15th International Conference, IPMI'97 Poultney, Vermont, USA, June 9–13, 1997 Proceedings
A new approach to the problem of automatic construction of eigenshape models is presented. Eigenshape models have proved to be successful in a variety of medical image analysis problems. However, automatic model construction is a difficult problem, and in many applications the models are built by hand — a painstaking process. Previous attempts to produce models automatically have been applicable only...
Hitherto no constitutive formalism of deformations provides a parameterization for the visually obvious features of their transformation grids. This paper notes a property of the thin-plate spline that one may exploit to this end. The bending energy that is minimized by the spline, usually expressed in matrix form, is also the double integral of the output of a nonlinear differential operator, the...
The problem of matching shapes parameterized as a set of points is frequently encountered in medical imaging tasks. When the point-sets are derived from landmarks, there is usually no problem of determining the correspondences or homologies between the two sets of landmarks. However, when the point sets are automatically derived from images, the difficult problem of establishing correspondence and...
Ultrasonic techniques are presented for the study of soft biological tissue structure and function. Changes in echo waveforms caused by microscopic variations in the elastic properties of tissue can reveal disease mechanism, in vivo. On a larger scale, elasticity imaging describes the macroscopic elastic properties of soft tissues. We present an analysis framework and preliminary results for studying...
We developed an Intravascular Impedance Catheter (2D-IIC) together with a non-iterative, non-linear reconstruction algorithm, capable of assessing a series of 2D discretized images of the impedance distribution of the arterial wall. The 2D-IIC uses a differential measurement technique based on our early version of the IIC [1], but features two new elements: asymetrically placed electrodes and...
This paper addresses the problem of image reconstruction in optical tomography with respect to the measurement types used. We demonstrate the difficulty of the simultaneous reconstruction of absorption and diffusion images, by using both a simple circular case with embedded inhomogeneities, and a complex neonatal head model, and show that improvements are possible by combining suitable measurement...
Recent advances in SPECT and PET technology permit ECG gating of tomographic cardiac images, allowing simultaneous measurement of 3D cardiac ventricular function with perfusion/metabolism. Extracting indices of regional function from these 4D data sets (3D space + time) remains a challenge. All approaches currently used to quantitate gated tomographic sequences deal separately with the spatial and...
This work demonstrates encouraging initial results for increasing the automation of a practical and precise MR brain image segmentation method. The intensity threshold for segmenting the brain exterior is automatically determined by locating the choroid plexus. This is done by finding peaks in a series of histograms taken over regions specified using anatomical knowledge. Intensity inhomogeneities...
We have developed an algorithm for segmenting objects with closed, non-intersecting boundaries, such as the heart and the lungs, that is independent of the imaging modality used (e.g., MRI, CT, echocardiography). Our method is automatic and requires as initialization a single pixel/voxel within the boundaries of the object. Existing segmentation techniques either require much more information during...
Robust segmentation of normal anatomical objects in medical images requires (1) methods for creating object models that adequately capture object shape and expected shape variation across a population, and (2) methods for combining such shape models with unclassified image data to extract modeled objects. Described in this paper is such an approach to model-based image segmentation, called deformable shape loci...
We propose a methodology for extracting parametric representations of the cerebral sulci from magnetic resonance images, and we consider its application to two medical imaging problems: quantitative morphological analysis and spatial normalization and registration of brain images. Our methodology is based on deformable models utilizing characteristics of the cortical shape. Specifically, a parametric...
This paper describes a general approach to signal detection with uncertainty in signal and/or background distributions. Attention is restricted to binary decision problems where the hypotheses can be expressed as signal-present vs signal-absent, but otherwise the treatment is general. Many familiar results come out as special cases.
The performance of Maximum Likelihood (ML) and Maximum a posteriori (MAP) estimates in nonlinear problems at low data SNR is not well predicted by the Cramér-Rao or other lower bounds on variance. In order to better characterize the distribution of ML and MAP estimates under these conditions, we derive an approximate density for the conditional distribution of such estimates. In one example, this...
When the projection of a collection of samples onto a subset of basis feature vectors has a Gaussian distribution, those samples have a generalized projective Gaussian distribution (GPGD). GPGDs arise in a variety of medical images as well as some speech recognition problems. We will demonstrate that GPGDs are better represented by continuous Gaussian mixture models (CGMMs) than finite Gaussian mixture...
PET measurements are usually precorrected for accidental coincidence events by real-time subtraction of the delayed window coincidences. Randoms subtraction compensates in mean for accidental coincidences but destroys the Poisson statistics. We propose and analyze two new approximations to the exact log-likelihood of the precorrected measurements, one based on a “shifted Poisson” model, the other...
Multimodal medical images are often of too different a nature to be registered on the basis of the image grey values only. It is the purpose of this paper to construct operators that extract similar structures from these images that will enable registration by simple grey value based methods, such as maximization of cross-correlation. These operators can be constructed using only basic morphological...
In image guided neurosurgery it is necessary to align preoperative image data with the patient. The rigid body approximation is usually applied, but is often not valid due to tissue deformation. Most non-rigid registration algorithms, such as those used for atlas matching, provide a smooth deformation, which does not model the characteristics of different tissues accurately since, for example, bone...
The present study investigates the possibility to utilize Compton scatter data for registration of abdominal SPECT images. A method for registration to CT is presented, based on principal component analysis and cross-correlation of binary images representing the interior of the patient. Segmentation of scatter images is performed with two methods, thresholding and a deformable contour method. To achieve...
Volume transformations of medical images play an important role for many applications such as registration of different modalities, mapping atlases onto clinical data, or simulation of surgical procedures. While registration and atlas mapping can for the major number of applications be performed without tight time constraints, it is essential for simulation systems that they allow real-time interaction...
We introduce the concept of generalization for models of functional neuroactivation, and show how it is affected by the number, N, of neuroimaging scans available. By plotting generalization as a function of N (i.e. a “learning curve”) we demonstrate that while simple, linear models may generalize better for small N's, more flexible, low-biased nonlinear models, based on artificial neural networks...