Summary
Objectives: For diagnosis or treatment assessment of knee joint osteoarthritis it is required
to measure bone morphometry from radiographic images. We propose a method for automatic
measurement of joint alignment from pre-operative as well as post-operative radiographs.
Methods: In a two step approach we first detect and segment any implants or other artificial
objects within the image. We exploit physical characteristics and avoid prior shape
information to cope with the vast amount of implant types. Subsequently, we exploit
the implant delineations to adapt the initialization and adaptation phase of a dedicated
bone segmentation scheme using deformable template models. Implant and bone contours
are fused to derive the final joint segmentation and thus the alignment measurements.
Results: We evaluated our method on clinical long leg radiographs and compared both the initialization
rate, corresponding to the number of images successfully processed by the proposed
algorithm, and the accuracy of the alignment measurement. Ground truth has been generated
by an experienced orthopedic surgeon. For comparison a second reader reevaluated the
measurements. Experiments on two sets of 70 and 120 digital radiographs show that
92% of the joints could be processed automatically and the derived measurements of
the automatic method are comparable to a human reader for pre-operative as well as
post-operative images with a typical error of 0.7° and correlations of r = 0.82 to
r = 0.99 with the ground truth.
Conclusions: The proposed method allows deriving objective measures of joint alignment from clinical
radiographs. Its accuracy and precision are on par with a human reader for all evaluated
measurements.
Keywords
Radiography - bone - lower extremity - replacement arthroplasty - orthopedics
