of 820 schoolchildren participated in the study; 53.7% were female and 46.3% were male. Only 22% of these students engaged in vigorous exercise, compared to 36.7% who engaged in low PA; additionally, 10% of the adolescents had a low BMI. After the analysis, it was found that 5.4% of participants had AIS. Low PA (p = 0.001), being underweight (p = 0.038), and time of first menstrual period (p = 0.033) were significantly associated with AIS, while gender, backpack weight, and way of carrying were not statistically related to AIS. Binary logistic regression identified low PA as an independent predictor of AIS (OR = 7.22, 95%CI [1.64, 31.79]).

CONCLUSIONS

The frequency of AIS in Palestine was significant, which highlighted the importance of this issue at a national and global level. There was an association between AIS and BMI, PA, and the time of the first menstrual cycle, which signifies the importance of early detection of the problem to limit its burden later in life.

PRACTICE IMPLICATIONS

Teachers, teenagers, and their parents should be provided with programs that educate and clarify AIS, and a specific protocol should be established for scoliosis screening in schools.

SCOLIONET: An Automated Scoliosis Cobb Angle Quantification Using Enhanced X-ray Images and Deep Learning Models

The advancement of medical prognoses hinges on the delivery of timely and reliable assessments. Conventional methods of assessments and diagnosis, often reliant on human expertise, lead to inconsistencies due to professionals' subjectivity, knowledge, and experience. To address these problems head-on, we harnessed artificial intelligence's power to introduce a transformative solution. We leveraged convolutional neural networks to engineer our SCOLIONET architecture, which can accurately identify Cobb angle measurements. Empirical testing on our pipeline demonstrated a mean segmentation accuracy of 97.50% (Sorensen-Dice coefficient) and 96.30% (Intersection over Union), indicating the model's proficiency in outlining vertebrae. The level of quantification accuracy was attributed to the state-of-the-art design of the atrous spatial pyramid pooling to better segment images. We also compared physician's manual evaluations against our machine driven measurements to validate our approach's practicality and reliability further. The results were remarkable, with a p-value (t-test) of 0.1713 and an average acceptable deviation of 2.86 degrees, suggesting insignificant difference between the two methods. Our work holds the premise of enabling medical practitioners to expedite scoliosis examination swiftly and consistently in improving and advancing the quality of patient care.

Imaging Methods to Quantify the Chest and Trunk Deformation in Adolescent Idiopathic Scoliosis: A Literature Review

Background context: Scoliosis is a three-dimensional deformity of the spine with the most prevalent type being adolescent idiopathic scoliosis (AIS). The rotational spinal deformation leads to displacement and deformation of the ribs, resulting in a deformity of the entire chest. Routine diagnostic imaging is performed in order to define its etiology, measure curve severity and progression during growth, and for treatment planning. To date, all treatment recommendations are based on spinal parameters, while the esthetic concerns and cardiopulmonary symptoms of patients are mostly related to the trunk deformation. For this reason, there is a need for diagnostic imaging of the patho-anatomical changes of the chest and trunk in AIS. Aim: The aim of this review is to provide an overview, as complete as possible, of imaging modalities, methods and image processing techniques for assessment of chest and trunk deformation in AIS. Methods: Here, we present a narrative literature review of (1) image acquisition techniques used in clinical practice, (2) a description of various relevant methods to measure the deformity of the thorax in patients with AIS, and (3) different image processing techniques useful for quantifying 3D chest wall deformity. Results: Various ionizing and non-ionizing imaging modalities are available, but radiography is most widely used for AIS follow-up. A disadvantage is that these images are only acquired in 2D and are not effective for acquiring detailed information on complex 3D chest deformities. While CT is the gold standard 3D imaging technique for assessment of in vivo morphology of osseous structures, it is rarely obtained for surgical planning because of concerns about radiation exposure and increased risk of cancer during later life. Therefore, different modalities with less or without radiation, such as biplanar radiography and MRI are usually preferred. Recently, there have been advances in the field of image processing for measurements of the chest: Anatomical segmentations have become fully automatic and deep learning has been shown to be able to automatically perform measurements and even outperform experts in terms of accuracy. Conclusions: Recent advancements in imaging modalities and image processing techniques make complex 3D evaluation of chest deformation possible. Before introduction into daily clinical practice, however, there is a need for studies correlating image-based chest deformation parameters to patient-reported outcomes, and for technological advancements to make the workflow cost-effective.

Test-retest reliability of a photographic marker-based system for postural examination

BACKGROUND

The BHOHB system (Bhohb S.r.l., Italy) is a portable non-invasive photographic marker-based device for postural examination.

OBJECTIVE

To assess the test-retest reliability of the BHOHB system and compare its reliability with an optoelectronic system (SMART-DX 700, BTS, Italy).

METHODS

Thirty volunteers were instructed to stand upright with five markers on the spinous processes of C7, T6, T12, L3 and S1 vertebrae to define the dorsal kyphosis and lumbar lordosis (sagittal plane) angles. Three markers were placed on the great trochanter, apex of iliac crest and lateral condyle of the femur to detect pelvic tilt. Finally, to define angles between the acromion and the spinous processes (frontal plane), two markers were placed on the right and left acromion. Postural angles were recoded simultaneously with BHOHB and optoelectronic systems during two consecutive recording sessions.

