Computerized pathological image analysis for neuroblastoma prognosis
Source:
Proceedings of the 2007 American Medical Informatics Association Annual Symposium (2007)
Abstract:
We present a pathological image analysis system for computer-aided prognosis of neuroblastoma, a
childhood cancer. The image analysis system automatically classifies Schwannian stromal development of pathological tissue and determines the grade of differentiation. Due to the computational cost of processing large digitized slides, the system was implemented in a multi-resolution framework that is set up to run on a cluster of computers with automated load balancing. In our experiments, overall accuracies for stromal classification and the
grade of differentiation were 96.6% and 95.3%, respectively. The multi-resolution framework reduced the run time by 60% compared to a single resolution run; parallelization on a 16-node cluster reduced the run times further by 91%.
