Application of Artificial Intelligence in Hip Ultrasound and its Performance in Detecting Developmental Dysplasia of the Hip

• Author / Creator

  Ghasseminia, Siyavash

• Developmental Dysplasia of Hip (DDH) which represents a wide range of abnormalities from acetabular dysplasia to fixed dislocation, is mainly defined by a loss of conformity between the femoral head and the acetabulum and it can lead to structural instability and osteoarthritis. The diagnosis of DDH on ultrasound is mainly based on Graf method. It is primarily focused on obtaining a single high-quality coronal 2D image containing elements such as acetabulum, ilium, and round femoral head. Graf method on 2DUS not only suffers from low inter and intra- rater agreement, but its reproducibility has also been shown to decline over time. Recording ‘sweep’ images allows more comprehensive hip assessment and introduces opportunities for automation by artificial intelligence (AI). In this thesis, agreement between readers with various background and expertise and an AI algorithm in detecting DDH is assessed. Additionally, this thesis evaluates the accuracy of AI in classification of DDH from 3DUS and its correlation with conventional clinical 2DUS.

• Subjects / Keywords

  • Artificial Intelligence
  • Ultrasound
  • Medical Imaging
  • Hip Dysplasia
  • Developmental Dysplasia of the Hip
  • 3D Ultrasound

• Graduation date

  Spring 2022

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-5s0a-ap39

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.