Mobile Application for Scoliosis Screening Using a Standard 2D Digital Camera

Akazawa, Tsutomu; Torii, Yoshiaki; Ueno, Jun; Saito, Asako; Niki, Hisateru

doi:10.7759/cureus.13944

Cited by 3 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 38 Thus, close monitoring is important. Previous photography-based attempts 39 to assess AIS based on back appearance features were found to be unreliable for various features that characterize scoliosis, since the traditional algorithms struggle to extract distinguishable features from back images. Deep learning is recognized as a promising approach due to its powerful ability to extract distinguishable features automatically.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph

Zhang,

Zhu,

Zhao

et al. 2023

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceAdolescent idiopathic scoliosis (AIS) is the most common pediatric spinal disorder. Routine physical examinations by trained personnel are critical to diagnose severity and monitor curve progression in AIS. In the presence of concerning malformation, radiographs are necessary for diagnosis or follow-up, guiding further management, such as bracing correction for moderate malformation and spine surgery for severe malformation. If left unattended, progressive deterioration occurs in two-thirds of patients, leading to significant health concerns for growing children.ObjectiveTo assess the ability of an open platform application (app) using a validated deep learning model to classify AIS severity and curve type, as well as identify progression.Design, Setting, and ParticipantsThis diagnostic study was performed with data from radiographs and smartphone photographs of the backs of adolescent patients at spine clinics. The ScolioNets deep learning model was developed and validated in a prospective training cohort, then incorporated and tested in the AlignProCARE open platform app in 2022. Ground truths (GTs) included severity, curve type, and progression as manually annotated by 2 experienced spine specialists based on the radiographic examinations of the participants’ spines. The GTs and app results were blindly compared with another 2 spine surgeons’ assessments of unclothed back appearance. Data were analyzed from October 2022 to February 2023.ExposureAcquisitions of unclothed back photographs using a mobile app.Main Outcomes and MeasuresOutcomes of interest were classification of AIS severity and progression. Quantitative statistical analyses were performed to assess the performance of the deep learning model in classifying the deformity as well as in distinguishing progression during 6-month follow-up.ResultsThe training data set consisted of 1780 patients (1295 [72.8%] female; mean [SD] age, 14.3 [3.3] years), and the prospective testing data sets consisted of 378 patients (279 [73.8%] female; mean [SD] age, 14.3 [3.8] years) and 376 follow-ups (294 [78.2%] female; mean [SD] age, 15.6 [2.9] years). The model recommended follow-up with an area under receiver operating characteristic curve (AUC) of 0.839 (95% CI, 0.789-0.882) and considering surgery with an AUC of 0.902 (95% CI, 0.859-0.936), while showing good ability to distinguish among thoracic (AUC, 0.777 [95% CI, 0.745-0.808]), thoracolumbar or lumbar (AUC, 0.760 [95% CI, 0.727-0.791]), or mixed (AUC, 0.860 [95% CI, 0.834-0.887]) curve types. For follow-ups, the model distinguished participants with or without curve progression with an AUC of 0.757 (95% CI, 0.630-0.858). Compared with both surgeons, the model could recognize severities and curve types with a higher sensitivity (eg, sensitivity for recommending follow-up: model, 84.88% [95% CI, 75.54%-91.70%]; senior surgeon, 44.19%; junior surgeon, 62.79%) and negative predictive values (NPVs; eg, NPV for recommending follow-up: model, 89.22% [95% CI, 84.25%-93.70%]; senior surgeon, 71.76%; junior surgeon, 79.35%). For distinguishing curve progression, the sensitivity and NPV were comparable with the senior surgeons (sensitivity, 63.33% [95% CI, 43.86%-80.87%] vs 77.42%; NPV, 68.57% [95% CI, 56.78%-78.37%] vs 72.00%). The junior surgeon reported an inability to identify curve types and progression by observing the unclothed back alone.ConclusionsThis diagnostic study of adolescent patients screened for AIS found that the deep learning app had the potential for out-of-hospital accessible and radiation-free management of children with scoliosis, with comparable performance as spine surgeons experienced in AIS management.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph

