Introduction : Image analysis plays a central role in orthopedics but comes along with many challenges like anonymization, bias, usability, and efficient analysis by multiple independent analyzers, etc. Tyche is a lightweight, browser-based program that addresses the challenges mentioned above by displaying images anonymized, in random order and facilitating the analysis by multiple analyzers. The goal of this study was to validate Tyche for the use of orthopedic images by comparing it with a validated standard program for orthopedic planning.
Method : One hundred three anterior-posterior pelvic radiographs were selected from our database and analyzed separately by five experienced orthopedic surgeons using both Tyche and validated software, mediCAD® (mediCAD Hectec GmbH, Altdorf, Germany). Common orthopedic measurement modalities (length, angle, area) and a score (Kellgren & Lawrence) were determined. Methods were compared using Pearson's correlation coefficients and Bland-Altman-Plots. A short video explaining Tyche can be found at www.tyche.expert/explain.
Results : All one hundred three radiographs were analyzed five times using both Tyche mediCAD®. Significant correlations ranging from r = 0.77 (angle-measurements) to r=0.99 (area-measurements) were found between the two programs for all measurements. Bland-Altman-Plots confirmed the non-inferiority of either method. Images were analyzed significantly faster using Tyche. No obvious transmission errors were found in results using Tyche compared to those from mediCAD®.
Conclusion : None of the currently available tools addresses all challenges in image analysis like anonymization, subjectivity, bias, and usability. Here we tested a new browser-based program, Tyche, by comparing results with a validated tool. In summary, results correlated significantly between the two methods. However, using Tyche, results were acquired faster, under complete anonymization, and with fewer transmission errors. We conclude that Tyche is a validated tool for orthopedic image analysis. For the first time, a validated browser-based tool enables independent analyzers worldwide to conduct efficient, multicenter, and randomized imaging studies and score validations.