Computer assisted automated detection is highly inevitable for recognizing neurological disorders, as it involves continuous monitoring of Electroencephalogram (EEG) signal. Being a non-stationary signal, suitable analysis is essential for EEG to differentiate the normal EEG and epileptic seizures. This paper highlights the importance of entropy based features to recognize the normal EEGs, and ictal as well as interictal epileptic seizures. Three non-linear features, such as, wavelet entropy, sample entropy, and spectral entropy are used to extract quantitative entropy features from the given EEG time using two neural network models, namely, recurrent Elman network (REN) and radial basis network (RBN) are then incorporated for the purpose of classification. The stationary properties of the EEG are exploited by estimating entropies at various time frames and the performance of the proposed scheme is evaluated using specificity, sensitivity and classification accuracy. From the experimental results, it is found that among the different entropies applied, the wavelet entropy features with recurrent Elman networks yields 99.75% and 94.5% accuracy for detecting normal vs. epileptic seizures and interictal focal seizures respectively.

Entropies based detection of epileptic seizures with artificial neural network classifiers

Effective segmentation and classification for HCC biopsy images

The aim of this study was to develop an open-source, modular, locally run or server-based system for 3D radiomics feature computation that can be used on any computer system and included in existing workflows for understanding associations and building predictive models between image features and clinical data, such as survival. The QIFE exploits various levels of parallelization for use on multiprocessor systems. It consists of a managing framework and four stages: input, pre-processing, feature computation, and output. Each stage contains one or more swappable components, allowing run-time customization. We benchmarked the engine using various levels of parallelization on a cohort of CT scans presenting 108 lung tumors. Two versions of the QIFE have been released: (1) the open-source MATLAB code posted to Github, (2) a compiled version loaded in a Docker container, posted to DockerHub, which can be easily deployed on any computer. The QIFE processed 108 objects (tumors) in 2:12 (h/mm) using 1 core, and 1:04 (h/mm) hours using four cores with object-level parallelization. We developed the Quantitative Image Feature Engine (QIFE), an open-source feature-extraction framework that focuses on modularity, standards, parallelism, provenance, and integration. Researchers can easily integrate it with their existing segmentation and imaging workflows by creating input and output components that implement their existing interfaces. Computational efficiency can be improved by parallelizing execution at the cost of memory usage. Different parallelization levels provide different trade-offs, and the optimal setting will depend on the size and composition of the dataset to be processed.

Quantitative Image Feature Engine (QIFE): an Open-Source, Modular Engine for 3D Quantitative Feature Extraction from Volumetric Medical Images.

A Brain Computer Interface (BCI) is a system that provides an individual a non-muscular way to control his surroundings by working on the activity signals generated in his brain Activity signals collected from the brain in the form Electroencephalogram (EEG) are used in the system described in this paper Time Domain normalization has been used in the preprocessing stage Wavelet transform with pattern adapted wavelet filter is used for the purpose of feature extraction Exact Radial Basis Neural networks are used for the classification of signals and heuristic weight adjustment of neural networks was done in final decision making Tests carried out on two different datasets give accuracies of more than 91% and 86%

Towards a Brain Computer Interface using wavelet transform with averaged and time segmented adapted wavelets

Electroencephalograms (EEG) are the brain signals that provide us the valuable information about the normal or epileptic state of the brain. In this paper the EEG signals were characterized by wavelet, sample and spectral entropy approach and the recurrent neural network classifier is used for the automated detection of epileptic seizures.

Automated detection of epileptic seizures using wavelet entropy feature with recurrent neural network classifier

As the standard especially for the storage and transmission of medical images, the standard of Digital Imaging and Communications in Medicine (DICOM) is popular to the people of the world. And as a result, almost all the outputs of the computerized tomography (CT), magnetic resonance (MR), digital subtraction angiography (DSA) and ultrasonography (US) are saved as DICOM format. However, the DICOM format files can be opened by the original programs of windows OS, which is not convenient with the further research in image processing. The paper mainly does some research in the conversion from DICOM format files into general image/ media files. The procedure is to convert DICOM format files into bitmaps and then convert the bitmaps into other general image/ media files. The images then can be viewed directly by the original programs of Windows OS, which will facilitate the further researches on image process. The DICOM format files can be displayed while being converted; the images displayed can also be done with some further operations, such as the process of lightness and contrast gradient of image, image filtering and segmentation.

Medical Image Conversion with DICOM

According to the features of the configuration and color information on the cancer cells, an adaptive automatic threshold segmentation based on the RGB and HIS color spaces is presented, which is available to segment suspected cancer cells and nucleus from the complex backgrounds in the microscopic images. The edges of the suspected cancer cells and nucleus are detected by using Canny operator. Using the technology of eight-chain code tracking, the feature values of suspected cancer cells are extracted. The feature values consists of the perimeter, the area, the height, the width, the circularity, the rectangularity, the extension and the area ratio between the nucleus and the cytolympth. Based on feature values, a two-round recognition scheme combined with morphologic and colourometry is proposed to recognize and classify the pathological and normal cells. The results show that the proposed algorithm can efficiently segment cell images and receive higher accuracy of cancer cell diagnosis.

Microscopic Image Analysis and Recognition On Pathological Cells

For many years brain-computer interfaces research programs have been very popular. The classification algorithm of the EEG signals has attracted much attention. In this paper, an experiment is designed on imaginary left or right hand movements and a new algorithm is proposed to identify different EEG patterns. Butterworth filter has been applied to retrieve the useful signals. Interference noise has been eliminated using a digital filter. The wavelet entropy is treated as one feature in our approach. The adaptive autoregressive model combined with the event-related desynchronization is used in our research to obtain the other feature. Two obtained features reflect time domain and frequency domain features of EEG signal, and will be used by a BP neural network for training. Simulation has been carried out and the results of the simulation show that this approach can restrain noise disturbance and can effectively express mental states. When used in the classification of special events in brain-computer interface, this approach has some advantage. Moreover, it can be used for the online analysis.

Zhenwang Zhang

Papers

Medical Image Conversion with DICOM

Microscopic Image Analysis and Recognition On Pathological Cells

Brainwave Classification Based on Wavelet Entropy and Event-Related Desynchronization