Leszek Nowak

Computational Intelligence and Image Processing Methods for Applications in Skin Cancer Diagnosis

Digital photography provides new powerful diagnostic tools in dermatology. Dermoscopy is a special photography technique which enables taking photos of skin lesions in chosen lighting conditions. Digital photography allows for seeing details of the skin changes under various enlargements and coloring. Computer-assisted techniques and image processing methods can be further used for image enhancement and analysis and for feature extraction and pattern recognition in the selected images. Special techniques used in skin-image processing are discussed in detail. Feature extraction methods and automated classification techniques based on statistical learning and model ensembling techniques provide very powerful tools which can assist the doctors in taking decisions. Performance of classifiers will be discussed in specific case of melanoma cancer diagnosis. The techniques have been tested on a large data set of images.

Semantic analysis of skin lesions using radial basis function neural networks

Artificial Neural Networks have been successfully applied to abroad spectrum of complex analysis problems. Computational intelligence is finding more and more applications in computer aided diagnostics, helping doctors to process large quantities of various medical data. In dermatology it is extremely difficult to perform automatic diagnostic differentiation of malignant melanoma based only on dermatoscopic images. Applying artificial intelligence algorithms to explore and search large database of dermatoscopic images allow doctors to semantically filter out image with specified characteristics. This paper presents an approach for characteristic objects classification found in image database of pigment skin lesions, based on radial basis function kernel for artificial neural networks.

Stafflines pattern detection using the swarm intelligence algorithm

This paper demonstrates the application of the Swarm Intelligence (SI) algorithm to recognize the specific patterns that are present in the digital images of handwritten music scores. The application introduced in this paper involves the detection of stafflines using particle swarm. The introduced solution described in this paper is a new approach to the problem, and illustrates how optimization algorithm can be modified and successfully applied in different subjects such as pattern recognition. The developed algorithm can be used as a first stage in Optical Music Recognition (OMR) that is followed by the staffline removal phase. It is worth pointing out, that contrary to most state-of-the-art algorithms, the proposed method does not require a binarization step in the preprocessing stage.

A decision support system based on the semantic analysis of melanoma images using multi-elitist PSO and SVM

The use of machine learning tools for the purpose of medical diagnosis is gradually increasing. This is mainly because the effectiveness of classification has improved a great deal to help medical experts in diagnosing diseases. Such a disease is melanoma malignum, which is a very common type of cancer among humans. In this paper, we use modified version of classical Particle Swarm Optimization (PSO) algorithm, known as the Multi-Elitist PSO (MEPSO) method and support vector machines (SVM) to classify melanoma malignum images previously preprocessed by image segmentation and image feature extraction. The classification accuracy obtained is ca. 96%. The proposed classification method can be developed to an automatic classification process, the performance of which is similar to human perception.

Pigmented network structure detection using semi-smart adaptive filters

This paper demonstrates a method for detecting pigment based dermatoscopic structure called pigment network. This structure is used in dermatoscopy as one of the criteria in clinical evaluation of pigmented skin lesions and can indicate if a lesion is of malignant nature. For detection process we have developed an adaptive filter, inspired by Swarm Intelligence (SI) optimization algorithms. The introduced filtering method is applied in a non-linear manner, to processed dermatoscopic image of a skin lesion. The non-linear approach derives from SI algorithms, and allows selective image filtering. In the beginning of filtration process, the filters (agents) are randomly applied to sections of the image, where each of them adapts its output based on the neighborhood surrounding it. Agents share its information with other agents that are located in immediate vicinity. This is a new approach to the problem of dermatoscopic structure detection, and it is highly flexible, as it can be applied to images without the need of previous pre-processing stage. This feature is highly desirable, mainly due to the fact that in most cases of computer aided diagnostic, input images need to be pre-processed (e.g.: brightness normalization, histogram equation, contrast enhancement, color normalization) and results of this can introduce unwanted artifacts, so this step need to be verified by human. Results of applying the introduced method can be used as one of the differential structures criteria for calculating the Total Dermatoscopy Score (TDS) of the ABCD rule.

3D integrated circuits layout optimization game

This paper is devoted to the original approach to block-level 3D IC layout design. The circuit components are modeled as autonomous mobile agents that explore their virtual world in order to find a globally near-optimal layout solution. The search space is defined by geometry features, wire connections, goals and constraints of the design task. The approach is illustrated by the example application to one of the MCNC benchmark circuits and implemented using Godot.

Computational Classification of Melanocytic Skin Lesions

The increasing incidence of melanoma skin cancer is alarming. The lack of objective diagnostic procedures encourages development of computer aided approaches. Presented research uses three different machine learning methods, namely the Naive Bayes classifier, the Random Forest and the K* instance-based classifier together with two meta-learning algorithms: the Bootstrap Aggregating (Bagging) and the Vote Ensemble Classifier. Diagnostic accuracy of the selected methods, such as sensitivity and specificity and the area under the ROC curve, are discussed. The obtained results confirm that clinical history context and dermoscopic structures present in the images are important and can give accurate diagnostic classification of the lesions.

Applications of Neural Networks in Semantic Analysis of Skin Cancer Images

Computational intelligence is finding more and more applications in computer aided diagnostics, helping doctors to process large quantities of various medical data [Buronni et al. 2004]. In dermatology it is extremely difficult to perform automatic diagnostic differentiation of malignant melanoma based only on dermatoscopic images. Applying artificial intelligence algorithms to explore and search large database of dermatoscopic images allow doctors to semantically filter out image with specified characteristics. This paper presents an semantic approach for characteristic objects classification found in image database of pigment skin lesions, based on radial basis function kernel for artificial neural networks. Presented approach is divided into few parts: JSEG image segmentation [Deng et al. 2001], feature extraction and classification. Prepared features vector consist of color models parts. For classification Artificial Neural Networks and Support Vector Machines are used and their performance is evaluated and compared. Success rates in both cases are greater than 90%.

Predictive analysis of blood gasometry parameters related to the infants respiration insufficiency

The paper presents application of artificial immune system in time series prediction of the medical data. Prediction mechanism used in the work is basing on the paradigm stating that in the immune system during the response there exist not only antigene – antibody connections but also antigene – antigene connections, which role is control of antibodies activity. Moreover in the work learning mechanism of the artificial immune network, and results of carried out tests are presented.