MSc Informatics and Multimedia
BSc Informatics Engineering
School of Reserve Officers Infantry
Adobe Certified, Web Communication using Dreamweaver
Test Of English International Communication
In this master thesis a 2D and a 3D CNN has been developed for extracting multi-dimensional medical image features for discriminating between primary to metastatic malignant liver lesions. The proposed network consists of four consecutive strided 3D Convolutional layers with 3x3x3 kernel size and ReLU as activation function followed by a fully-connected layer with 2048 neurons and a Softmax layer for binary classification. The results demonstrated a superior classification performance of the 3D over the 2D with 93.9% vs 65% and 95% vs 67% tissue classification accuracy and sensitivity respectively. These results suggest that there is a significant potential benefit of Deep Learning on MRI in enhancing the diagnostic information towards more precise, personalized health care in liver cancer patients. Early image-based information regarding primary-metastatic pathology can optimize therapy decisions early and spare patients of unnecessary therapy.
Proceedings of the 14th Extended Semantic Web Conference (ESWC2017)
java application for accessing/editing data of a complex MsSQL db. eclipse/jdk/jdbc/mssql
a simple responsive website html/css/js/seo/social media integration for an individual taxi driver
as part of my thesis was to develop a system for informing the client about the current location of the city buses in real time for android devices.
after I successfully completed the web-app for University Hostpital of Heraklion they also assign me with the creation of a captive portal for their wifi infrastructure for better monitor/management the network resources
I designed a web-app as an inventory for all the computers of the hospital utilizing user input and the existing OCS Inventory database
my first web application for distributing pdf report files, only by inserting a 10 digit pin
a simple web site for a small company in html/js/css