Detecting and characterizing vertebral fractures in CT scans

Start date: 01-02-2021
End date: 31-07-2021

Clinical problem

Osteoporosis is a silent age-related disease that slowly decreases the stability of the bones, which eventually leads to bones starting to fracture and collapse. These kind of fractures are referred to as compression fractures. Every year, millions of CT scans of the thorax and abdomen are made worldwide, for reasons other than osteoporosis and compression fractures, but providing the opportunity to detect compression fractures of the spine.

Solution

The goal of this project is to develop a system that automatically determines for each vertebra visible on a CT scan whether it is normal or whether it is fractured and collapsed, or is starting to collapse. For abnormal vertebrae, the system can quantify the degree to which the bone has collapsed in order to distinguish between early stage fractures and advanced fractures.

People

Michel Botros

Michel Botros

Master Student

Diagnostic Image Analysis Group

Nikolas Lessmann

Nikolas Lessmann

Assistant Professor

Diagnostic Image Analysis Group

Stan Buckens

Stan Buckens

Radiologist

Radiology, Radboudumc

Matthieu Rutten

Matthieu Rutten

Associate Professor, Radiologist

Diagnostic Image Analysis Group

Bram van Ginneken

Bram van Ginneken

Professor

Diagnostic Image Analysis Group