In this paper, we present a Computer Aided Diagnosis that implements a supervised approach to discriminate vessels versus tubules that are two different types of structural elements in images of biopsy tissue. In particular, in this work we formerly describe an innovative preliminary step to segment region of interest, then the procedure to extract from them significant features and finally present and discuss the Back Propagation Neural Network binary classifier performance that shows Precision 91 % and Recall 91 %.
Neural network classification of blood vessels and tubules based on haralick features evaluated in histological images of kidney biopsy / Bevilacqua, Vitoantonio; Pietroleonardo, Nicola; Triggiani, Vito; Gesualdo, Loreto; Di Palma, Anna Maria; Rossini, Michele; Dalfino, Giuseppe; Mastrofilippo, Nico (LECTURE NOTES IN COMPUTER SCIENCE). - In: Advanced Intelligent Computing Theories and Applications 11th International Conference, ICIC 2015, Fuzhou, China, August 20-23, 2015. Proceedings, Part III[s.l] : Springer, 2015. - ISBN 978-3-319-22052-9. - pp. 759-765 [10.1007/978-3-319-22053-6_81]
Neural network classification of blood vessels and tubules based on haralick features evaluated in histological images of kidney biopsy
BEVILACQUA, Vitoantonio;
2015-01-01
Abstract
In this paper, we present a Computer Aided Diagnosis that implements a supervised approach to discriminate vessels versus tubules that are two different types of structural elements in images of biopsy tissue. In particular, in this work we formerly describe an innovative preliminary step to segment region of interest, then the procedure to extract from them significant features and finally present and discuss the Back Propagation Neural Network binary classifier performance that shows Precision 91 % and Recall 91 %.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.