Search Filters

  • Media Source
  • Presentation Format
  • Media Type
  • Media Year
  • Language
  • Diagnosis / Condition
  • Diagnosis Method
  • Patient Populations
  • Treatment / Technique

Detection Loosening of Total Knee Arthroplasty Implant from Plain Radiograph Using Machine Learning Algorithm

Detection Loosening of Total Knee Arthroplasty Implant from Plain Radiograph Using Machine Learning Algorithm

Man-Soo Kim, MD, PhD, KOREA, REPUBLIC OF Dongho Kwak, MD, KOREA, REPUBLIC OF Sungcheol Yang, MD, KOREA, REPUBLIC OF Hyukjin Jang, MD, KOREA, REPUBLIC OF Ryu Kyoung Cho, MD, KOREA, REPUBLIC OF Yong In, MD, PhD, KOREA, REPUBLIC OF

Seoul St. Mary's Hospital, Seoul, KOREA, REPUBLIC OF


2023 Congress   ePoster Presentation   2023 Congress   Not yet rated

 

Anatomic Location

Anatomic Structure

Diagnosis / Condition

Patient Populations

Diagnosis Method


Summary: CNN algorithm through transfer learning shows high accuracy in detecting loosening of TKA implant through plain radiograph. These results can be expected to be utilized as an auxiliary tool in the decision making process in diagnosing loosening of TKA implant by orthopedic surgeons.


Introduction

Detecting loosening of total knee arthroplasty (TKA) implants is a challenging process, even for experienced clinicians, and may not always be available, potentially delaying diagnosis. The purpose of this study was to investigate whether the loosening of TKA implant could be detected on plain radiograph using deep convolution neural network (CNN).

Methods

An analysis was conducted on 100 patients who underwent revision TKA due to loosening at one institution from 2012 to 2020. 100 patients who underwent primary TKA without loosening were extracted through propensity score matching for age, gender, body mass index, and operation side. We implemented training acceleration in a pre-trained CNN model called VGG19 through a transfer learning method that gradually changes the freezing layer. Training and testing were conducted in a ratio of 8:2.

Results

In the first model that trained only the last layer of the classification layer, the accuracy in diagnosing loosening of TKA implant was 87.5% and the accuracy for no-loosening was 56.3%. However, as the trained learning layer was gradually increased to the feature learning part, the accuracy in diagnosing loosening increased to 100%, and the accuracy for the non-loosening increased to 95%.

Conclusion

CNN algorithm through transfer learning shows high accuracy in detecting loosening of TKA implant through plain radiograph. These results can be expected to be utilized as an auxiliary tool in the decision making process in diagnosing loosening of TKA implant by orthopedic surgeons.


More 2023 ISAKOS Congress Content