AI-Powered Scoliosis Auto-Analysis System Multicenter Development and Validations

Recruiting

• Conditions: Spinal Deformity
• Interventions: Other: Nude back photo

• Registration Number: NCT05146193
• Lead Sponsor: The University of Hong Kong

Brief Summary

The investigators aim to use artificial intelligence (AI) to help clinicians in diagnosing and assessing spinal deformities.

Detailed Description

Background Spinal deformity is a prevalent spinal disorder in both paediatric and adult populations. The spine alignment need to be quantitively assessed for further treatment planning. However, the current practice requires spine surgeons to manually place landmarks of endplates and key vertebrae. The process is laborious and prone to inter- and intra-rater variance. Thus, the investigators have developed an AI-powered spine alignment assessment system (AlignProCARE) to facilitate clinicians in fast, accurate and consistent analytical results.

The investigators aim to test and improve the performance of the spine alignment auto-analysis in all patients with spinal deformities in multiple centers including Malaysia, China, and Japan

Objectives:

1. prospectively test the alignment assessment of patients' spinal deformities with whole spine X-rays (both PA and lateral) and nude back image with the assessment via AlignProCARE.

2. Collect 500 labeled deformity radiographs and nude back images in both PA and lateral views per center. 150 patients need to be followed up with radiographs and nude back photos collected (all parameters measured again).

3. Use transfer learning to update the current AlignProCARE for scoliosis analysis to form AlignProCARE+.

4 Qualitatively analyse the AlignProCARE+ using an independent dataset.

Basic Information
|
Recruitment & Eligibility
|
Study & Design
|
Trial Locations

Study Timeline

• Study First Submitted: 2021-11-12
• Study First Submitted QC: 2021-11-23
• Study First Posted: 2021-12-06
• Study Start: 2022-05-01
• Status Verified: 2024-12
• Last Update Submitted: 2024-12-03
• Last Update Posted: 2024-12-06
• Primary Completion: 2025-02-01
• Study Completion: 2025-02-01

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 2500

Inclusion Criteria

• Idiopathic scoliosis, adult deformity (spondylolisthesis, idiopathic kyphosis, kyphoscoliosis, lordoscoliosis)

Read More

Exclusion Criteria

• Refusal for imaging, postoperative patients

Read More

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
All subjects are diagnosed of having a spinal deformity	Nude back photo	Routine care of patients with spinal deformities

Primary Outcome Measures

Name	Time	Method
Cobb angle	1 year	Coronal Cobb angle of the spinal deformity. The most tilted end vertebrae away from the apex will be used for measurement of the Cobb angle.The anteroposterior radiograph is used to assess

Secondary Outcome Measures

Name	Time	Method
Curve severity	1 year	Severity classifications: normal-mild; moderate and severe
Lumbar lordosis	1 year	Lumbar lordosis L1-S1: angle between upper endplate of L1 to top of S1 in the lateral radiograph
Sacral slope	1 year	Sacral slope angle measurement in degrees in the lateral radiograph
Pelvic incidence	1 year	Pelvic incidence angle measurement in degrees in the lateral radiograph
Thoracic kyphosis	1 year	Thoracic kyphosis T5-12: angle between upper endplate of T5 to lower endplate of T12 in the lateral radiograph
Pelvic tilt	1 year	Pelvic tilt angle measurement in degrees in the lateral radiograph
Maximum thoracic kyphosis	1 year	Maximum thoracic kyphosis: angle measurement from the upper endplate of most tilted upper end vertebra to the lower endplate of the lower end vertebra of the thoracic spine in the sagittal plane radiograph

Trial Locations

Locations (1)

Duchess of Kent Children's Hospital; 🇭🇰 Hong Kong, Hong Kong