Automated Pap Smear Cell Analysis: Optimizing the Cervix Cytological Examination

Abstract

Cervical cancer screening is one of the most widespread tests in the world, and the acquisition of digital images of Pap smears is about to become part of the laboratories routine. The ability to collect these standard exam data has increased drastically, and available tools for image analysis and quantification are not accurate and/or customized enough to deliver relevant information about the image content. Aiming at enabling pathology laboratories to deal with large amounts of digitized Pap smears slides, we propose to design computer vision algorithms for quantitative analysis and pattern recognition from 2D images. The goal is to bring high technology to laboratories focused on underserved communities of women for the prevention of cervical cancer; in these public health care institutions, there is no perspective of using "omics" data in the medium term, but only clinical annotations and Pap smears slides. Here, we describe our project and propose computational tools adapted to this application, addressing the needs from end-to-end, including enhancement, noise minimization, segmentation of regions of interest, extraction and classification of objects.

Automating cell detection and classification in human brain fluorescent microscopy images using dictionary learning and sparse coding

“…Method proposed by Ushizima et al (DU) [52]: the super-pixel Voronoi diagram (SPVD) method [52] was selected the best performing algorithm during the Overlapping Cervical Cytology Image Segmentation Challenge [52, 53]. We tested a modified version provided by the authors, tuned to work with fluorescence instead of bright field.…”