Identifying vertebral end plate lesions (schmorl's nodes) using a semi-automatic method

Newell, Nicolas, Grant, Caroline A., Izatt, Maree T., Little, J. Paige, Pearcy, Mark J., & Adam, Clayton J. (2015) Identifying vertebral end plate lesions (schmorl's nodes) using a semi-automatic method. In Williams, Richard (Ed.) 26th Annual Scientific Meeting of the Spine Society of Australia, 10-12 April 2015, National Convention Centre, Canberra, A.C.T.

PDF (13kB)



There is a large range in the reported prevalence of end plate lesions (EPLs), sometimes referred to as Schmorl's nodes in the general population (3.8-76%). One possible reason for this large range is the differences in definitions used by authors. Previous research has suggested that EPLs may potentially be a primary disturbance of growth plates that leads to the onset of scoliosis. The aim of this study was to develop a technique to measure the size, prevalence and location of EPLs on Computed Tomography (CT) images of scoliosis patients in a consistent manner.


A detection algorithm was developed and applied to measure EPLs for five adolescent females with idiopathic scoliosis (average age 15.1 years, average major Cobb 60°). In this algorithm, the EPL definition was based on the lesion depth, the distance from the edge of the vertebral body and the gradient of the lesion edge. Existing low-dose, CT scans of the patients' spines were segmented semi-automatically to extract 3D vertebral endplate morphology. Manual sectioning of any attachments between posterior elements of adjacent vertebrae and, if necessary, endplates was carried out before the automatic algorithm was used to determine the presence and position of EPLs.


EPLs were identified in 15 of the 170 (8.8%) endplates analysed with an average depth of 3.1mm. 73% of the EPLs were seen in the lumbar spines (11/15). A sensitivity study demonstrated that the algorithm was most sensitive to changes in the minimum gradient required at the lesion edge.


An imaging analysis technique for consistent measurement of the prevalence, location and size of EPLs on CT images has been developed. Although the technique was tested on scoliosis patients, it can be used to analyse other populations without observer errors in EPL definitions.

Impact and interest:

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

16 since deposited on 23 Sep 2015
9 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 87647
Item Type: Conference Item (Other)
Refereed: Yes
Additional URLs:
Keywords: vertebral endplate, endplate lesion, endplate irregularity, schmorl's nodes, semi-automatic method, computer algorithm, idiopathic scoliosis
Subjects: Australian and New Zealand Standard Research Classification > ENGINEERING (090000) > BIOMEDICAL ENGINEERING (090300) > Biomechanical Engineering (090302)
Australian and New Zealand Standard Research Classification > MEDICAL AND HEALTH SCIENCES (110000) > CLINICAL SCIENCES (110300) > Orthopaedics (110314)
Divisions: Current > Schools > School of Chemistry, Physics & Mechanical Engineering
Current > Institutes > Institute of Health and Biomedical Innovation
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Copyright 2015 The Authors
Deposited On: 23 Sep 2015 01:37
Last Modified: 23 Sep 2015 01:37

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page