Iterative randomized irregular circular algorithm for proliferation rate estimation in brain tumor Ki-67 histology images

摘要: This CAD system calculates proliferation rate estimation (PRE) automatically.A novel Iterative Randomized Irregular Circular Algorithm (IRIC) has been proposed.The Brain Tumor Ki-67 Histology Images are taken from UKM Medical Centre.Prior to a random set region of interest, IRIC counts blue and brown cells PRE.IRIC outperforms Hough Transform about 98% F-measurement rate. Proliferation is clinically performed histopathology images. As brain tumor tissues very complex, accurate PRE determination requires manual cell counting that tedious, time consuming inherently inaccurate due inter-personal variations. Therefore, pathologists usually determine the based on their experience visualization without actual counting. Automating can substantially increase efficiency accuracy pathologists' PRE. In addition, developing deterministic reproducible value crucial reduce inter-observer variability. this paper, Computer Aided Diagnosis (PRECAD) developed automate microscopic images for tumors. The process involves six steps: color space transformation, customized modification, nuclei segmentation K-Means clustering, preprocessing extracted cells, an iterative structured circle detection algorithm, finally, calculating value. proposed algorithm able detect irregular overlapping by introducing dynamic initialization basic RCD method, dividing entire image into partitions 8-neighbor connected components. We initiated new selection method determining best candidate yields reduced probability incorrectly detecting circles, technique via number iterations guarantees finding all in selected partition. Using same innovations mentioned above, our also be used ?two or more cells. PRECAD achieved high accuracy, as determined quantitative analysis precision, recall test values 97.8%, 98.3% 98.7%, 98.4% respectively. Thus, reliable pathologist estimating rate, while featuring inherent reproducibility.