![]() ![]() Bland Altman plots showed overall good agreement between measurements performed by both methods. The coefficient of correlation (r) for all three axes was above or equal to 0.90. We observed a strong correlation between post-mortem MRI measurements at 7T and post-mortem macroscopic measurements at autopsy, with p<0.001. Three-axis cardiac measurements were performed by both examination methods, using the same landmarks. After post-mortem imagistic examination, all cases were submitted to conventional autopsy. All cases were immersed in 10% formalin solution, and after proper fixation they were examined using high-field MRI at 7T. All fetuses resulted from therapeutic termination of pregnancy (TOP) due to plurimalformative syndromes or chromosomal anomalies. Twelve second-trimester fetuses with gestational ages ranging from 13 to 19 weeks of gestation were considered. The aim of our study was to establish if high-field post-mortem MRI at 7T can perform three-dimensional measurements of the fetal heart, and retrieve results comparable to post-mortem macroscopic measurements performed at autopsy, in fetuses with whole body weight below 500 g. ![]() The objective of this project was to develop a fully automated computer vision system that can count tokens used at festivals for buying food and drinks.Objective. Supervisors: Wim Rutten, Michel Van Putten, Chin TangwiriyasakulĮxtraction of the Subthalamic Nucleus from Rat Brain ImagesĮxtraction of certain biological structures from grayscale histological images using a texture descriptor (GLCM) and a classifier (SVM) for segmentation/classification. We extracted the features for different periods (8, 6, 4, and 2 seconds) to see what the influence on all of the above parameters was. Since the eventual aim is to build a system that can be used at home, we examined several electrode configurations in order to find out the minimum number of electrodes needed to control the system. Furthermore, we have employed a spatial filtering method, namely common spatial patterns (CSP), to see if classification outcomes could be improved. For this purpose we have investigated four band power features: broad-band (8 - 30 Hz), α-band (8 - 13 Hz), β-band (13 - 30 Hz), and user-defined band and two classification methods: linear discriminant analysis (LDA) and support vector machines (SVM). Our goal was to find a way to model the two states associated with the sensorimotor rhythm: synchronized (rest) and desynchronized (active). The BCI system should give the patient neurofeedback according to his sensorimotor rhythm. This is done by using electroencephalographic (EEG) signals in a brain computer interface (BCI) setup. The effect of this approach is improved by neurofeedback. One method is the practice of motor imagery. Several methods exist for stroke rehabilitation. The available software should of course be improved and evolved during my thesis.ĪUTOMATIC CLASSIFICATION BETWEEN ACTIVE BRAIN STATE VERSUS REST STATE IN HEALTHY SUBJECTS AND STROKE PATIENTS As the name implies it should take some already available software, like SpectraClassifier (SC) and the INTERPRET Decision Support System (DSS), and transform them into plug-ins for jMRUI. My personal project is supposed to be delivered within 36 months from the start-date. My research falls in the Research Program 2 (RP2) research programme of TRANSACT: “MRS in multi-modal fusion”. This research will be developed in the context of the following EU Initial Training Network (FP7-PEOPLE-2012-ITN): TRANSACT, Transforming Magnetic Resonance Spectroscopy into a Clinical Tool, to which I have been appointed as a Marie Curie Early Stage Researcher (ESR). July 2010 - Bachelor in Applied Electronics, Universitatea Politehnica Bucuresti, Facultatea de electronica, Telecomunicatii si Tehnologia Informatieiĭecision support system and spectral classification tool meta-plug-ins for the jMRUI platform Romanian, English, Italian, French, German, Japaneseĭecember 2012 - MsC in Electrical Engineering - Biomedical Systems, University of Twente Pattern recognition, Signal Processing, Machine Learning, Brain Computer Interface, Magnetic Resonance Spectroscopy, Brain Tumor, Decision-Support Systems
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |