This paper presents the design and the implementation of a Computer Aided Diagnosis (CAD) system for the clinical analysis of Peripheral Blood Smears (PBS also called Blood Film). The proposed system is able to count and classify the five types of leucocytes located in the tail of a PBS for computing the leukocyte formula. Image processing and segmentation techniques were used to extract 33 leucocyte's features (morphological, chromatic and texture-based). Only 7 features, selected by using the Information Gain Ranking algorithm of Weka platform, were used to evaluate the classification performance of two different classifiers: Back Propagation Neural Network (BPNN) and Decision Tree (DT). From the comparison between the two proposed approaches we can argue that the BPNN performed better than the DT on the validation set. Finally, the Neural Network classifier was evaluated with a test set composed of 1274 leucocytes obtaining good results in terms of Precision (87.9%) and Sensitivity (97.4%).
A supervised CAD to support telemedicine in hematology / Bevilacqua, Vitoantonio; Buongiorno, Domenico; Carlucci, Pierluigi; Giglio, Ferdinando; Tattoli, Giacomo; Guarini, Attilio; Sgherza, Nicola; De Tullio, Giacoma; Minoia, Carla; Scattone, Anna; Simone, Giovanni; Girardi, Francesco; Zito, Alfredo; Gesualdo, Loreto. - (2015). (Intervento presentato al convegno International Joint Conference on Neural Networks, IJCNN 2015 tenutosi a Killarney, Ireland nel July 12-17, 2015) [10.1109/IJCNN.2015.7280464].
A supervised CAD to support telemedicine in hematology
BEVILACQUA, Vitoantonio;Buongiorno, Domenico;
2015-01-01
Abstract
This paper presents the design and the implementation of a Computer Aided Diagnosis (CAD) system for the clinical analysis of Peripheral Blood Smears (PBS also called Blood Film). The proposed system is able to count and classify the five types of leucocytes located in the tail of a PBS for computing the leukocyte formula. Image processing and segmentation techniques were used to extract 33 leucocyte's features (morphological, chromatic and texture-based). Only 7 features, selected by using the Information Gain Ranking algorithm of Weka platform, were used to evaluate the classification performance of two different classifiers: Back Propagation Neural Network (BPNN) and Decision Tree (DT). From the comparison between the two proposed approaches we can argue that the BPNN performed better than the DT on the validation set. Finally, the Neural Network classifier was evaluated with a test set composed of 1274 leucocytes obtaining good results in terms of Precision (87.9%) and Sensitivity (97.4%).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
