A Portable Software Application to Measure Fracture Callus in Radiographs

Document Type

Student Presentation

Presentation Date


Faculty Sponsor

Trevor Lujan


Advancements in fracture care technology require accurate methods to objectively measure clinical outcome metrics. The formation of fracture callus is visible on standard radiographs and has relevance to healing and mechanical integrity at the fracture site. However, established techniques for measuring fracture callus in radiographs are time-­‐intensive and subjective, with large inter-­‐physician variability. In this undergraduate research project, a Java application, OrthoRead, was developed to measure periosteal fracture callus in digital radiographs. OrthoRead requires users to select four points along the external cortex to define the cortical fragments. Once these fragments are defined, callus is automatically segmented. OrthoRead had less than 4% error at varying image resolutions, rotations, and user-­‐ defined cortical points. The callus extracted by OrthoRead correlated extremely well with an independent analysis by orthopedic surgeons (R2=0.95). OrthoRead had over three times less inter-­‐observer variance with an average run-­‐time of less than three seconds. This study has developed and validated the first software application to rapidly identify and quantify fracture callus in digital radiographs. OrthoRead can serve as an important scientific tool in quantifying an outcome metric with clinical relevance. It can support prospective and retrospective clinical studies investigating implant efficacy, and can assist research on fracture healing mechanobiology.

This document is currently not available here.