An intelligent system for image-based rating of corrosion severity at stem taper of retrieved hip replacement implants

Roohollah Milimonfared; Reza H Oskouei; Mark Taylor; Lucian B Solomon

doi:10.1016/j.medengphy.2018.08.002

An intelligent system for image-based rating of corrosion severity at stem taper of retrieved hip replacement implants

Med Eng Phys. 2018 Nov:61:13-24. doi: 10.1016/j.medengphy.2018.08.002. Epub 2018 Aug 23.

Authors

Roohollah Milimonfared¹, Reza H Oskouei², Mark Taylor¹, Lucian B Solomon³

Affiliations

¹ The Medical Device Research Institute, Flinders University, Adelaide, Australia.
² The Medical Device Research Institute, Flinders University, Adelaide, Australia. Electronic address: reza.oskouei@flinders.edu.au.
³ Department of Orthopaedics and Trauma Service, Royal Adelaide Hospital, Adelaide, Australia; Centre for Orthopaedic and Trauma Research, The University of Adelaide, Adelaide, Australia.

PMID: 30146392
DOI: 10.1016/j.medengphy.2018.08.002

Abstract

Visual scoring of damage at taper junctions is the sole method to quantify corrosion in large-scale retrieval studies of failed hip replacement implants. This study introduces an intelligent image analysis-based method that objectively rates corrosion at stem taper of retrieved hip implants according to the well-known Goldberg scoring method. A Support Vector Machine classifier was used that takes in vectors of global and local textural features and assigns scores to the corresponding images. Bayesian optimisation fine-tunes the hyperparameters of the classifier to minimise the cross-validation error.

Keywords: Digital image processing; Machine learning; Metallic implants; Texture analysis; Total hip arthroplasty.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Arthroplasty, Replacement, Hip*
Corrosion
Image Processing, Computer-Assisted*
Support Vector Machine*