G. Valli

Genetic design of optimum linear and nonlinear QRS detectors

Describes an approach to the design of optimum QRS detectors. The authors report on detectors including a linear or nonlinear polynomial filter, which enhances and rectifies the QRS complex, and a simple, adaptive maxima detector. The parameters of the filter and the detector, and the samples to be processed are selected by a genetic algorithm which minimizes the detection errors made on a set of reference ECG signals. Three different architectures and the experimental results achieved on the MIT-BIH Arrhythmia Database are described.<<ETX>>

An algorithm for real-time vessel enhancement and detection

In this paper we present an algorithm for the real-time enhancement and detection of blood vessels in medical images. The algorithm is based on a set of linear filters sensitive to vessels of different orientation and thickness. Such filters are obtained as linear combinations of properly shifted Gaussian kernels. The output of multiple oriented vessel-enhancing filters can be integrated to obtain images in which vessels are highly enhanced independently of their direction and thickness. To avoid spurious responses in the presence of step edges or to enhance the skeletons of vessels, the output of directional filters can be validated before integration. Skeleton detection and vessel segmentation can be performed via thresholding with hysteresis. Experimental results on synthetic images and real coronary arteriograms are reported.

Neural networks for computer-aided diagnosis: detection of lung nodules in chest radiograms

The paper describes a neural-network-based system for the computer aided detection of lung nodules in chest radiograms. Our approach is based on multiscale processing and artificial neural networks (ANNs). The problem of nodule detection is faced by using a two-stage architecture including: 1) an attention focusing subsystem that processes whole radiographs to locate possible nodular regions ensuring high sensitivity; 2) a validation subsystem that processes regions of interest to evaluate the likelihood of the presence of a nodule, so as to reduce false alarms and increase detection specificity. Biologically inspired filters (both LoG and Gabor kernels) are used to enhance salient image features. ANNs of the feedforward type are employed, which allow an efficient use of a priori knowledge about the shape of nodules, and the background structure. The images from the public JSRT database, including 247 radiograms, were used to build and test the system. We performed a further test by using a second private database with 65 radiograms collected and annotated at the Radiology Department of the University of Florence. Both data sets include nodule and nonnodule radiographs. The use of a public data set along with independent testing with a different image set makes the comparison with other systems easier and allows a deeper understanding of system behavior. Experimental results are described by ROC/FROC analysis. For the JSRT database, we observed that by varying sensitivity from 60 to 75% the number of false alarms per image lies in the range 4-10, while accuracy is in the range 95.7-98.0%. When the second data set was used comparable results were obtained. The observed system performances support the undertaking of system validation in clinical settings.

A neural network expert system for diagnosing and treating hypertension

Hypernet (Hypertension Neural Expert Therapist), a neural network expert system for diagnosing and treating hypertension, is described. After a brief look at artificial neural networks, the authors describe the structure of the three modules that make up Hypernet, starting with the specific problem each network is intended to solve and explaining how the network is expected to operate. The tools developed for implementing the system are a compiler for a simple descriptive language that enables the authors to define, train, and test networks; a graphic editor that translates the network drawn by the user into the proper statements; and a set of programs for interactively generating the examples. The data used as examples, the learning phase, and the results of tests for evaluating the performance of each network are described. and conclusions about overall system results are presented.<<ETX>>

3-D Segmentation Algorithm of Small Lung Nodules in Spiral CT Images

Computed tomography (CT) is the most sensitive imaging technique for detecting lung nodules, and is now being evaluated as a screening tool for lung cancer in several large samples studies all over the world. In this report, we describe a semiautomatic method for 3-D segmentation of lung nodules in CT images for subsequent volume assessment. The distinguishing features of our algorithm are the following. 1) The user interaction process. It allows the introduction of the knowledge of the expert in a simple and reproducible manner. 2) The adoption of the geodesic distance in a multithreshold image representation. It allows the definition of a fusion--segregation process based on both gray-level similarity and objects shape. The algorithm was validated on low-dose CT scans of small nodule phantoms (mean diameter 5.3-11 mm) and in vivo lung nodules (mean diameter 5--9.8 mm) detected in the Italung-CT screening program for lung cancer. A further test on small lung nodules of Lung Image Database Consortium (LIDC) first data set was also performed. We observed a RMS error less than 6.6% in phantoms, and the correct outlining of the nodule contour was obtained in 82/95 lung nodules of Italung-CT and in 10/12 lung nodules of LIDC first data set. The achieved results support the use of the proposed algorithm for volume measurements of lung nodules examined with low-dose CT scanning technique.

