Ensemble based system for whole-slide prostate cancer probability mapping using color texture features.
Name:
Publisher version
View Source
Access full-text PDFOpen Access
View Source
Check access options
Check access options
Affiliation
School of Computer Science and Informatics, University College Dublin, Ireland.Issue Date
2011MeSH
AlgorithmsColor
Histological Techniques
Humans
Image Interpretation, Computer-Assisted
Male
Pattern Recognition, Automated
Prostatic Neoplasms
Metadata
Show full item recordCitation
Ensemble based system for whole-slide prostate cancer probability mapping using color texture features., 35 (7-8):629-45 Comput Med Imaging GraphJournal
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging SocietyDOI
10.1016/j.compmedimag.2010.12.005PubMed ID
21269807Abstract
We present a tile-based approach for producing clinically relevant probability maps of prostatic carcinoma in histological sections from radical prostatectomy. Our methodology incorporates ensemble learning for feature selection and classification on expert-annotated images. Random forest feature selection performed over varying training sets provides a subset of generalized CIEL*a*b* co-occurrence texture features, while sample selection strategies with minimal constraints reduce training data requirements to achieve reliable results. Ensembles of classifiers are built using expert-annotated tiles from training images, and scores for the probability of cancer presence are calculated from the responses of each classifier in the ensemble. Spatial filtering of tile-based texture features prior to classification results in increased heat-map coherence as well as AUC values of 95% using ensembles of either random forests or support vector machines. Our approach is designed for adaptation to different imaging modalities, image features, and histological decision domains.Item Type
ArticleLanguage
enISSN
1879-0771ae974a485f413a2113503eed53cd6c53
10.1016/j.compmedimag.2010.12.005