Fully Automatic Localisation of Vertebrae in CT images using Random Forest Regression Voting

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We describe a system for fully automatic vertebra localisation and segmentation in 3D CT volumes containing arbitrary regions of the spine, with the aim of detecting osteoporotic fractures. To avoid the difficulties of high-resolution manual annotation on overlapping structures in 3D, the system consists of several 2D operations. First, a Random Forest regressor is used to localise the spinal midplane in a coronal maximum intensity projection. A 2D sagittal image showing the midplane is then produced. A second set of regressors are used to localise each vertebral body in this image. Finally, a Random Forest Regression Voting Constrained Local Model is used to segment each detected vertebra.

The system was evaluated on 402 CT volumes. 83% of vertebrae between T4 and L4 were detected and, of these, 97% were segmented with a mean error of less than or equal to 1mm . A simple classifier was applied to perform a fracture/non-fracture classification for each image, achieving 69% recall at 70% precision.
Original languageEnglish
Title of host publicationComputational Methods and Clinical Applications for Spine Imaging
Subtitle of host publication4th International Conference and Challenge, CSI 2016
EditorsJianhua Yao, Tomaz Vrtovec, Guoyan Zheng, Alejandro Frangi, Ben Glocker, Shuo Li
PublisherSpringer Nature
Number of pages13
VolumeLNCS 10182
ISBN (Electronic)9783319550503
ISBN (Print)9783319550497, 9783319550503
Publication statusPublished - 1 Mar 2017

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743


Dive into the research topics of 'Fully Automatic Localisation of Vertebrae in CT images using Random Forest Regression Voting'. Together they form a unique fingerprint.

Cite this