Automatic Extraction of Spinopelvic Parameters Using Deep Learning to Detect Landmarks as Objects
Ali Asghar Mohammadi Nasrabadi, William McNally, Gemah Moammer, John McPhee
Surgeons measure spinopelvic parameters from X-ray images to evaluate spinopelvic alignment preoperatively for surgical planning. Automatic extraction of these parameters not only saves time but also provides consistent measurements, avoiding human error. In this paper, we introduce a new approach to automatic spinopelvic parameter extraction, which considers landmarks as objects. The landmarks are extracted using a deep learning object detection algorithm that can address the drawbacks of heatmap-based regression. The model is evaluated using two datasets totalling 1000 lateral spinal and pelvic X-ray images. Acceptable accuracy is achieved when comparing the reference manual parameter measurements with those obtained automatically by our prediction model.
Friday 8th July
Poster Session 3.2 - onsite 11:00 - 12:00, virtual 15:20 - 16:20 (UTC+2)