Title :
IMAGE ANALYSIS FOR AUTOMATED ASSESSMENT OF GRADE OF NEUROBLASTIC DIFFERENTIATION
Author :
Kong, Jun ; Shimada, Hiroyuki ; Boyer, Kim ; Saltz, Joel ; Gurcan, Metin
Author_Institution :
Dept. of Electr. & Comput. Eng., Ohio State Univ., Columbus, OH
Abstract :
Peripheral neuroblastic tumors (pNTs) make the most commonly encountered tumor groups in children. Neuroblastoma, one of the categories in pNTs, is known to have unique biological behaviors with variable clinical prognoses of the patients. Part of the neuroblastoma prognosis is closely related with grade of neuroblastic differentiation. In this work, we present an automatic classification system that includes a novel segmentation method using the EM algorithm with the Fisher-Rao criterion as its kernel. This is followed by a classification stage with classifiers applied to the actual neuroblastoma images. The good classification accuracy suggests that the developed method is promising in automating this pathological assessment
Keywords :
biomedical optical imaging; brain; cellular biophysics; expectation-maximisation algorithm; feature extraction; image segmentation; medical image processing; neurophysiology; paediatrics; pattern classification; tumours; Fisher-Rao criterion; automated assessment; automatic classification system; biological behaviors; children; expectation-maximization algorithm; feature extraction; image analysis; neuroblastic differentiation; neuroblastoma; neuroblastoma images; neuroblastoma prognosis; pathological assessment automation; pattern classification; peripheral neuroblastic tumors; segmentation method; tumor groups; variable clinical prognoses; Biomedical computing; Color; Computed tomography; Image analysis; Image coding; Image segmentation; Image storage; Neoplasms; Pathology; Pediatrics;
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on
Conference_Location :
Arlington, VA
Print_ISBN :
1-4244-0672-2
Electronic_ISBN :
1-4244-0672-2
DOI :
10.1109/ISBI.2007.356788