RESULTS

The BHOHB system revealed excellent reliability for all the angles (ICCs: 0.92-0.99, SEM: 0.78∘-3.33∘) as well as a shorter processing time compared to the optoelectronic system. Excellent reliability was also found for all the angles detected through the optoelectronic system (ICCs: 0.91-0.99, SEM: 0.84∘-2.80∘).

CONCLUSION

The BHOHB system resulted as a reliable non-invasive and user-friendly device to monitor spinal posture, especially in subjects requiring repeat examinations.

Prevalence of idiopathic scoliosis in athletes: a systematic review and meta-analysis

Objective

This study aimed to determine the prevalence of idiopathic scoliosis (IS) in child, adolescent and adult athletes of all sports activity levels.

Design

Systematic review with meta-analysis.

Data sources

Electronic databases (PubMed, Scopus, ProQuest, Sage journals, ScienceDirect, Google Scholar and Springer) were systematically searched up from inception to 28 September 2021.

Eligibility criteria for selecting studies

Observational investigations were included to evaluate the prevalence of IS in athletes (engaged in any type of individual and team sports). Congenital scoliosis, neuromuscular scoliosis, Scheuermann’s kyphosis and de novo scoliosis were not included. The risk of bias was assessed using the tool developed by Hoy et al.

Results

Twenty-two studies were included (N=57 470, range 15–46544, participants), thirteen studies were of high-quality. The estimated prevalence of IS in athletes was 27% (95% CI 20% to 35%, I²=98%), with a 95% prediction interval (1% to 69%). The prevalence of IS was significantly higher in female athletes (35%, 95% CI 27% to 34%, I²=98%). Ballet dancers showed a high IS prevalence (35%, 95% CI 24% to 47%, I²=98%). Recreational athletes showed a higher IS prevalence (33%, 95% CI 24% to 43%, I²=98%) than at competitive-level athletes (0.05%, 95% CI 0.03% to 0.08%, I²=98%), followed by elite (20%, 95% CI 13% to 27%, I²=98%).

Conclusions

The prevalence of IS in athletes was similar or higher to that as seen in other studies of the general population. IS prevalence may have a U-shaped relationship relative to level of competition. Further studies are required to determine which sports have the highest IS prevalence.

Using deep transfer learning to detect scoliosis and spondylolisthesis from x-ray images

Recent years have witnessed wider prevalence of vertebral column pathologies due to lifestyle changes, sedentary behaviors, or injuries. Spondylolisthesis and scoliosis are two of the most common ailments with an incidence of 5% and 3% in the United States population, respectively. Both of these abnormalities can affect children at a young age and, if left untreated, can progress into severe pain. Moreover, severe scoliosis can even lead to lung and heart problems. Thus, early diagnosis can make it easier to apply remedies/interventions and prevent further disease progression. Current diagnosis methods are based on visual inspection by physicians of radiographs and/or calculation of certain angles (e.g., Cobb angle). Traditional artificial intelligence-based diagnosis systems utilized these parameters to perform automated classification, which enabled fast and easy diagnosis supporting tools. However, they still require the specialists to perform error-prone tedious measurements. To this end, automated measurement tools were proposed based on processing techniques of X-ray images. In this paper, we utilize advances in deep transfer learning to diagnose spondylolisthesis and scoliosis from X-ray images without the need for any measurements. We collected raw data from real X-ray images of 338 subjects (i.e., 188 scoliosis, 79 spondylolisthesis, and 71 healthy). Deep transfer learning models were developed to perform three-class classification as well as pair-wise binary classifications among the three classes. The highest mean accuracy and maximum accuracy for three-class classification was 96.73% and 98.02%, respectively. Regarding pair-wise binary classification, high accuracy values were achieved for most of the models (i.e., > 98%). These results and other performance metrics reflect a robust ability to diagnose the subjects’ vertebral column disorders from standard X-ray images. The current study provides a supporting tool that can reasonably help the physicians make the correct early diagnosis with less effort and errors, and reduce the need for surgical interventions.

A Review of the Methods on Cobb Angle Measurements for Spinal Curvature

Scoliosis is a common disease of the spine and requires regular monitoring due to its progressive properties. A preferred indicator to assess scoliosis is by the Cobb angle, which is currently measured either manually by the relevant medical staff or semi-automatically, aided by a computer. These methods are not only labor-intensive but also vary in precision by the inter-observer and intra-observer. Therefore, a reliable and convenient method is urgently needed. With the development of computer vision and deep learning, it is possible to automatically calculate the Cobb angles by processing X-ray or CT/MR/US images. In this paper, the research progress of Cobb angle measurement in recent years is reviewed from the perspectives of computer vision and deep learning. By comparing the measurement effects of typical methods, their advantages and disadvantages are analyzed. Finally, the key issues and their development trends are also discussed.