El jueves 12 de mayo, en la Sala de Grados A de la ETSI Telecomunicación, está prevista una sesión doble de conferencias sobre Machine Learning  techniques for Diagnosis and Decision Making support in Medicine

Las conferencias previstas son:

Combined Machine Learning Techniques for Decision Making Support in Medicine
Ponente: Dra. Ruxandra Stoen (Department of Computer Science, University of Craiova, Romania)
Lugar: Ingeniería de Telecomunicación- Sala de Grados A
Fecha y Hora: Jueves, 12 de mayo, a las 11:30
Abstract: Computational intelligent support for decision making is becoming increasingly popular and essential among medical professionals. Also, with the modern medical devices being capable to communicate with ICT, created models can easily find practical translation into software. Machine learning solutions for medicine range from the robust but opaque paradigms of support vector machines and neural networks to the also performant, yet more comprehensible, decision trees and rule-based models. So how can such different techniques be combined such that the professional obtains the whole spectrum of their particular advantages? The presented approaches have been conceived for various medical problems, while permanently bearing in mind the balance between good accuracy and understandable interpretation of the decision in order to truly establish a trustworthy ‘artificial’ second opinion for the medical expert.
Personal data: Dr. Ruxandra Stoean is Associate Professor at the Department of Computer Science, University of Craiova, Romania. Her interest in evolutionary computation and support vector machines is revealed by more than 60 published papers, two book chapters and one book published by Springer, while the impact of her research is reflected by an h-index of 8 on Thomson Reuters Web of Science. She was and is involved in several projects related to automated learning in medicine funded by national research agencies. She was awarded the prize Grigore Moisil for Computer Science by the Romanian Academy in 2008 for her research results.

 

Automated Diagnosis of Colorectal Neoplasm Based on Histological Images
Ponente: Dr.  Catalin Stoen (Department of Computer Science, University of Craiova, Romania)
Lugar: Ingeniería de Telecomunicación- Sala de Grados A
Fecha y Hora: Jueves, 12 a las 12:00 (estimada)
Idioma: Inglés
Abstract: The pathologists are faced with large amount of histological images to interpret in order to correctly identify whether the tissue that is examined is part of a healthy organ or a cancerous one. In the latter case, they have to decide the degree of the cancer. The current research aims to reduce the amount of work of the human expert by identifying at least the simplest cases and allowing the pathologist to concentrate on the most complicated ones. It is assumed that the histological images are already produced. The computational process consists of several stages like preprocessing the images, segmentation of the components of interest (glands, nuclei), feature extraction from the identified components and finally diagnosis via machine learning techniques. The results indicate an accuracy of almost 80% in diagnosing 357 images in 4 different classes and there are prospects for further improvement.
Personal data: Dr. Catalin Stoean is Associate Professor at the Department of Computer Science, University of Craiova, Romania. Most of his publications are related to evolutionary computation and applications of such models especially for classification. Image processing represents one of his recent interests, as he currently leads an interdisciplinary project related to the application of computational technologies in medicine.