Wyniki wyszukiwania - BazTech

1

Electroencephalography (EEG) signal processing for epilepsy and autism spectrum disorder diagnosis

Ibrahim S., Djemal R., Alsuwailem A.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 1

16--26

EN

Quantification of abnormality in brain signals may reveal brain conditions and pathologies. In this study, we investigate different electroencephalography (EEG) feature extraction and classification techniques to assist in the diagnosis of both epilepsy and autism spectrum disorder (ASD). First, the EEG signal is pre-processed to remove major artifacts before being decomposed into several EEG sub-bands using a discrete-wavelet-transform (DWT). Two nonlinear methods were studied, namely, Shannon entropy and largest Lyapunov exponent, which measure complexity and chaoticity in the EEG recording, in addition to the two conventional methods (namely, standard deviation and band power). We also study the use of a cross-correlation approach to measure synchronization between EEG channels, which may reveal abnormality in communication between brain regions. The extracted features are then classified using several classification methods. Different EEG datasets are used to verify the proposed design exploration techniques: the University of Bonn dataset, the MIT dataset, the King Abdulaziz University dataset, and our own EEG recordings (46 subjects). The combination of DWT, Shannon entropy, and k-nearest neighbor (KNN) techniques produces the most promising classification result, with an overall accuracy of up to 94.6% for the three-class (multi-channel) classification problem. The proposed method obtained better classification accuracy compared to the existing methods and tested using larger and more comprehensive EEG dataset. The proposed method could potentially be used to assist epilepsy and ASD diagnosis therefore improving the speed and the accuracy.

2

Nuclei segmentation for computer-aided diagnosis of breast cancer

Kowal M., Filipczuk P.

International Journal of Applied Mathematics and Computer Science

|

2014

|

Vol. 24, no. 1

19--31

EN

Breast cancer is the most common cancer among women. The effectiveness of treatment depends on early detection of the disease. Computer-aided diagnosis plays an increasingly important role in this field. Particularly, digital pathology has recently become of interest to a growing number of scientists. This work reports on advances in computer-aided breast cancer diagnosis based on the analysis of cytological images of fine needle biopsies. The task at hand is to classify those as either benign or malignant. We propose a robust segmentation procedure giving satisfactory nuclei separation even when they are densely clustered in the image. Firstly, we determine centers of the nuclei using conditional erosion. The erosion is performed on a binary mask obtained with the use of adaptive thresholding in grayscale and clustering in a color space. Then, we use the multi-label fast marching algorithm initialized with the centers to obtain the final segmentation. A set of 84 features extracted from the nuclei is used in the classification by three different classifiers. The approach was tested on 450 microscopic images of fine needle biopsies obtained from patients of the Regional Hospital in Zielona Góra, Poland. The classification accuracy presented in this paper reaches 100%, which shows that a medical decision support system based on our method would provide accurate diagnostic information.

3

GLCM and GLRLM based texture features for computer-aided breast cancer diagnosis

Filipczuk P., Fevens T., Krzyżak A., Obuchowicz A.

Journal of Medical Informatics & Technologies

|

2012

|

Vol. 19

109--115

EN

This paper presents 15 texture features based on GLCM (Gray-Level Co-occurrence Matrix) and GLRLM (Gray-Level Run-Length Matrix) to be used in an automatic computer system for breast cancer diagnosis. The task of the system is to distinguish benign from malignant tumors based on analysis of fine needle biopsy microscopic images. The features were tested whether they provide important diagnostic information. For this purpose the authors used a set of 550 real case medical images obtained from 50 patients of the Regional Hospital in Zielona Góra. The nuclei were isolated from other objects in the images using a hybrid segmentation method based on adaptive thresholding and kmeans clustering. Described texture features were then extracted and used in the classification procedure. Classification was performed using KNN classifier. Obtained results reaching 90% show that presented features are important and may significantly improve computer-aided breast cancer detection based on FNB images.

4

A new approach to generating pseudoisochromatic plates

Laskowski M.

