Semi-automatic determination of detailed vertebral shape from lumbar radiographs using active appearance models
The vertebral endplates in lumbar radiographs were located by a semi-automatic annotation method using statistical shape models.
Vertebral fractures are common osteoporotic fractures, but current quantitative detection methods (morphometry) lack specificity. We have previously developed more specific quantitative classifiers of vertebral fracture using shape and appearance models. This method has only been applied to DXA vertebral fracture assessment (VFA) images and not to spinal radiographs. The classifiers require a detailed annotation of the outline of the vertebral endplate, so we investigated the application of similar semi-automated annotation methods to lumbar radiographs as the initial step in the generalisation of the statistical classifiers used in VFA images.
The vertebral body outlines in a training set of 670 lumbar radiographs were manually annotated by expert radiologists. This training set was used to build statistical models of vertebral shape and appearance using triplets of vertebrae. In order to segment vertebrae, the models were refitted using a sequence of active appearance models of vertebral triplets, using a miss-40-out train/test cross-validation experiment. The accuracy was evaluated against the manual annotation and analysed by fracture grade.
Good accuracy was obtained for normal vertebrae (0.82 mm) and fracture grades 1 and 2 (1.19 mm), but the localisation accuracy deteriorated for grade 3 fractures to 2.12 mm.
Vertebral body shape annotation can be substantially automated on lumbar radiographs. However, an occasional manual correction may be required, typically with either severe fractures, or when there is a high degree of projectional tilting or scoliosis. The located detailed shapes may enable the development of more powerful quantitative classifiers of osteoporotic vertebral fracture.
KeywordsActive appearance model Annotation Computer-assisted diagnosis Osteoporosis Vertebral fracture
The authors acknowledge the kind provision of digitised training images by the team at the University of Sheffield (Professor R. Eastell and Dr. L. Ferrar). We thank Professor Cyrus Cooper (Universities of Southampton and Oxford) and Professor David Reid (University of Aberdeen) for permission to use radiographs from earlier studies. The authors wish to thank Mr Stephen Capener (SC) who performed the manual annotation of the vertebrae in the first dataset. The work was funded through a grant from Arthritis Research UK, with earlier foundation work having been funded by grants from the Central Manchester University Hospitals NHS Foundation Trust (CMFT) Research Endowment Fund.
Conflicts of interest
- 4.Ensrud KE, Nevitt MC, Palermo L et al (1999) What proportion of incident morphometric vertebral fractures are clinically diagnosed and vice versa? J Bone Miner Res 14(S1):S138Google Scholar
- 19.Cootes TF, Edwards GJ, Taylor CJ (1998) Active appearance models. In: Burkhardt H, Neumann B (eds) Proc. 5th European conference on computer vision. Springer, Berlin, pp 484–498Google Scholar
- 25.Scott IM, Cootes TF, Taylor CJ (2003) Improving active appearance model matching using local image structure. In: Proceedings of the 18th conference on information processing in medical imaging, Ambleside, UK, July 20–25, 2003, pp 258–269Google Scholar
- 26.Roberts MG (2008) Automatic detection and classification of vertebral fracture using statistical models of appearance. PhD thesis, University of ManchesterGoogle Scholar
- 27.Howe B, Gururajan A, Sari-Sarraf H et al. (2004) Hierarchical segmentation of cervical and lumbar vertebrae using a customized generalized hough transform and extensions to active appearance models. In: Proceedings IEEE 6th SSIAI, Lake Tahoe, NV, March 2004, 182–186Google Scholar
- 28.de Bruijne M, Nielsen M. (2004) Image segmentation by shape particle filtering. In: Proc. International Conference on Pattern Recognition 2004, 722–725Google Scholar