AutoCOR: Autonomous Condylar Offset Ratio Calculator on TKA-Postoperative Lateral Knee X-ray

TL;DR

AutoCOR is an automated software tool that uses machine learning and image processing to accurately calculate posterior and anterior condylar offset ratios on knee X-rays, aiding postoperative TKA evaluation.

Contribution

The paper introduces AutoCOR, the first autonomous software for calculating condylar offset ratios on knee radiographs using unsupervised machine learning techniques.

Findings

Strong correlation between software and ground truth PCOR values (r=0.845).

Moderate correlation between software and ground truth ACOR values (rs=0.519).

AutoCOR demonstrates potential for clinical application in TKA assessment.

Abstract

The postoperative range of motion is one of the crucial factors indicating the outcome of Total Knee Arthroplasty (TKA). Although the correlation between range of knee flexion and posterior condylar offset (PCO) is controversial in the literature, PCO maintains its importance on evaluation of TKA. Due to limitations on PCO measurement, two novel parameters, posterior condylar offset ratio (PCOR) and anterior condylar offset ratio (ACOR), were introduced. Nowadays, the calculation of PCOR and ACOR on plain lateral radiographs is done manually by orthopedic surgeons. In this regard, we developed a software, AutoCOR, to calculate PCOR and ACOR autonomously, utilizing unsupervised machine learning algorithm (k-means clustering) and digital image processing techniques. The software AutoCOR is capable of detecting the anterior/posterior edge points and anterior/posterior cortex of the femoral shaft on true postoperative lateral conventional radiographs. To test the algorithm, 50 postoperative true lateral radiographs from Istanbul Kosuyolu Medipol Hospital Database were used (32 patients). The mean PCOR was 0.984 (SD 0.235) in software results and 0.972 (SD 0.164) in ground truth values. It shows strong and significant correlation between software and ground truth values (Pearson r=0.845 p<0.0001). The mean ACOR was 0.107 (SD 0.092) in software results and 0.107 (SD 0.070) in ground truth values. It shows moderate and significant correlation between software and ground truth values (Spearman's rs=0.519 p=0.0001412). We suggest that AutoCOR is a useful tool that can be used in clinical practice.