Author: Yang, De
Title: Mild adolescent idiopathic scoliosis (AIS) classification using 3D ultrasound imaging methods
Advisors: Zheng, Yongping (BME)
Degree: Ph.D.
Year: 2023
Subject: Scoliosis
Spine -- Abnormalities -- Imaging
Three-dimensional imaging in medicine
Ultrasonic imaging
Hong Kong Polytechnic University -- Dissertations
Department: Department of Biomedical Engineering
Pages: xxii, 147 pages : color illustrations
Language: English
Abstract: Mild adolescent idiopathic scoliosis (AIS), with Cobb<20°, together with high bone maturity grade, was hypothesized as the right stage to intervene to prevent progression. AIS curve can be categorized into either structural or non-structural depending on the spine morphology (flexibility). Lenke classification is the state-of-the-art scoliosis classification scheme for pre-surgery AIS planning. However, no study has reported the scoliosis classification scheme for mild AIS curve-correction exercise assessment, which requires the knowledge of curve types in different spinal segments. Using X-ray to characterize AIS curves remains the clinical gold standard while compromising the risks of radiation exposure. For non-radiative alternatives, 3D ultrasound imaging has demonstrated its reliability for the coronal spinal curvature measurement. The overall objective of this study is to investigate the validity and reliability of a measurement parameter, Bending Asymmetry Index (BAI), originated from the 3D ultrasound imaging. BAI is derived from bilateral bending of spine, reflecting the curve type in spinal morphology of scoliosis, and can be used for mild AIS classification purposes. Non-structural curve demonstrates a quasi-symmetrical pattern in bilateral bending, while structural curve shows distinctive asymmetrical pattern. The BAI methods were validated through different anatomical landmarks: 1) vertebral body centroid; 2) spinous process; and 3) transverse process features.
In the present study, several features have been applied for the BAI methods. Vertebral body centroid was used to validate the pre-surgery AIS patients' classification in X-ray for ethical concerns. Two ultrasound-based BAI methods, namely as BAIsp (using spinous process) and BAItp (using transverse process features), were validated for mild AIS patients classification. These BAI methods all demonstrated promising results for AIS curve type classification. Ultrasound BAI methods not only classify mild AIS curves, but also take an important role in AIS screening referrals.
Further studies are worthwhile to investigate whether deep learning approaches could liberate the manual procedures for the current semi-automatic BAI methods. Due to the radiation-free nature of ultrasound, it will also be very meaningful to conduct follow-up investigation of patients with AIS for monitoring BAI changes as a progression indication.
Rights: All rights reserved
Access: open access

Files in This Item:
File Description SizeFormat 
6756.pdfFor All Users5.57 MBAdobe PDFView/Open

Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show full item record

Please use this identifier to cite or link to this item: