Computerized System for Quantitative Assessment of Atherosclerotic Plaques in the Femoral and Iliac Arteries Visualized by Multislice Computed Tomography.

OBJECTIVE: The investigation is aimed at the development of a semiautomatic method of examining the femoral and iliac arteries, and quantifying atherosclerotic plaques visible in the multislice computed tomography images. METHODS: We have utilized the advanced morphology and segmentation methods for processing of a series of the images. In particular, a novel sorted pixel intensity approach to segment the artery into the lumen/plaque regions has been used, and effectively combined with the Gaussian mixture modeling to increase the accuracy of the segmentation. RESULTS: Our numerical results are compared with those obtained manually by two experts. Statistics relevant to the progression of atherosclerosis have also been suggested. Results of the semiautomatic tracking of the femoral and iliac arteries and of the quantitative evaluation of atherosclerotic alterations therein have been shown to correspond well with the expert's results. CONCLUSION: The developed system is likely to be valuable tool for supporting the quantitative evaluation of atherosclerotic changes in arteries. SIGNIFICANCE: In its present form the system can be used for planning surgical treatment and/or predicting the course of the atherosclerotic alterations.

Computerized system for recognition of autism on the basis of gene expression microarray data.

The aim of this paper is to provide a means to recognize a case of autism using gene expression microarrays. The crucial task is to discover the most important genes which are strictly associated with autism. The paper presents an application of different methods of gene selection, to select the most representative input attributes for an ensemble of classifiers. The set of classifiers is responsible for distinguishing autism data from the reference class. Simultaneous application of a few gene selection methods enables analysis of the ill-conditioned gene expression matrix from different points of view. The results of selection combined with a genetic algorithm and SVM classifier have shown increased accuracy of autism recognition. Early recognition of autism is extremely important for treatment of children and increases the probability of their recovery and return to normal social communication. The results of this research can find practical application in early recognition of autism on the basis of gene expression microarray analysis.

Computer approach to recognition of Fuhrman grade of cells in clear-cell renal cell carcinoma.

OBJECTIVE: To present a computerized system for recognition of Fuhrman grade of cells in clear-cell renal cell carcinoma on the basis of microscopic images of the neoplasm cells in application of hematoxylin and eosin staining. STUDY DESIGN: The applied methods use combined gradient and mathematical morphology to obtain nuclei and classifiers in the form of support vector machine to estimate their Fuhrman grade. The starting point is a microscopic kidney image, which is subject to the advanced methods of preprocessing, leading finally to estimation of Fuhrman grade of cells and the whole analyzed image. RESULTS: The results of the numerical experiments have shown that the proposed nuclei descriptors based on different principles of generation are well connected with the Fuhrman grade. These descriptors have been used as the diagnostic features forming the inputs to the classifier, which performs the final recognition of the cells. The average discrepancy rate between the score of our system and the human expert results, estimated on the basis of over 3,000 nuclei, is below 10%. CONCLUSION: The obtained results have shown that the system is able to recognize 4 Fuhrman grades of the cells with high statistical accuracy and agreement with different expert scores. This result gives a good perspective to apply the system for supporting and accelerating the research of kidney cancer.

Nucleolus detection in the Fuhrman grading system for application in CCRC.

The paper presents a method for nucleolus detection in images of nuclei in clear-cell renal carcinoma (CCRC). The method is based on the similarity of the nuclei image and the two-dimensional paraboloidal window function. The results of numerical experiments performed on almost 2600 images of CCRC nuclei have confirmed the good accuracy of the method. The developed algorithm will be used to accelerate further research in computer-assisted diagnosis of CCRC.

Neural system for heartbeats recognition using genetically integrated ensemble of classifiers.

This paper presents the application of genetic algorithm for the integration of neural classifiers combined in the ensemble for the accurate recognition of heartbeat types on the basis of ECG registration. The idea presented in this paper is that using many classifiers arranged in the form of ensemble leads to the increased accuracy of the recognition. In such ensemble the important problem is the integration of all classifiers into one effective classification system. This paper proposes the use of genetic algorithm. It was shown that application of the genetic algorithm is very efficient and allows to reduce significantly the total error of heartbeat recognition. This was confirmed by the numerical experiments performed on the MIT BIH Arrhythmia Database.

Computer system for cell counting in selected brain tumors at Ki-67 immunohistochemical staining.

OBJECTIVE: To present a computerized system for cell counting in histopathologic slides of meningioma and oligodendroglioma stained immunohistochemically against Ki-67 antigen and discuss the variability of tumor cell numbers in the field of view of analyzed neoplasms to standardize tumor cellularity. STUDY DESIGN: A computer program using an algorithm based on mathematical morphology was developed to perform quantitative evaluation of slides. That solution was combined with the Support Vector Machine used for classification of cell immunoreactivity. RESULTS: The mean number of cells in the analyzed field of view from patients with meningioma was 623. Of these, 95% were in the 386-781 cells range. In oligodendrogliomas the mean was 474 cells and all results were in the 204-736 range. The mean relative discrepancy between results of our system and human expert score was 8%. CONCLUSION: The proposed system appeared to be an efficient tool for supporting histopathologic diagnosis. The applied sequential thresholding simulated well the human process of cell recognition. Cellularity of the analyzed tumors did not show stability within the specimens from different patients. The results were also highly variable in different fields of view obtained from the same patient.