Prace Instytutu Elektrotechniki

|

2011

|

Z. 251

127-133

EN

Pseudoisochromatic plates have been used for detecting dichromacy (especially protanopia and deutanopia) for almost a century. This method, although widespread due to its simplicity and relatively low examination cost, is often criticized because of potential ambiguity and inaccessibility for certain groups of patients. In this article author analyzes different versions of currently used pseudoisochromatic plates and introduces a tool for generating customized plates in order to detect different types of dichromacy in certain user groups.

PL

Tablice pseudoizochromatyczne od prawie stulecia wykorzystywane są do detekcji dichromatyzmu (zwłaszcza protanopii i deutanopii). Pomimo wielu zalet - takich, jak choćby prostota i niski koszt badania - metoda ta jest często krytykowana ze względu na potencjalną niejednoznaczność uzyskiwanych wyników oraz niedostępność dla niektórych grup pacjentów. Poniższy artykuł omawia aplikację generującą tablice pseudoizochromatyczne dostosowane do diagnozowania konkretnego rodzaju zaburzenia widzenia barw oraz do konkretnego pacjenta. Przedstawione zostaną również wstępne wyniki badań.

5

Enhancement of accuracy in mammograms interpretation using ontology-driven editor for lesions description and CAD tool - preliminary results

Podsiadły-Marczykowska T., Wróblewska A., Przelaskowski A.

Journal of Medical Informatics & Technologies

|

2007

|

Vol. 11

235--243

EN

Although mammography is the standard of reference for the detection of early breast cancer, as many as 25% of breast cancers may be missed. To reduce the possibility of missing a cancer, the following methods and tools has been proposed: continuing education and training, prospective double reading, retrospective evaluation of missed cases, and use of computer-aided detection (CAD). In the presented paper we report on preliminary results of reducing the number of false-negative cases in mammograms interpretation by using ontology-driven editor for mammograms description, and MammoViewer, a CAD tool for radiologists' perception improvement. The use of editor resulted in reduction of interpretation errors and improved consistency of diagnosis. Computerized image processing methods make the signs of pathologies more conspicuous and so resulted in improvement of lesion perception.

6

Registration approaches for the optimisation of medical diagnostics and treatment

Chlebiej M., Król Z., Mikołajczak P.

Journal of Medical Informatics & Technologies

|

2005

|

Vol. 9

57--64

EN

Many medical diagnostics and treatment procedures in the oncology, cranio-maxillofacial surgery, radiotherapy and neurosurgery deal with volumetric as well as surface data. Tumor detection or generation of the virtual treatment scene involves using complementary data sets that are obtained from different sensors, for example MR and CT data, or by the same sensor at different epochs. The very need for registration arises from the fact that the complementary data sets are acquired by imaging devices using different spatial coordinate systems or/and the anatomically correct superposition of two data instances cannot be performed without locally applied elastic transformation. The volume or surface matching is therefore an essential task in these applications. From the mathematical point of view the data aligning problem is an optimization task, which can be solved by using deterministic or non-deterministic optimization algorithms. Depending on the data size and the complexity of required matching transformation the runtime behaviour of the registration methods can stretch out between real-time and many hours' computations. In this paper various applications of the same registration paradigm are presented and discussed. The wide spectrum of the medical applications shows the importance of the registration approach for the optimization of medical diagnostics and treatment.

7

Application of covering algorithm for classification of melanoma spots on the skin

Grzymała-Busse J. W., Hippe Z. S.

Journal of Applied Computer Science

|

2002

|

Vol. 10, nr 2

27-33

EN

An in-house elaborated and implemented covering algorithm was applied. For the development of learning models (in the form of production rules), used then for computer-assisted classification (hence, diagnosing) of melanoma spots on the skin. In our research, four types of marks (namely, Benign nevus, Blue nevus, Suspicious nevus, and Melanoma malignant) have be en investigated. One of the generated learning models (the most promimissing one) was optimized by execution of selected generic operations on production rules, what lead to a very concise set of rules (4 rules only) giving errorless classification of unseen cases tested.