An artificial vision system for X-ray images of human coronary trees

The coronary tree expert (CORTEX) analyzer, which is a vision system for the description of the bidimensional shape and position of coronary vessels using standard nonsubtracted radiographic images, is described. A bottom-up approach was used to deal with the typical characteristics of medical images, such as structural and nonstructural noise and complexity and variability of biological shapes. On these grounds, grouping criteria were utilized to produce intermediate image representations with an increasing complexity in a hierarchical manner (from edge points to curves, segments, bars, and finally to vessels and their mutual relations). In this way, uncertain, inconsistent, and deficient information was efficiently processed. The evaluation of CORTEX segmentation is also performed according to a signal-detection-theory-like approach. >

Tissue characterization from X-ray images

The study of the fine-scale structure of biological tissues is crucial for diagnosing a wide number of different diseases. In X-ray images, fine structures usually induce a correlation among image gray levels and are commonly perceived as textures. In this paper, we report on a Computer Vision approach to the characterization of biological tissues as imaged by standard X-ray techniques. In particular, using features derived from co-occurrence matrices, we have assessed spatial gray-level dependence of bone tissue and lung parenchyma images. A hybrid neural network was adopted to distinguish pathological tissues from normal ones and to classify different pathologies.

Neural network segmentation of magnetic resonance spin echo images of the brain

This paper describes a neural network system to segment magnetic resonance (MR) spin echo images of the brain. Our approach relies on the analysis of MR signal decay and on anatomical knowledge; the system processes two early echoes of a standard multislice sequence. Three main subsystems can be distinguished. The first implements a model of MR signal decay; it synthesizes a four-echo multiecho sequence, in order to add images characterized by long echo-times to the input sequence. The second subsystem exploits a priori anatomical knowledge by producing an image, in which pixels belonging to brain parenchyma are highlighted. Such anatomical information allows the following submodule to distinguish biologically different tissues with similar water content, and hence similar appearance, which might produce misclassifications. The grey levels of the reconstructed sequence and the output of the second module are processed by the third subsystem, which performs the segmentation of the sequence. Each pixel is assigned to one of five different tissue classes that can be revealed with brain MR spin echo imaging. With a suitable encoding, a five-level segmented image can then be produced. The system is based on feed-forward networks trained with the back-propagation algorithm; experiments to assess its performance have been carried out on both simulated and clinical images.

Three-dimensional knowledge driven reconstruction of coronary trees

A knowledge-driven approach to the three-dimensional reconstruction of coronary artery trees by means of two X-ray projections is proposed. The spatial reconstruction of the tree skeleton is discussed. A binary tree model of the arterial structure and its projections is employed. Consequently, the reconstruction of the three-dimensional tree skeleton is achieved by (a) matching the skeletons of corresponding pairs of vascular segments in the two views and (b) back-projecting the coupled skeleton projections. From a geometrical point of view, the matching problem is, in general, ill-conditioned. For this reason, additional information sources were used. Thus, the matching phase is accomplished by using both the imaging geometry information, as well as anatomical and topological knowledge, about the coronary arteries coded in a rule base. As far as the back-projection phase is concerned, an algorithm was developed based on: (1) the imaging geometry, (2) the bounding of the back-projection error and (3) a contiguity criterion.

A neural network architecture for understanding discrete three-dimensional scenes in medical imaging

Magnetic resonance and computed tomography produce sets of tomograms which are termed discrete 3D scenes. Usually, discrete 3D scenes are analyzed in two dimensions by observing each tomogram on a screen so that the three-dimensional information contained in the scene can be recovered only partially and qualitatively. The three-dimensional reconstruction of the shape of biological structures from discrete 3D scenes would allow a complete and quantitative recovery of the available information, but this task has proved hard for conventional processing techniques. In this paper we present a system architecture based on neural networks for the fully automated segmentation and recognition of structures of interest in discrete 3D scenes. The system includes a retina and two main processing modules, an Attention-Focuser System and a Region-Finder System, which have been implemented by using feed-forward nets trained with the back-propagation algorithm. This architecture has been tested on computer-simulated structures and has been applied to the reconstruction of the spinal cord and the brain from sets of tomograms.