A novel gland segmentation and classification scheme applied to an H&E histology image of the prostate tissue is proposed.
For gland segmentation, we associate appropriate nuclei objects with each lumen object to create a gland segment. We further extract 22 features to describe the structural information and contextual information for each segment. These features are used to classify a gland segment into one of the three classes: artifact, normal gland and cancer gland. On a dataset of 48 images at 5x magnification (which includes 525 artifacts, 931 normal glands and 1,375 cancer glands), we achieved the following classification accuracies: 93% for artifacts v. true glands; 79% for normal v. cancer glands, and 77% for discriminating all three classes. The proposed method outperforms state of the art methods in terms of segmentation and classification accuracies and computational efficiency.
Written by:
Nguyen K, Sarkar A, Jain AK. Are you the author?
Michigan State Unversity, East Lansing, MI 48824, USA
Reference: Med Image Comput Comput Assist Interv. 2012;15(Pt 1):115-23.
PubMed Abstract
PMID: 23285542
