Using cell nuclei features to detect colon cancer tissue in hematoxylin and eosin stained slides

• Published in: Cytometry. Part A Vol. 91; no. 8; pp. 785 - 793
• Main Authors: Jørgensen, Alex Skovsbo, Rasmussen, Anders Munk, Andersen, Niels Kristian Mäkinen, Andersen, Simon Kragh, Emborg, Jonas, Røge, Rasmus, Østergaard, Lasse Riis
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.08.2017
• Subjects: Algorithms; Area Under Curve; Benign; Cancer; Cell Nucleus - pathology; Cell proliferation; cell segmentation; Classification; Clustering; Colon; Colon cancer; Colonic Neoplasms - pathology; Colorectal cancer; Cytometry; Diagnosis; Differentiation; Eosine Yellowish-(YS) - administration & dosage; Feature extraction; H&E stain; Hematoxylin - administration & dosage; Humans; image analysis; Image Interpretation, Computer-Assisted - methods; Image processing; Image segmentation; Nuclei; Nuclei (cytology); Sensitivity and Specificity; Staining and Labeling - methods; Tissues; Vector quantization; colon; cancer; H&E stain; cell segmentation; classification; image analysis

Currently, diagnosis of colon cancer is based on manual examination of histopathological images by a pathologist. This can be time consuming and interpretation of the images is subject to inter‐ and intra‐observer variability. This may be improved by introducing a computer‐aided diagnosis (CAD) syst...