Medical experts often examine hundreds of spine x-rays to determine existence of diseases like
osteoarthritis, osteoporoses, and osteophites. Accurate vertebrae segmentation plays a great role in the
proper assessment of various vertebral abnormalities. Manual segmentation methods are both time
consuming and non-reproducible, hence, developing efficient computer-assisted segmentation methods has
been a long standing goal. Over the past decade, segmentation methods that utilize statistical models of
shape and appearance have drawn much interest within the medical imaging community. However, despite
being a promising approach, they are always faced with a number of challenges such as: poor image
quality, and the ability to generalize well to unseen vertebral deformities.
This paper presents a novel vertebral segmentation method using Contourlet-based salient point matching
and a localized multi-scale shape prior. We employ a multi-scale directional analysis tool, namely
contourlets, to build local appearance profiles at salient points of the vertebra's body. The contourlet-based
local appearance model is used to detect the vertebral bodies in the test x-ray image. A novel localized
multi-scale shape prior is used to drive the segmentation process. Within a best-basis selection framework,
the proposed shape prior benefits from the multi-scale nature of wavelet packets, and the capability of ICA
to capture hidden independent modes of variations. Experiments were conducted using a set of 100 digital
x-ray images of lumbar spines. The contourlet-based appearance profiles and the localized multi-scale
shape prior were constructed using a training subset of images, and then matched to unseen images.
Promising results were obtained compared to related work in the literature with an average segmentation
error of 1.1997 mm.