Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/73825
Title: Clasificadores para el reconocimiento automático de células blásticas en leucemias agudas linfoides y mieloides
Author: Molina Abril, Helena
Tutor: Alférez, Santiago  
Others: Universitat Oberta de Catalunya
Ventura, Carles  
Morán Moreno, Jose Antonio  
Abstract: Morphological tests of peripheral blood analysis is the first step in the process of fast morphological diagnosis of patients with malignant blood diseases, including acute leukemia, in which an early treatment is crucial for longer patient's survival. These tests are as well widely used for the selection of additional techniques and monitoring of such patients. The automatic analysis of peripheral blood images has been integrated into the daily routine of numerous clinical laboratories. These automatic systems are greatly advantageous, since they allow to classify a large number of normal blood cells. However, these systems generally underestimate the total number of blast cells, since they are easily confused with normal and reactive lymphocytes. In this work we aim to automatically and objectively differenciate between different types of cells, focussing our interest on reactive lymphocytes (infections) and blast cells (acute leukemias). A database of quantitative characteristics directly extracted from the digital images of peripheral blood smear samples, obtained in the CORE laboratory of the Hospital Clinic of Barcelona, will be used for this purpose. Machine learning techniques will be applied for the generation of classifiers, which will be evaluated through the calculation of different performance measures.
Keywords: machine learning
acute leukemia
Document type: info:eu-repo/semantics/masterThesis
Issue Date: Jan-2018
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
hmolinaaTFM0118memoria.pdfMemoria del TFM2,9 MBAdobe PDFThumbnail
View/Open