Andrzej Obuchowicz

Computer-aided diagnosis of breast cancer based on fine needle biopsy microscopic images

Prompt and widely available diagnostics of breast cancer is crucial for the prognosis of patients. One of the diagnostic methods is the analysis of cytological material from the breast. This examination requires extensive knowledge and experience of the cytologist. Computer-aided diagnosis can speed up the diagnostic process and allow for large-scale screening. One of the largest challenges in the automatic analysis of cytological images is the segmentation of nuclei. In this study, four different clustering algorithms are tested and compared in the task of fast nuclei segmentation. K-means, fuzzy C-means, competitive learning neural networks and Gaussian mixture models were incorporated for clustering in the color space along with adaptive thresholding in grayscale. These methods were applied in a medical decision support system for breast cancer diagnosis, where the cases were classified as either benign or malignant. In the segmented nuclei, 42 morphological, topological and texture features were extracted. Then, these features were used in a classification procedure with three different classifiers. The system was tested for classification accuracy by means of microscopic images of fine needle breast biopsies. In cooperation with the Regional Hospital in Zielona Góra, 500 real case medical images from 50 patients were collected. The acquired classification accuracy was approximately 96-100%, which is very promising and shows that the presented method ensures accurate and objective data acquisition that could be used to facilitate breast cancer diagnosis.

Segmentation of Breast Cancer Fine Needle Biopsy Cytological Images

Segmentation of Breast Cancer Fine Needle Biopsy Cytological Images This paper describes three cytological image segmentation methods. The analysis includes the watershed algorithm, active contouring and a cellular automata GrowCut method. One can also find here a description of image pre-processing, Hough transform based pre-segmentation and an automatic nuclei localization mechanism used in our approach. Preliminary experimental results collected on a benchmark database present the quality of the methods in the analyzed issue. The discussion of common errors and possible future problems summarizes the work and points out regions that need further research.

Genetic programming based approaches to identification and fault diagnosis of non-linear dynamic systems

System identification is one of the most important research directions. It is a diverse field which can be employed in many different areas. One of them is the model-based fault diagnosis. Thus, the problems of system identification and fault diagnosis are closely related. Unfortunately, in both cases, the research is strongly oriented towards linear systems, while the problem of identification and fault diagnosis of non-linear dynamic systems still remains open. There are, of course, many more or less sophisticated approaches to this problem, although they are not as reliable and universal as those related to linear systems, and the choice of the method to be used depends on the application. The purpose of this paper is to provide a new system identification framework based on a genetic programming technique. Moreover, a fault diagnosis scheme for non-linear systems is proposed. In particular, a new fault detection observer is presented, and the Lyapunov approach is used to show that the proposed observer is convergent under certain conditions. It is also shown how to use the genetic programming technique to increase the convergence rate of the observer. The final part of this paper contains numerical examples concerning identification of chosen parts of the evaporation station at the Lublin Sugar Factory S.A., as well as state estimation and fault diagnosis of an induction motor.

Cytomorphometry of Fine Needle Biopsy Material from the Breast Cancer

A computer system has been developed for evaluating the morphometrical feature extraction. The features are derived directly from a digital scan of breast fine needle biopsy slides. First the background elimination by thresholding hue component is applied, then the actual segmentation is done with region growing technique. The quality of feature space is measured with classifier based on nonparametric density estimation. The automatic system of malignancy classification was applied on a set of medical images with promising results. The comparison of human accuracy in the cytological diagnosis of breast cancer with the accuracy of digital image analysis combined with computer-based classification is presented.

Computational Intelligence Techniques in Image Segmentation for Cytopathology

A variety of computational intelligence approaches to nuclei segmentation in the microscope images of fine needle biopsy material is presented in this chapter. The segmentation is one of the most important steps of the automatic medical diagnosis based on the analysis of the microscopic images, and is crucial to making a correct diagnostic decision. Due to complex nature of biological images, standard segmentation methods are not effective enough. In this chapter we present and discuss some modified versions of watershed algorithm, active contours, cellular automata, GrowCut technique, as well as new approaches like fuzzy sets of I and II type, and the sonar-like method.

