BACKGROUND: Infection with high-risk human papillomaviruses (hrHPVs) is a frequent cause of cervical intraepithelial neoplasias and carcinomas. The recently developed p16/Ki67 dual stain of cytologic preparations possesses superior specificity over current HPV testing for detecting moderate- and high-grade dysplasias and can potentially be applied in routine cytology screening. Image analysis can possibly improve the efficiency of evaluating Papanicolaou (Pap) smears, if dual-stained nuclei are accurately localized and reliably distinguished from the background of other cells. METHODS: Here, we describe a technique comprising color deconvolution, radial symmetry detector, and a superpixel-based segmentation for computerized delineation of nuclei in Pap smears stained with p16/Ki67. RESULTS: The performance of the method was determined by the precision and recall in 99 images (n = 19,323 cells) and reached 0.952 and 0.958, respectively. The accuracy of delineation, assessed by the Jaccard index (n = 1,080 cells), was 0.794. In single cells the precision and recall was higher than in clumps (P = 0.005). CONCLUSIONS: In summary, the new technique delineates large and small nuclei irrespectively of coloration with a significantly better performance than a method solely involving the radial symmetry detector. Therefore, it is suited to automatically define nuclear areas for quantification of nuclear biomarkers in smears.
BACKGROUND:Infection with high-risk human papillomaviruses (hrHPVs) is a frequent cause of cervical intraepithelial neoplasias and carcinomas. The recently developed p16/Ki67 dual stain of cytologic preparations possesses superior specificity over current HPV testing for detecting moderate- and high-grade dysplasias and can potentially be applied in routine cytology screening. Image analysis can possibly improve the efficiency of evaluating Papanicolaou (Pap) smears, if dual-stained nuclei are accurately localized and reliably distinguished from the background of other cells. METHODS: Here, we describe a technique comprising color deconvolution, radial symmetry detector, and a superpixel-based segmentation for computerized delineation of nuclei in Pap smears stained with p16/Ki67. RESULTS: The performance of the method was determined by the precision and recall in 99 images (n = 19,323 cells) and reached 0.952 and 0.958, respectively. The accuracy of delineation, assessed by the Jaccard index (n = 1,080 cells), was 0.794. In single cells the precision and recall was higher than in clumps (P = 0.005). CONCLUSIONS: In summary, the new technique delineates large and small nuclei irrespectively of coloration with a significantly better performance than a method solely involving the radial symmetry detector. Therefore, it is suited to automatically define nuclear areas for quantification of nuclear biomarkers in smears.
Authors: Miriam Reuschenbach; Andreas Clad; Christina von Knebel Doeberitz; Nicolas Wentzensen; Janina Rahmsdorf; Frauke Schaffrath; Henrik Griesser; Nikolaus Freudenberg; Magnus von Knebel Doeberitz Journal: Gynecol Oncol Date: 2010-07-08 Impact factor: 5.482
Authors: Nicolas Wentzensen; Barbara Fetterman; Diane Tokugawa; Mark Schiffman; Philip E Castle; Shannon N Wood; Eric Stiemerling; Nancy Poitras; Thomas Lorey; Walter Kinney Journal: Cancer Cytopathol Date: 2014-08-12 Impact factor: 5.284
Authors: Nicolas Wentzensen; Lauren Schwartz; Rosemary E Zuna; Katie Smith; Cara Mathews; Michael A Gold; R Andy Allen; Roy Zhang; S Terence Dunn; Joan L Walker; Mark Schiffman Journal: Clin Cancer Res Date: 2012-06-06 Impact factor: 12.531
Authors: Hans Ikenberg; Christine Bergeron; Dietmar Schmidt; Henrik Griesser; Francisco Alameda; Claudio Angeloni; Johannes Bogers; Roger Dachez; Karin Denton; Jalil Hariri; Thomas Keller; Magnus von Knebel Doeberitz; Heinrich H Neumann; Luis M Puig-Tintore; Mario Sideri; Susanne Rehm; Ruediger Ridder Journal: J Natl Cancer Inst Date: 2013-10-04 Impact factor: 13.506