A Tool for Automatic Estimation of Patient Position in Spinal CT Data

TL;DR

This paper introduces an automatic tool that uses CNNs to accurately rotate spinal CT scans into a standard position, facilitating better data consistency for research and clinical use.

Contribution

It presents a novel CNN-based method for automatic patient position estimation in spinal CT data, achieving high accuracy and providing accessible implementations.

Findings

Achieved 99.55% accuracy in rotation prediction

Enabled automatic correction of patient positioning in spinal CT scans

Provided user-friendly implementations in Matlab and Python

Abstract

Much of the recently available research and challenge data lack the meta-data containing any information about the patient position. This paper presents a tool for automatic rotation of CT data into a standardized (HFS) patient position. The proposed method is based on the prediction of rotation angle with CNN, and it achieved nearly perfect results with an accuracy of 99.55 %. We provide implementations with easy to use an example for both Matlab and Python (PyTorch), which can be used, for example, for automatic rotation correction of VerSe2020 challenge data.