Automatic Breast Cancer Diagnosis Based on K-Means Clustering and Adaptive Thresholding Hybrid Segmentation

The paper presents k-means based hybrid segmentation method for breast cancer diagnosis problem. It is part of the computer system to support diagnosis based on microscope images of the fine needle biopsy. The system assumes distinguishing malignant from benign cases. Described method is an alternative to the previously presented algorithms based on fuzzy c-means clustering and competitive neural networks. However, it uses similar idea of combining clustering in RGB space with adaptive thresholding. At first, thresholding reveals objects on background. Then image is clustered with k-means algorithm to distinguish nuclei from red blood cells and other objects. Correct segmentation is crucial to obtain good quality features measurements and consequently successful diagnosis. The system of malignancy classification was tested on a set of real case medical images with promising results.

Network of dynamic neurons in fault detection systems

The neural-residual generator (NRG) construction for a dynamic system is the goal of this paper. The neural networks modeling the dynamic system are constructed with dynamics models of artificial neurons, which contain inner feedbacks. Such a model consists of an adder module, a linear dynamic system and a nonlinear activation function. Two optimization problems are solved with NRG construction: searching for an optimal network architecture and dynamic neuron model (DNM) network training. The boiler unit of a power plant is chosen as a modeled dynamic system.The cascade network of dynamic neurons (CNDN) as a neural-residual generator for fault detection in a dynamic systems is considered. The neural network is composed of dynamic neurons, which contain inner feedbacks. These neurons consists of an adder module, a linear dynamic system (IIR filter), and a non-linear activation function. The cascade-correlation algorithm is used for network architecture and parameter allocation. As a illustrative example of the diagnosed dynamic system, the two-tank system is chosen. The proposed approach is useful in neural modelling of dynamic system for FDI (Fault Detection and Isolation).

Fuzzy Clustering and Adaptive Thresholding Based Segmentation Method for Breast Cancer Diagnosis

The paper provides a preview of some work in progress on the computer system to support breast cancer diagnosis. The approach is based on microscope images of the FNB (Fine Needle Biopsy) and assumes distinguishing malignant from benign cases. Research is focused on two different problems. The first is segmentation and extraction of morphometric parameters of nuclei present on cytological images. The second concentrates on breast cancer classification using selected features. Studies in both areas are conducted in parallel. This work is mainly devoted to the problem of image segmentation in order to obtain good quality features measurements. Correct segmentation is crucial for successful diagnosis. The paper describes hybrid segmentation algorithm based on fuzzy clustering and adaptive thresholding. The automatic system of malignancy classification was applied on a set of medical images with promising results.

Hough Transform, (1+1) Search Strategy and Watershed Algorithm in Segmentation of Cytological Images

This paper describes an early stage of cytological image recognition and presents a proposition of a hybrid segmentation method. The analysis includes the Hough transform in conjunction with the watershed algorithm. One can also find here a short description of image pre-processing and an automatic nuclei localization mechanism used in our approach. Preliminary experimental results collected on a handprepared benchmark database are also presented with discussion of common errors and possible future problems.

Multidimensional mutations in evolutionary algorithms based on real-valued representation

This work is focused on the fact that the most probable distance of mutated points in multi-dimensional Gaussian and Cauchy mutations is not in a close neighborhood of the origin, but at a certain distance from it. In the case of the Gaussian mutation, this distance is proportional to the norm of the standard deviation vector and increases with the landscape dimension. This may cause a decrease in the sensitivity of the evolutionary algorithm to narrow peaks when the landscape dimension increases, but, simultaneously, it strengthens the exploration property of the algorithm. Moreover, the influence of the reference frame orientation on the effectiveness of the non-spherical multi-dimensional Cauchy mutation is analyzed using simulation experiments. Four multi-dimensional mutations (Gaussian, modified Gaussian, non-spherical and spherical Cauchy mutations) are applied to two classes of evolutionary algorithms based on real-valued representation, i.e. Galars evolutionary search with soft selection and evolutionary programming. A comparative analysis is provided for convergence to the local optimum, sensitivity to narrow peaks, saddle crossing and symmetry problems.