Unsupervised Segmentation of Color-Texture Regions in Images and Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active mask segmentation of fluorescence microscope images
IEEE Transactions on Image Processing
Real-time foreground-background segmentation using codebook model
Real-Time Imaging
Hi-index | 0.00 |
This paper proposes a novel method for segmenting microscope images of schisotsomiasis. Schistosomiasis is a parasitic disease with a global impact second only to malaria. Automated analysis of the parasite's reaction to drug therapy enables high-throughput drug discovery. These reactions take the form of phenotypic changes that are currently evaluated manually via a researcher viewing the video and assigning phenotypes. The proposed method is capable of handling the unique challenges of this task including the complex set of morphological, appearance-based, motion-based, and behavioral changes of parasites caused by putative drug therapy. This approach adapts a region-based segmentation algorithm designed to quickly identify the background of an image. This modified implementation along with morphological post-processing provides accurate and efficient segmentation results. The results of this algorithm improve the correctness of automated phenotyping and provide promise for high-throughput drug screening.