Computer-aided diagnosis in chest radiography: a survey

The traditional chest radiograph is still ubiquitous in clinical practice, and will likely remain so for quite some time. Yet, its interpretation is notoriously difficult. This explains the continued interest in computer-aided diagnosis for chest radiography. The purpose of this survey is to categorize and briefly review the literature on computer analysis of chest images, which comprises over 150 papers published in the last 30 years. Remaining challenges are indicated and some directions for future research are given.     

Object shape dependent PSF model for SPECT imaging

An analytical expression for the point spread function (PSF) and the line spread function (LSF) of a parallel hole gamma camera is presented, for homogeneous media and for photons having mainly Compton interactions in the object. The PSF of scattered photons is described by convolving a zeroth-order modified Bessel function of the second kind with the unscattered PSF, which is approximated by a Gaussian. The complete PSF (scatter plus nonscatter) depends on the source distance ( z) and depth (d) of the source in the object. For convex-shaped emitting objects, the dependence of the PSF on the object contour can be incorporated by a simple correction. Thus, a complete mathematical model of the imaging of an activity distribution in a homogeneous medium is obtained. The model has been evaluated for ^99mTechnetium line sources by using a LEAP collimator at various energy windows (ΔE). It is shown that the model is valid to a high accuracy at ΔE=15%, for a large range of values of z and d     

CTA-based angle selection for diagnostic and interventional angiography of saccular intracranial aneurysms

Coil embolization is a safe treatment for cerebral aneurysms only if the width of the neck in relation to the fundus of the aneurysm is small. Therefore, accurate visualization of the aneurysmal neck is required both in the diagnostic process and during the intervention. Conventional digital subtraction angiography (DSA) is still the preferred modality for the examination of cerebrovascular abnormalities like aneurysms, but it often does not provide the required morphological characteristics due to the suboptimal selection of projection angles and resulting overprojections of surrounding vasculature. This paper presents a method for performing a computer-assisted calculation of the optimal projection angles for DSA by post-processing computed tomographic angiography (CTA) volume data using ray-casting techniques and a combination of image processing algorithms. By means of phantom studies, retrospective simulations of angiograms, and in vivo applications of calculated optimal viewing angles, it is demonstrated that the proposed method results in better angiographic projections of the neck of saccular aneurysms with small neck-fundus ratio than those acquired at standard angles prescribed by clinical protocols.     

Automated lumen definition from 30 MHz intravascular ultrasound images

One prerequisite for standard clinical use of intravascular ultrasound imaging is rapid evaluation of the data. The main quantities to be extracted from the data are the size and the shape of the lumen. Until now, no accurate, robust and reproducible method to obtain the lumen boundaries from intravascular ultrasound images has been described. In this study, 21 different (semi-)automated binary-segmentation methods for determining the lumen are compared with manual segmentation to find an alternative for the laborious and subjective procedure of manual editing. After a preprocessing step in which the catheter area is filled with lumen-like grey values, all approaches consist of two steps: (i) smoothing the images with different filtering methods and (ii) extracting the lumen by an object definition method. The combination of different filtering methods and object definition methods results in a total of 21 methods and 80 experiments. The results are compared with a reference image, obtained from manual editing, by use of four different quality parameters--two based on squared distances and two based on Mahalanobis distances. The evaluation has been carried out on 15 images, of which seven are obtained before balloon dilation and eight after balloon dilation. While for the post-dilation images no definite conclusions can be drawn, an automated contour model applied to images smoothed with a large kernel appears to be a good alternative to manual contouring. For pre-dilation images a fully automated active contour model, initialized by thresholding, preceded by filtering with a small-scale median filter is the best alternative for manual delineation. The results of this method are even better than manual segmentation, i.e. they are consistently closer to the reference image than the average distance of all individual manual segmentations.     

