Acquisition, analysis, and integration of medical images with nonimage biomedical information are essential for research and clinical practice. Individualization of health care, assessment of disease risk, tailoring of therapies, and lifelong monitoring places extraordinary demands on emerging technologies in medical imaging, information management, and molecular medicine. To achieve the anticipated benefits in outcomes that new technology can deliver, imaging informatics infrastructure and tools must be available to represent, store, integrate, and present the data in a useful manner. Currently, images are not well integrated with other forms of biological knowledge. This paper outlines the clinical and research requirements for imaging, and identifies barriers to progress and links these needs with the current and future informatics technologies that may overcome them.

Directional features are extremely important in diagnostic imaging. They can be used either in the searching for important indications of abnormality or for the reference in image alignment. The wavelet transform (WT) as an efficient method for multiresolution representation has been used extensively in medical imaging. However, from the view point of directional selectivity it is not so efficient in feature extraction. In this paper, an analysis and comparison of directional selectivity of wavelet transforms with three different frequency decompositions were undertaken. WTs with radial-angular decomposition were used for two medical imaging problems: mass detection in digital mammography and lung nodule detection in chest radiography. The results demonstrated its efficiency.

A multiresolution statistical method for identifying clinically normal tissue in digitized mammograms is used to construct an algorithm for separating normal regions from potentially abnormal regions; that is, small regions that may contain isolated calcifications. This is the initial phase of the development of a general method for the automatic recognition of normal mammograms. The first step is to decompose the image with a wavelet expansion that yields a sum of independent images, each containing different levels of image detail. When calcifications are present, there is strong empirical evidence that only some of the image components are necessary for the purpose of detecting a deviation from normal. The underlying statistic for each of the selected expansion components can be modeled with a simple parametric probability distribution function. This function serves as an instrument for the development of a statistical test that allows for the recognition of normal tissue regions. The distribution function depends on only one parameter, and this parameter itself has an underlying statistical distribution. The values of this parameter define a summary statistic that can be used to set detection error rates. Once the summary statistic is determined, spatial filters that are matched to resolution are applied independently to each selected expansion image. Regions of the image that correlate with the normal statistical model are discarded and regions in disagreement (suspicious areas) are flagged. These results are combined to produce a detection output image consisting only of suspicious areas. This type of detection output is amenable to further processing that may ultimately lead to a fully automated algorithm for the identification of normal mammograms.

Multi-resolution and multi-orientation are part of the biological mechanism of human visual system. The interest in multi-resolution image analysis has been growing rapidly. Comparatively, however, the multi-orientation method has received less attention. Based on the relationship between multifrequency channel decomposition and the wavelet model developed by Mallat [1989], a combined multiresolution/multi-orientation representation by directional wavelet transform (DWT) is introduced in this paper. Because of its high orientation selectivity, the DWT allows the processing of directional information more efficiently. It is applied successfully to feature enhancement and extraction of X-ray mammographic images.

A novel wavelet-based neural network with fuzzy-logic adaptivity (WNNFA) is proposed for image restoration using a nuclear medicine gamma camera based on the measured system point spread function. The objective is to restore image degradation due to photon scattering and collimator photon penetration with the gamma camera and allow improved quantitative external measurements of radionuclides in vivo. The specific clinical model proposed is the imaging of bremsstrahlung radiation using /sup 32/P and /sup 90/Y. The theoretical basis for four-channel multiresolution wavelet decomposition of the nuclear image into different subimages is developed with the objective of isolating the signal from noise. A fuzzy rule is generated to train a membership function using least mean squares to obtain an optimal balance between image restoration and the stability of the neural network, while maintaining a linear response for the camera to radioactivity dose. A multichannel modified Hopfield neural network architecture is then proposed for multichannel image restoration using the dominant signal subimages.

When clustering algorithms are applied to image segmentation, the goal is to solve a classification problem. However, these algorithms do not directly optimize classification duality. As a result, they are susceptible to two problems: 1) the criterion they optimize may not be a good estimator of "true" classification quality, and 2) they often admit many (suboptimal) solutions. This paper introduces an algorithm that uses cluster validity to mitigate problems 1 and 2. The validity-guided (re)clustering (VGC) algorithm uses cluster-validity information to guide a fuzzy (re)clustering process toward better solutions. It starts with a partition generated by a soft or fuzzy clustering algorithm. Then it iteratively alters the partition by applying (novel) split-and-merge operations to the clusters. Partition modifications that result in improved partition validity are retained. VGC is tested on both synthetic and real-world data. For magnetic resonance image (MRI) segmentation, evaluations by radiologists show that VGC outperforms the (unsupervised) fuzzy c-means algorithm, and VGC's performance approaches that of the (supervised) k-nearest-neighbors algorithm.