Comparative analysis of methods for accurate recognition of cells through nuclei staining of Ki-67 in neuroblastoma and estrogen/progesterone status staining in breast cancer.

OBJECTIVE: To compare 2 automatic systems for the recognition and counting of 2 different families of cells through nuclei staining: Ki-67 in neuroblastoma and estrogen/progesterone (ER/PR) status staining in breast cancer. STUDY DESIGN: Morphology-based segmentation strategies and the Support Vector Machine approach have been used for the accurate extraction and recognition of the cells. To achieve the highest possible accuracy, 2 specialized systems specially suited for Ki-67 and ER/PR staining have been developed. RESULTS: The testing set of histologic slides of Ki-67 and ER/PR staining has been assessed by our system and the results compared to the score of a human expert. The results are in good agreement. The average differences are within the acceptable limits of 10%. The main advantage of the system is its absolute repeatability of scores. CONCLUSION: The proposed computer-assisted automatic system of cell extraction and recognition through nuclei staining has confirmed sufficient accuracy for the tested images and may provide a useful tool for cell recognition and counting on the basis of histologic slides with Ki-67 and ER/PR staining.

New automated image analysis method for the assessment of Ki-67 labeling index in meningiomas.

Many studies have emphasised the importance of Ki-67 labeling index (LI) as the proliferation marker in meningiomas. Several authors confirmed, that Ki-67 LI has prognostic significance and correlates with likelihood of tumour recurrences. These observations were widely accepted by pathologists, but up till now no standard method for Ki-67 LI assessment was developed and introduced for the diagnostic pathology. In this paper we present a new computerised system for automated Ki-67 LI estimation in meningiomas as an aid for histological grading of meningiomas and potential standard method of Ki-67 LI assessment. We also discuss the concordance of Ki-67 LI results obtained by presented computerized system and expert pathologist, as well as possible pitfalls and mistakes in automated counting of immunopositive or negative cells. For the quantitative evaluation of digital images of meningiomas the designed software uses an algorithm based on mathematical description of cell morphology. This solution acts together with the Support Vector Machine (SVM) used in the classification mode for the recognition of immunoreactivity of cells. The applied sequential thresholding simulated well the human process of cell recognition. The same digital images of randomly selected tumour areas were parallelly analysed by computer and blindly by two expert pathologists. Ki-67 labeling indices were estimated and the results compared. The mean relative discrepancy between the levels of Ki-67 LI by our system and by the human expert did not exceed 14% in all investigated cases. These preliminary results suggest that the designed software could be an useful tool supporting the diagnostic digital pathology. However, more extended studies are needed for approval of this suggestion.

Image processing for accurate cell recognition and count on histologic slides.

OBJECTIVE: To design an automatic system for recognition and count of two different cell families on histologic slides. STUDY DESIGN: The segmentation strategy uses color information on the image. The morphologic operations and Support Vector Machine approaches are used for each color to obtain precise segmentation of the image into separate cells for recognition. RESULTS: A large set of histologic slides of bone marrow was assessed byour system and the results compared to the score of a human expert. The results are in good agreement. The difference is within acceptable limits (below 10%). CONCLUSION: The automatic system of cell recognition and extraction is accurate and provides a useful tool for cell recognition and count on histologic slides.

Support vector machine-based expert system for reliable heartbeat recognition.

This paper presents a new solution to the expert system for reliable heartbeat recognition. The recognition system uses the support vector machine (SVM) working in the classification mode. Two different preprocessing methods for generation of features are applied. One method involves the higher order statistics (HOS) while the second the Hermite characterization of QRS complex of the registered electrocardiogram (ECG) waveform. Combining the SVM network with these preprocessing methods yields two neural classifiers, which have been combined into one final expert system. The combination of classifiers utilizes the least mean square method to optimize the weights of the weighted voting integrating scheme. The results of the performed numerical experiments for the recognition of 13 heart rhythm types on the basis of ECG waveforms confirmed the reliability and advantage of the proposed approach.

Higher order statistics and neural network for tremor recognition.

This paper is concerned with the tremor characterization for the purpose of recognition. Three different types of tremor are considered in this paper: the parkinsonian, essential, and physiological. It has been proven that standard second-order statistical description of tremor is not sufficient to distinguish between these three types. Higher order polyspectra based on third- and fourth-order cumulants have been proposed as the additional characterization of the tremor time series. The set of 30 quantities based on the polyspectra has been proposed and investigated as the features for the recognition of tremor. The neural network of the multilayer perceptron structure has been used as a classifier. The results of numerical experiments have proven high efficiency of the proposed approach. The average error of recognition of three types of tremor did not exceed 3%.

Fast Second Order Learning Algorithm for Feedforward Multilayer Neural Networks and its Applications.

The paper presents the efficient training program of multilayer feedforward neural networks. It is based on the best second order optimization algorithms including variable metric and conjugate gradient as well as application of directional minimization in each step. Its efficiency is proved on the standard tests, including parity, dichotomy, logistic and two-spiral problems. The application of the algorithm to the solution of higher dimensionality problems like deconvolution, separation of sources and identification of nonlinear dynamic plant are also given and discussed. It is shown that the appropriately trained neural network can be used for the nonconventional solution of these standard signal processing tasks with satisfactory accuracy. The results of numerical experiments are included and discussed in the paper. Copyright 1996 Elsevier Science Ltd.