Memoryless pipelined trigonometric processor

The development and results of memoryless algorithms for the evaluation of sinusoidal functions are described. Differing from the MacLaurin power series method, the algorithms proposed here use the binary representation of an angle in a pipelined manner to calculate sinusoidal functions.<>     

A trained spin-glass model for grouping of image primitives

A method is presented that uses grouping to improve local classification of image primitives. The grouping process is based upon a spin-glass system, where the image primitives are treated as possessing a spin. The system is subject to an energy functional consisting of a local and a bilocal part, allowing interaction between the image primitives. Instead of defining the state of lowest energy as the grouping result, the mean state of the system is taken. In this way, instabilities caused by multiple minima in the energy are being avoided. The means of the spins are taken as the a posteriori probabilities for the grouping result. In the paper, it is shown how the energy functional can be learned from example data. The energy functional is defined in such a way that, in case of no interactions between the elements, the means of the spins equal the a priori local probabilities. The grouping process enables the fusion of the a priori local and bilocal probabilities into the a posteriori probabilities. The method is illustrated both on grouping of line elements in synthetic images and on vessel detection in retinal fundus images.     

Invertible Apertured Orientation Filters in Image Analysis

A unitary approach for locally apertured orientation analysis of 2D and 3D scalar images is proposed. The size of the local aperture (the scale) needed for the orientation representation induces in general a lost of spatial acuity, or blur. Our construction permits a compensation of the blur by a reconstruction procedure. For this purpose, a special scale-dependent orientation bundle (map of the visual space into function of both position and orientation) is build from the local Gaussian-derivatives jet of a scalar image. In this construction there is an invertible relation between the orientation bundle and the original image. This invertible transformation is used to regain the original acuity in the spatial domain after analyzing orientation features at any given scale.The approach turns out to be highly effective for the detection of elongated structures and for removal of elongated artifacts in 2D images.     

Evaluation of registration methods on thoracic CT: the EMPIRE10 challenge

EMPIRE10 (Evaluation of Methods for Pulmonary Image REgistration 2010) is a public platform for fair and meaningful comparison of registration algorithms which are applied to a database of intrapatient thoracic CT image pairs. Evaluation of nonrigid registration techniques is a nontrivial task. This is compounded by the fact that researchers typically test only on their own data, which varies widely. For this reason, reliable assessment and comparison of different registration algorithms has been virtually impossible in the past. In this work we present the results of the launch phase of EMPIRE10, which comprised the comprehensive evaluation and comparison of 20 individual algorithms from leading academic and industrial research groups. All algorithms are applied to the same set of 30 thoracic CT pairs. Algorithm settings and parameters are chosen by researchers expert in the configuration of their own method and the evaluation is independent, using the same criteria for all participants. All results are published on the EMPIRE10 website (http://empire10.isi.uu.nl). The challenge remains ongoing and open to new participants. Full results from 24 algorithms have been published at the time of writing. This paper details the organization of the challenge, the data and evaluation methods and the outcome of the initial launch with 20 algorithms. The gain in knowledge and future work are discussed.     

Retrospective correction of MR intensity inhomogeneity byinformation minimization

In this paper, the problem of retrospective correction of intensity inhomogeneity in magnetic resonance (MR) images is addressed. A novel model-based correction method is proposed, based on the assumption that an image corrupted by intensity inhomogeneity contains more information than the corresponding uncorrupted image. The image degradation process is described by a linear model, consisting of a multiplicative and an additive component which are modeled by a combination of smoothly varying basis functions. The degraded image is corrected by the inverse of the image degradation model. The parameters of this model are optimized such that the information of the corrected image is minimized while the global intensity statistic is preserved. The method was quantitatively evaluated and compared to other methods on a number of simulated and real MR images and proved to be effective, reliable, and computationally attractive. The method can be widely applied to different types of MR images because it solely uses the information that is naturally present in an image, without making assumptions on its spatial and intensity distribution. Besides, the method requires no preprocessing, parameter setting, nor user interaction. Consequently, the proposed method may be a valuable tool in MR image analysis.