Determining the Mechanical Axis of the Femur From a Standard Antero-Posterior Knee Radiograph With Deep Learning.
Deep learning estimated femoral mechanical axis correction factor accurate to 1.02°
Determining the Mechanical Axis of the Femur From a Standard Antero-Posterior Knee Radiograph With Deep Learning.
As the femoral head is not visible on a standard antero-posterior (antero-posterior) knee view, surgeons looking to assess alignment on a patient who has only an antero-posterior view must either (i) forgo crucial long leg measurements, (ii) use the less meaningful anatomic axis, or (iii) use crude approximations.
The purpose of this study was to develop a deep learning (deep learning) model for predicting the correction factor between the anatomical and mechanical axes.
We compared the mean absolute error (mean absolute error) and standard deviation of mean absolute error (SD) of our deep learning model against two other published approaches (i) linear regression and (ii) adding 6° of varus to the anatomic axis.
software predicted the correction angle to near-exact precision, more accurate than older methods
The linear regression approach resulted in an mean absolute error of 1.34° (SD: 1.10°), while the 6° varus approach resulted in an mean absolute error of 2.00° (SD: 1.47°).
We developed a deep learning model to predict the mechanical axis of the femur from a single, standard antero-posterior view knee radiograph.
The deep learning model was accurate to within 1°, a clinically relevant level of accuracy, and a substantial improvement on published regression and 6° varus addition methods.
This model delivers automated calculations of several important alignment measurements from standard radiographs, which may provide substantial clinical and research benefits.