[en] Vertebra segmentation; [en] Template matching; [en] Medical image analysis
Abstract :
[en] In the last years, medical image processing methods have been successfully applied to the diagnosis of various disease. Image segmentation is one of the most important steps in image processing, which provides the homogeneous regions and make the images easier to analyze. In the context of conventional radiography of vertebrae, segmentation becomes a challenging stage due to low level contrast and noises present in this imaging modality. In this work, we describe a robust method to segment cervical vertebrae in X-ray images. Our model-based segmentation enables the extraction of accurate clinical data from the input images.
Research center :
CRTI - Centre de Recherche en Technologie de l'Information