GemIdent is an interactive program that identifies regions of interest in images. It is specifically designed for color segmentation in images with few colors, where the objects of interest look alike with small variation. For example, oranges in a tree (see quick demo) and cells in microscopic images (see histological demo). GemIdent was developed at Stanford University by Dr. Adam Kapelner during the Summer and Fall of 2006 in the lab of Dr. Peter Lee under the tutelage of Professor Susan Holmes. The GemIdent algorithm takes full advantage of color information in the images and the identification engine employs the latest supervised machine learning algorithms. The concept was inspired by data from the Kohrt et al 2006 publication concerning immune profiles of lymphnodes in breast cancer patients. Hence, GemIdent works well when identifying cells in IHC-stained tissue imaged via automated light microscopy when the nuclear background stain and membrane/cytoplasmic stain are well-defined.
References in zbMATH (referenced in 2 articles )
Showing results 1 to 2 of 2.
- Chen, Shengyong; Zhao, Mingzhu; Wu, Guang; Yao, Chunyan; Zhang, Jianwei: Recent advances in morphological cell image analysis (2012)
- Yan, Donghui; Wang, Pei; Linden, Michael; Knudsen, Beatrice; Randolph, Timothy: Statistical methods for tissue array images -- algorithmic scoring and co-training (2012)