Paper
29 March 2013 Novel chromatin texture features for the classification of pap smears
Babak Ehteshami Bejnordi, Ramin Moshavegh, K. Sujathan, Patrik Malm, Ewert Bengtsson, Andrew Mehnert
Author Affiliations +
Proceedings Volume 8676, Medical Imaging 2013: Digital Pathology; 867608 (2013) https://doi.org/10.1117/12.2007185
Event: SPIE Medical Imaging, 2013, Lake Buena Vista (Orlando Area), Florida, United States
Abstract
This paper presents a set of novel structural texture features for quantifying nuclear chromatin patterns in cells on a conventional Pap smear. The features are derived from an initial segmentation of the chromatin into bloblike texture primitives. The results of a comprehensive feature selection experiment, including the set of proposed structural texture features and a range of different cytology features drawn from the literature, show that two of the four top ranking features are structural texture features. They also show that a combination of structural and conventional features yields a classification performance of 0.954±0.019 (AUC±SE) for the discrimination of normal (NILM) and abnormal (LSIL and HSIL) slides. The results of a second classification experiment, using only normal-appearing cells from both normal and abnormal slides, demonstrates that a single structural texture feature measuring chromatin margination yields a classification performance of 0.815±0.019. Overall the results demonstrate the efficacy of the proposed structural approach and that it is possible to detect malignancy associated changes (MACs) in Papanicoloau stain.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Babak Ehteshami Bejnordi, Ramin Moshavegh, K. Sujathan, Patrik Malm, Ewert Bengtsson, and Andrew Mehnert "Novel chromatin texture features for the classification of pap smears", Proc. SPIE 8676, Medical Imaging 2013: Digital Pathology, 867608 (29 March 2013); https://doi.org/10.1117/12.2007185
Lens.org Logo
CITATIONS
Cited by 12 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Particles

Feature selection

Image segmentation

Image classification

Image filtering

Absorbance

Binary data

Back to Top