Amidst the current health crisis and social distancing, telemedicine has become an important part of mainstream of healthcare, and building and deploying computational tools to support screening more efficiently is an increasing medical priority. The early identification of cervical cancer precursor lesions by Pap smear test can identify candidates for subsequent treatment. However, one of the main challenges is the accuracy of the conventional method, often subject to high rates of false negative. While machine learning has been highlighted to reduce the limitations of the test, the absence of high-quality curated datasets has prevented strategies development to improve cervical cancer screening. The Center for Recognition and Inspection of Cells (CRIC) platform enables the creation of CRIC Cervix collection, currently with 400 images (1,376 × 1,020 pixels) curated from conventional Pap smears, with manual classification of 11,534 cells. This collection has the potential to advance current efforts in training and testing machine learning algorithms for the automation of tasks as part of the cytopathological analysis in the routine work of laboratories.

Objective The objective of this study is to assess the performance of cytopathology laboratories providing services to the Brazilian Unified Health System (Sistema Único de Saúde -SUS) in the State of Minas Gerais, Brazil. Methods This descriptive study uses data obtained from the Cervical Cancer Information System from January to December 2012. Three quality indicators were analyzed to assess the quality of cervical cytopathology tests: positivity index, percentage of atypical squamous cells (ASCs) in abnormal tests, and percentage of tests compatible with high-grade squamous intraepithelial lesions (HSILs). Laboratories were classified according to their production scale in tests per year 5,000; from 5,001 to 10,000; from 10,001 to 15,000; and 15,001. Based on the collection of variables and the classification of laboratories according to production scale, we created and analyzed a database using Microsoft Office Excel 97-2003. Results In the Brazilian state of Minas Gerais, 146 laboratories provided services to the SUS in 2012 by performing a total of 1,277,018 cervical cytopathology tests. Half of these laboratories had production scales 5,000 tests/year and accounted for 13.1% of all tests performed in the entire state; in turn, 13.7% of these laboratories presented production scales of > 15,001 tests/year and accounted for 49.2% of the total of tests performed in the entire state. The positivity indexes of most laboratories providing services to the SUS in 2012, regardless of production scale, were below or well below recommended limits. Of the 20 laboratories that performed more than 15,001 tests per year, only three presented percentages of tests compatible with HSILs above the lower limit recommended by the Brazilian Ministry of Health. Conclusion The majority of laboratories providing services to the SUS in Minas Gerais presented quality indicators outside the range recommended by the Brazilian Ministry of Health.

Background and objectives: Saliency refers to the visual perception quality that makes objects in a scene to stand out from others and attract attention. While computational saliency models can simulate the expert's visual attention, there is little evidence about how these models perform when used to predict the cytopathologist's eye fixations. Saliency models may be the key to instrumenting fast object detection on large Pap smear slides under real noisy conditions, artifacts, and cell occlusions. This paper describes how our computational schemes retrieve regions of interest (ROI) of clinical relevance using visual attention models. We also compare the performance of different computed saliency models as part of cell screening tasks, aiming to design a computer-aided diagnosis systems that supports cytopathologists. Method: We record eye fixation maps from cytopathologists at work, and compare with 13 different saliency prediction algorithms, including deep learning. We develop cell-specific convolutional neural networks (CNN) to inves

Inclusion of rapid prescreening and/or 100% rapid review improved the diagnostic sensitivity of the cervical cytology examination and reduced false-negative results of routine screening and can provide good quality control.