Title :
Computer-aided Prognosis of Neuroblastoma: Detection of mitosis and karyorrhexis cells in digitized histological images
Author :
Sertel, O. ; Catalyurek, U.V. ; Shimada, H. ; Guican, M.N.
Author_Institution :
Dept. of Electr. & Comput. Eng., Ohio State Univ., Columbus, OH, USA
Abstract :
Histopathological examination is one of the most important steps in evaluating prognosis of patients with neuroblastoma (NB). NB is a pediatric tumor of sympathetic nervous system and current evaluation of NB tumor histology is done according to the International Neuroblastoma Pathology Classification. The number of cells undergoing either mitosis or karyorrhexis (MK) plays an important role in this classification system. However, manual counting of such cells is tedious and subject to considerable inter- and intra-reader variations. A computer-assisted system may allow more precise results leading to more accurate prognosis in clinical practice. In this study, we propose an image analysis approach that operates on digitized NB histology samples. Based on the likelihood functions estimated from the samples of manually marked regions, we compute the probability map that indicates how likely a pixel belongs to an MK cell. Component-wise 2-step thresholding of the generated probability map provides promising results in detecting MK cells with an average sensitivity of 81.1% and 12.2 false positive detections on average.
Keywords :
biomedical optical imaging; cancer; cellular biophysics; image classification; image segmentation; medical image processing; neurophysiology; paediatrics; probability; tumours; International Neuroblastoma Pathology Classification; component-wise 2-step thresholding; computer-aided prognosis; computer-assisted system; digitized histological images; false positive detection; histopathological examination; image analysis approach; inter-reader variation; intra-reader variation; karyorrhexis cell detection; likelihood functions; mitosis cell detection; patient prognosis; pediatric tumor; probability map generation; sympathetic nervous system; Cancer; Image color analysis; Image texture analysis; Microscopy; Neoplasms; Niobium; Pathology; Sympathetic nervous system; Tumors; USA Councils; Cell Death; Child; Diagnosis, Computer-Assisted; Humans; Image Processing, Computer-Assisted; Likelihood Functions; Mitosis; Neuroblastoma; Prognosis; Signal Processing, Computer-Assisted;
Conference_Titel :
Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE
Conference_Location :
Minneapolis, MN
Print_ISBN :
978-1-4244-3296-7
DOI :
10.1109/IEMBS.2009.5332910