A computationally efficient mixed feature based neural network (MFNN) is proposed for the detection of microcalcification clusters (MCCs) in digitized mammograms. The MFNN employs features computed in both the spatial and spectral domain and uses spectral entropy as a decision parameter. Backpropagation with Kalman filtering (KF) is employed to allow more efficient network training as required for evaluation of different features, input images, and related error analysis. A previously reported, wavelet-based image-enhancement method is also employed to enhance microcalcification clusters for improved detection. The relative performance of the MFNN for both the raw and enhanced images is evaluated using a common image database of 30 digitized mammograms, with 20 images containing 21 biopsy proven MCCs and ten normal cases. The computed sensitivity (true positive (TP) detection rate) was 90.1% with an average low false positive (FP) detection of 0.71 MCCs/image for the enhanced images using a modified k-fold validation error estimation technique. The corresponding computed sensitivity for the raw images was reduced to 81.4% and with 0.59 FP's MCCs/image. A relative comparison to an earlier neural network (NN) design, using only spatially related features, suggests the importance of the addition of spectral domain features when the raw image data is analyzed.

A technique is proposed for the detection of tumors in digital mammography. Detection is performed in two steps: segmentation and classification. In segmentation, regions of interest are first extracted from the images by adaptive thresholding. A further reliable segmentation is achieved by a modified Markov random field (MRF) model-based method. In classification, the MRF segmented regions are classified into suspicious and normal by a fuzzy binary decision tree based on a series of radiographic, density-related features. A set of normal (50) and abnormal (45) screen/film mammograms were tested. The latter contained 48 biopsy proven, malignant masses of various types and subtlety. The detection accuracy of the algorithm was evaluated by means of a free response receiver operating characteristic curve which shows the relationship between the detection of true positive masses and the number of false positive alarms per image. The results indicated that a 90% sensitivity can be achieved in the detection of different types of masses at the expense of two falsely detected signals per image. The algorithm was notably successful in the detection of minimal cancers manifested by masses </=10 mm in size. For the 16 such cases in the authors' dataset, a 94% sensitivity was observed with 1.5 false alarms per image. An extensive study of the effects of the algorithm's parameters on its sensitivity and specificity was also performed in order to optimize the method for a clinical, observer performance study.

A novel hybrid filter architecture is proposed that incorporates an adaptive multistage nonlinear filter (AMNF) and a tree-structured wavelet transform (TSWT) specifically designed for image enhancement in medical imaging using different sensors. The AMNF is used for noise suppression and image enhancement. The TSWT is used for multiresolution decomposition and reconstruction of the medical images where selective reconstruction of subimages is used to perform further enhancement of specific clinical features. The AMNF-TSWT filter produced enhanced images for different modalities namely, digital mammography, chest, skin cancer and retinal images, that provided improved visualization of specific clinical features compared to the raw digital images. The AMNF-TSWT filter should prove to be useful for the use of neural networks for feature classification using different sensors and imaging protocols.>

A new class of nonlinear filters with more robust characteristics for noise suppression and detail preservation is proposed for processing digital mammographic images. The new algorithm consists of two major filtering blocks: (a) a multistage tree-structured filter for image enhancement that uses central weighted median filters as basic sub-filtering blocks and (b) a dispersion edge detector. The design of the algorithm also included the use of linear and curved windows to determine whether variable shape windowing could improve detail preservation. First, the noise-suppressing properties of the tree-structured filter were compared to single filters, namely the median and the central weighted median with conventional square and variable shape adaptive windows; simulated images were used for this purpose. Second, the edge detection properties of the tree-structured filter cascaded with the dispersion edge detector were compared to the performance of the dispersion edge detector alone, the Sobel operator, and the single median filter cascaded with the dispersion edge detector. Selected mammographic images with representative biopsy-proven malignancies were processed with all methods and the results were visually evaluated by an expert mammographer. In all applications, the proposed filter suggested better detail preservation, noise suppression, and edge detection than all other approaches and it may prove to be a useful tool for computer-assisted diagnosis in digital mammography.

An order statistic and neural network hybrid filter (OSNNH) is proposed for the restoration of gamma camera images using the measured modulation transfer function. Planar images of beta-emitting radionuclides are used to evaluate the filter because they exhibit higher degradation than images of single photon emitters due to increased photon scattering and collimator septal penetration. The filter performance is quantitatively evaluated and compared to that of the Wiener filter by investigating the relationship between the externally measured counts from sources of phosphorous-32 ((32)P) at various depths in water. An effective linear attenuation coefficient for (32)P is determined to be equal to 0.13 cm(-1) and 0.14 cm(-1) for the OSNNH and the Wiener filters, respectively. Evaluation of phantom and patient filtered images demonstrates that the OSNNH filter avoids ring effects caused by the ill-conditioned blur matrix and noise overriding caused by matrix inversion, typical of other restoration filters such as the Wiener.

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms, and a supervised computational neural network. Initial clinical results are presented on normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. For a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed, with fuzz-c-means approaches being slightly preferred over feedforward cascade correlation results. Various facets of both approaches, such as supervised versus unsupervised learning, time complexity, and utility for the diagnostic process, are compared.

The suitability of artificial neural networks (ANNs) for the classification of multispectral magnetic resonance images (MSMRI) is explored. MSMRI feature space distributions of various tissues and phantoms were examined to determine if the data is more suitable for ANN classification, as opposed to classical Bayesian approaches for intensity-based classification. Additionally, MSMRI normalization methods were investigated to determine suitability for improving feature space distributions independent of classification methods.>