The analysis of medical images has been woven into the fabric of the pattern analysis and machine intelligence (PAMI) community since the earliest days of these Transactions. Initially, the efforts in this area were seen as applying pattern analysis and computer vision techniques to another interesting dataset. However, over the last two to three decades, the unique nature of the problems presented within this area of study have led to the development of a new discipline in its own right. Examples of these include: the types of image information that are acquired, the fully three-dimensional image data, the nonrigid nature of object motion and deformation, and the statistical variation of both the underlying normal and abnormal ground truth. In this paper, we look at progress in the field over the last 20 years and suggest some of the challenges that remain for the years to come.

https://hal.inria.fr/inria-00615100/document

Medical image analysis: progress over two decades and the challenges ahead

Segmentation using boundary finding is enhanced both by considering the boundary as a whole and by using model-based global shape information. The authors apply flexible constraints, in the form of a probabilistic deformable model, to the problem of segmenting natural 2-D objects whose diversity and irregularity of shape make them poorly represented in terms of fixed features or form. The parametric model is based on the elliptic Fourier decomposition of the boundary. Probability distributions on the parameters of the representation bias the model to a particular overall shape while allowing for deformations. Boundary finding is formulated as an optimization problem using a maximum a posteriori objective function. Results of the method applied to real and synthetic images are presented, including an evaluation of the dependence of the method on prior information and image quality. >

/pdf/boundary-finding-with-parametrically-deformable-models-1sb2rkma2i.pdf

Boundary finding with parametrically deformable models

Modal matching is a new method for establishing correspondences and computing canonical descriptions. The method is based on the idea of describing objects in terms of generalized symmetries, as defined by each object's eigenmodes. The resulting modal description is used for object recognition and categorization, where shape similarities are expressed as the amounts of modal deformation energy needed to align the two objects. In general, modes provide a global-to-local ordering of shape deformation and thus allow for selecting which types of deformations are used in object alignment and comparison. In contrast to previous techniques, which required correspondence to be computed with an initial or prototype shape, modal matching utilizes a new type of finite element formulation that allows for an object's eigenmodes to be computed directly from available image information. This improved formulation provides greater generality and accuracy, and is applicable to data of any dimensionality. Correspondence results with 2D contour and point feature data are shown, and recognition experiments with 2D images of hand tools and airplanes are described. >

/pdf/modal-matching-for-correspondence-and-recognition-e1qs3uolnt.pdf

Modal matching for correspondence and recognition

DRAMMS: Deformable registration via attribute matching and mutual-saliency weighting

https://www.cbica.upenn.edu/sbia/papers/cviu97.pdf

Spatial transformation and registration of brain images using elastically deformable models

The problem of measuring the motion of deformable objects from image sequences is addressed. The approach is based upon modeling the overall boundary of the object as a deformable contour and then tracking local segments of the contour through the temporal sequence. Motion computation involves first matching the local segments between pairs of contours by minimizing the deformation between the segments using a measure of bending energy. Results from the match process are incorporated into an optimization functional, along with a general smoothness term, whose local minimum results in a smooth flow field that is consistent with the match data. The computation is performed for all pairs of frames in the temporal sequence, resulting in a composite flow field over the entire sequence. The technique is applied to synthetic contour sequences and the problem of tracking left ventricular (LV) endocardial motion from medical image sequences. >

Measurement of non-rigid motion using contour shape descriptors

A unified framework for visual motion tracking of non-rigid objects with specific applications to the left ventricular endocardial wall motion is outlined. The theory considers both two dimensional contours and three dimensional surfaces and in each case uses an elastic model of the object with constraints on the types of motion allowed for tracking the movement. The basic theme in both two and three dimensional analysis is to match bending and stretching properties of shapes in consecutive time instances for deducing quantitative information about the motion of the LV wall. Several algorithms are presented, and applications to real and simulated data are included. At the end, future directions for research are discussed.

Non-Rigid Motion Models for Tracking the Left Ventricular Wall

A new approach for tracking and quantifying the nonrigid, nonuniform motion of the left ventricular (LV) endocardial wall from cardiac image sequences, on a point-by-point basis over the entire cardiac cycle, is presented. The first step in the algorithm uses one of two approaches to estimate the LV boundary from each image in the sequence. Motion computation involves first matching local segments on one contour to segments on the next contour in the sequence using a shape-based strategy based on bending energy. Results from the match process are incorporated into an optimization functional, along with a smoothness term. The nearest local minimum of the functional to the initial match is found, resulting in a smooth flow field that is consistent with the match data. The computation is performed for all pairs of frames in the temporal sequence and equally sampled points on one contour are tracked throughout the sequence, resulting in a composite flow field over the entire sequence. The method provides a more accurate estimate of perceived motion than previous techniques. >

Shape-based tracking of left ventricular wall motion

The use of mathematical models and optimization theory is suggested as a unifying approach to solving certain automated segmentation and analysis problems in medical imaging. Within this framework, the authors present three examples. Being able to view segmented objects and/or quantitative descriptions of an object's shape, size, and movement properties is felt to be an improved form of visualizing the anatomy for purposes of diagnosis. The first two examples are related to extracting features and ultimately segmenting outlines of objects, useful for many 2D anatomical object recognition problems. The third example is an analysis method that is specific to the problem of tracking motion of the wall of the left ventricle of the heart. >

Medical image analysis using model-based optimization

This paper has presented the formulation and initial results for a new algorithm aimed at estimating and quantifying the trajectories of points on the left ventricular wall of the heart based on two- dimensional image-derived shape information. The algorithm is based on first automatically estimating the LV contour for two frames and then sampling the contours and tracking the motion of each sample point. Work is currently in progress to evaluate and compare each of three shape-based matching criteria, and to extend the algorithm to multiple frames. Future work will extend the approach to three spatial dimensions, capitalizing on the idea that all of the basic concepts, including curvature measurement, can be readily adapted for the higher dimensional problem.

R.L. Owen

Papers

Measurement of non-rigid motion using contour shape descriptors

Non-Rigid Motion Models for Tracking the Left Ventricular Wall

Shape-based tracking of left ventricular wall motion

Medical image analysis using model-based optimization

Measurement of left ventricular wall motion from contour shape deformation.