<title>Statistical models of appearance for medical image analysis and computer vision</title>

TLDR

Statistical models of shape and appearance are powerful tools for interpreting medical images. The paper describes two matching approaches and demonstrates their application to various problems. The authors build statistical shape, texture, and shape–texture models from landmarked training images, then fit them to target images by optimizing parameters, using Active Shape and Active Appearance Models with difference‑decomposition updates for rapid matching. With sufficient training data, these models can synthesize any image of normal anatomy.

Abstract

Statistical models of shape and appearance are powerful tools for interpreting medical images. We assume a training set of images in which corresponding landmark points have been marked on every image. From this data we can compute a statistical model of the shape variation, a model of the texture variation and a model of the correlations between shape and texture. With enough training examples such models should be able to synthesize any image of normal anatomy. By finding the parameters which optimize the match between a synthesized model image and a target image we can locate all the structures represented by the model. Two approaches to the matching will be described. The Active Shape Model essentially matches a model to boundaries in an image. The Active Appearance Model finds model parameters which synthesize a complete image which is as similar as possible to the target image. By using a difference decomposition approach the current difference between target image and synthesized model image can be used to update the model parameters, leading to rapid matching of complex models. We will demonstrate the application of such models to a variety of different problems.