RSNA 2021 Imaging Informatics Preview

Deep-learning tool can help in total hip arthroplasty surveillance

By Will Morton, AuntMinnie.com staff writer

Tuesday, November 30 | 8:00 a.m.-9:00 a.m. | SSMK05-3 | Room S406B
Research to develop a fully automated deep-learning tool to measure femoral component subsidence on hip x-ray without any user input will be discussed in this Tuesday morning session. A team at the Mayo Clinic in Rochester, MN, believes that its artificial intelligence-enabled algorithm could improve total hip arthroplasty (THA) radiographic surveillance efforts.

Detecting subtle subsidence in THA patients can be challenging for radiologists and orthopedic surgeons alike, according to the group, which includes presenter Dr. Pouria Rouzrokh.

The researchers developed an image processing algorithm to measure subsidence by automatically annotating reference points on the femur and implant. They then compared the algorithm's performance and manual subsidence measurements by two independent orthopedic surgeons on 135 patients.

The mean, median, and standard deviation of measurement discrepancy between the automatic and manual measurements were 0.6, 0.3, and 0.7 mm, the team found. The deep-learning tool quantified subsidence as small as 0.1 mm. Automatic and manual measurements were strongly correlated and had no significant differences. Also, an app version of the tool annotated radiographs and measured subsidence in less than 12 seconds per patient, the researchers added.

"Our tool has implications both in the clinic and research settings and can be leveraged to accelerate and automate the measurement process," the group wrote.

Check out the session to get the details.


Copyright © 2021 AuntMinnie.com

Last Updated er 11/18/2021 4:09:58 PM