Automatic prosthetic-parameter estimation from anteroposterior pelvic radiographs after total hip arthroplasty using deep learning-based keypoint detection.

Tsung-Wei TsengYueh-Peng ChenYu-Cheng YehChang-Fu KuoTzuo-Yau FanSheng-Hsun Lee

Published in: The international journal of medical robotics + computer assisted surgery : MRCAS (2022)

The accuracy of BKNet is equivalent to that of human observers, and BKNet was able to perform prosthetic-parameter estimation from keypoint detection with superior cost-effectiveness, repeatability, and timesaving compared to human observers.

Keyphrases

deep learning
endothelial cells
total hip arthroplasty
machine learning
loop mediated isothermal amplification
label free
real time pcr
rectal cancer
convolutional neural network
sensitive detection