Compression Fractures Detection on CT

TL;DR

This paper introduces an automated deep learning-based method for detecting vertebral compression fractures in CT scans, aiming to improve diagnosis accuracy and reduce missed cases in osteoporosis management.

Contribution

It presents a novel combination of CNN and RNN models for efficient and accurate detection of compression fractures in spine CT images.

Findings

High detection accuracy demonstrated in experiments

Reduced false negatives compared to manual diagnosis

Potential for clinical application in osteoporosis screening

Abstract

The presence of a vertebral compression fracture is highly indicative of osteoporosis and represents the single most robust predictor for development of a second osteoporotic fracture in the spine or elsewhere. Less than one third of vertebral compression fractures are diagnosed clinically. We present an automated method for detecting spine compression fractures in Computed Tomography (CT) scans. The algorithm is composed of three processes. First, the spinal column is segmented and sagittal patches are extracted. The patches are then binary classified using a Convolutional Neural Network (CNN). Finally a Recurrent Neural Network (RNN) is utilized to predict whether a vertebral fracture is present in the series of patches.