Zhang,

Zhu,

Zhao

et al. 2023

JAMA Netw Open

View full text Add to dashboard Cite

show abstract

“…Apps can improve the accuracy of screening by physicians and be used to detect scoliosis in patients on a global scale [ 30 ]. Figure 2 shows the reference architecture and graphical workflow of ICT-based scoliosis management.…”

Section: Ict-based Scoliosis Managementmentioning

confidence: 99%

Scoliosis Management through Apps and Software Tools

Bottino

Settino

Promenzio³

et al. 2023

IJERPH

View full text Add to dashboard Cite

Background: Scoliosis is curvature of the spine, often found in adolescents, which can impact on quality of life. Generally, scoliosis is diagnosed by measuring the Cobb angle, which represents the gold standard for scoliosis grade quantification. Commonly, scoliosis evaluation is conducted in person by medical professionals using traditional methods (i.e., involving a scoliometer and/or X-ray radiographs). In recent years, as has happened in various medicine disciplines, it is possible also in orthopedics to observe the spread of Information and Communications Technology (ICT) solutions (i.e., software-based approaches). As an example, smartphone applications (apps) and web-based applications may help the doctors in screening and monitoring scoliosis, thereby reducing the number of in-person visits. Objectives: This paper aims to provide an overview of the main features of the most popular scoliosis ICT tools, i.e., apps and web-based applications for scoliosis diagnosis, screening, and monitoring. Several apps are assessed and compared with the aim of providing a valid starting point for doctors and patients in their choice of software-based tools. Benefits for the patients may be: reducing the number of visits to the doctor, self-monitoring of scoliosis. Benefits for the doctors may be: monitoring the scoliosis progression over time, managing several patients in a remote way, mining the data of several patients for evaluating different therapeutic or exercise prescriptions. Materials and Methods: We first propose a methodology for the evaluation of scoliosis apps in which five macro-categories are considered: (i) technological aspects (e.g., available sensors, how angles are measured); (ii) the type of measurements (e.g., Cobb angle, angle of trunk rotation, axial vertebral rotation); (iii) availability (e.g., app store and eventual fee to pay); (iv) the functions offered to the user (e.g., posture monitoring, exercise prescription); (v) overall evaluation (e.g., pros and cons, usability). Then, six apps and one web-based application are described and evaluated using this methodology. Results: The results for assessment of scoliosis apps are shown in a tabular format for ease of understanding and intuitive comparison, which can help the doctors, specialists, and families in their choice of scoliosis apps. Conclusions: The use of ICT solutions for spinal curvature assessment and monitoring brings several advantages to both patients and orthopedics specialists. Six scoliosis apps and one web-based application are evaluated, and a guideline for their selection is provided.

show abstract

“…However, abnormal curvature is considered a condition that can be diagnosed and then treated. Methods of diagnosing abnormal curvature include the forward bend test and radiography [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

A Neural Network Approach for Inertial Measurement Unit-Based Estimation of Three-Dimensional Spinal Curvature

Mak

Liang²,

Chim

et al. 2023

Sensors

View full text Add to dashboard Cite

The spine is an important part of the human body. Thus, its curvature and shape are closely monitored, and treatment is required if abnormalities are detected. However, the current method of spinal examination mostly relies on two-dimensional static imaging, which does not provide real-time information on dynamic spinal behaviour. Therefore, this study explored an easier and more efficient method based on machine learning and sensors to determine the curvature of the spine. Fifteen participants were recruited and performed tests to generate data for training a neural network. This estimated the spinal curvature from the readings of three inertial measurement units and had an average absolute error of 0.261161 cm.

show abstract

Mobile Application for Scoliosis Screening Using a Standard 2D Digital Camera

Cited by 3 publications

References 9 publications

Deep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph

Deep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph

Scoliosis Management through Apps and Software Tools

A Neural Network Approach for Inertial Measurement Unit-Based Estimation of Three-Dimensional Spinal Curvature

Contact Info

Product

Resources

About