Evaluation of CellSolutions BestPrep® Automated Thin-Layer Liquid-Based Cytology Papanicolaou Slide Preparation and BestCyte® Cell Sorter Imaging System

Abstract

Objective: A double-blind study was conducted to compare the performance of the new BestPrep® (CellSolutions) liquid-based thin-layer Papanicolaou (Pap) test with ThinPrep® (Hologic). Study Design: Samples from the study patients (n = 105) were collected twice in the same encounter with the ThinPrep sample always taken first and the BestPrep sample collected second. Slides were prepared according to both manufacturers' protocols and evaluated using manual microscopic review and the BestCyte® cell sorter imaging system (CellSolutions). Diagnostic truth for each case was determined by independent manual review of both slides by multiple pathologists and histology when available. The presence of atypical squamous cells of undetermined significance was the threshold for positive for sensitivity and specificity calculations. Results: BestPrep and ThinPrep, by manual review, had sensitivities for high-grade squamous intraepithelial lesion (HSIL) cases of 100 and 95.6%, respectively. Using the BestCyte cell sorter, both had 100% sensitivity. For the same HSIL cases, the digene HC2 high-risk human papillomavirus DNA test had sensitivities of 100% (BestPrep) and 95.6% (ThinPrep). Specificities were 71.4% (BestPrep) and 54.8% (ThinPrep). Conclusions: BestPrep was equivalent to ThinPrep for manual review even though BestPrep was always the second sample collected. The BestCyte cell sorter provides a practical alternative to manual review for both BestPrep and ThinPrep slides.

Towards generic image classification using tree-based learning: An extensive empirical study

“…We therefore suggest it could be used as a first try on any new image classification problem and we provided guidelines to do so. We already successfully applied these guidelines and variants of our approach in practical biomedical applications including (Delga et al, 2014;Jeanray et al, 2015).…”

Automated screening of Papanicolaou tests: A review of the literature

“…However, there are certainly widely accepted niche applications, such as maintaining an image for a slide sent out for consultation or sacrificed to perform additional testing such as molecular studies. Recently a WSI‐based cytology screening system, known as BestCyte, has been introduced . Similar to the original PAPNET, the system displays the most concerning cells of interest in panels on a monitor screen to facilitate cytotechnologist interpretation.…”

“…Recently a WSI-based cytology screening system, known as BestCyte, has been introduced. 65 Similar to the original PAPNET, the system displays the most concerning cells of interest in panels on a monitor screen to facilitate cytotechnologist interpretation. The complete WSI of the slide is also available for review.…”

The Need for Careful Data Collection for Pattern Recognition in Digital Pathology

“…Table 1 lists and organizes recommendations for less biased data collection based on lessons learned from the design of a practical cytology system,[20] from observations in digital pathology challenges,[21] from more general recommendations in the broader microscopy image analysis,[222326] and from computer vision literature. [27] While all these recommendations might not be followed simultaneously due to current standard practices and limited resources, we recommend to follow the most of these whenever possible.…”