Automatic Extraction of Spinopelvic Parameters Using Deep Learning to Detect Landmarks as Objects

AliAsghar MohammadiNasrabadi, William McNally, Gemah Moammer, John McPhee

Keywords: medical imaging, deep learning, spinopelvic parameters, object detection

TL;DR: Automatic extraction of spinopelvic parameters, provides consistency in annotations and parameter mesurements besides saving time from surgeons.

Abstract: 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.

Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: novel methodological ideas without extensive validation

Primary Subject Area: Detection and Diagnosis

Secondary Subject Area: Application: Radiology

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.