Abstract

The purpose of this study was to discriminate the main subsets of lung carcinomas of the WHO classification of 2004 by nuclear chromatin texture feature analysis. Our collective comprised 56 typical and 19 atypical carcinoids, 37 small-cell carcinomas, 15 large-cell neuroendocrine carcinomas, 42 adenocarcinomas, and 26 squamous cell carcinomas. After Feulgen staining, cell nuclei were automatically measured using a high-resolution image analyser (CytoSavant Oncometrics, Vancouver, BC, Canada). Texture features describing the granularity and the compactness of the nuclear chromatin were extracted for calculation of classification rules, which allowed the discrimination of different tumor groups. By applying the classification rule that described the granularity of the nuclear chromatin (defined by four different parameters) small-cell and non-small-cell lung carcinoma could correctly be discriminated in 93%. No significant discrimination was possible between the different subtypes of large-cell carcinomas, including large-cell neuroendocrine carcinoma. When using compactness of chromatin (defined by four texture parameters) as a means of discrimination, carcinoids and non-small-cell lung carcinomas were correctly distinguished in 92%. No significant discrimination between neuroendocrine tumors was achieved though. Our findings are in accordance with the new WHO classification of 2004: neuroendocrine tumors of the lung are now classified according only to their mitotic counts and presence of necrosis but not by their morphology; their discrimination by the means of nuclear image analysis is not sufficient and therefore not appropriate any longer.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.