Low-Cost Interventions to Improve Cervical Cancer Screening: An Integrative Review.

PROBLEM IDENTIFICATION: Cervical cancer (CC) is a major public health problem in low- and middle-income countries. Although screening can reduce CC incidence, screening programs are difficult to implement in resource-limited countries, making innovative interventions necessary. LITERATURE SEARCH: PubMed®, MEDLINE®, CINAHL®, LILACS, and SciELO databases were searched for studies published within the past five years that explored interventions to improve CC screening. DATA EVALUATION: Of the 486 articles identified, 35 were included in the review. The evidence was summarized, analyzed, and organized by theme. SYNTHESIS: Several low-cost interventions improved aspects of CC screening, most of which were associated with a significant increase in adherence and uptake. Other interventions led to better baseline knowledge and involvement among patients and healthcare providers and a higher proportion of patients receiving treatment. Screening programs can use single or multiple approaches and match them to the local conditions and available resources. IMPLICATIONS FOR PRACTICE: By understanding the various interventions that can mitigate CC incidence, healthcare providers can select the best approach to reach women eligible for CC screening.

Cric searchable image database as a public platform for conventional pap smear cytology data.

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.

Cervical cancer: Automation of Pap test screening.

BACKGROUND: Cervical cancer progresses slowly, increasing the chance of early detection of pre-neoplastic lesions via Pap exam test and subsequently preventing deaths. However, the exam presents both false-negatives and false-positives results. Therefore, automatic methods (AMs) of reading the Pap test have been used to improve the quality control of the exam. We performed a literature review to evaluate the feasibility of implementing AMs in laboratories. METHODS: This work reviewed scientific publications regarding automated cytology from the last 15 years. The terms used were "Papanicolaou test" and "Automated cytology screening" in Portuguese, English, and Spanish, in the three scientific databases (SCIELO, PUBMED, MEDLINE). RESULTS: Of the resulting 787 articles, 34 were selected for a complete review, including three AMs: ThinPrep Imaging System, FocalPoint GS Imaging System and CytoProcessor. In total, 1 317 148 cytopathological slides were evaluated automatically, with 1 308 028 (99.3%) liquid-based cytology slides and 9120 (0.7%) conventional cytology smears. The AM diagnostic performances were statistically equal to or better than those of the manual method. AM use increased the detection of cellular abnormalities and reduced false-negatives. The average sample rejection rate was ≤3.5%. CONCLUSION: AMs are relevant in quality control during the analytical phase of cervical cancer screening. This technology eliminates slide-handling steps and reduces the sample space, allowing professionals to focus on diagnostic interpretation while maintaining high-level care, which can reduce false-negatives. Further studies with conventional cytology are needed. The use of AM is still not so widespread in cytopathology laboratories.

Saliency-driven system models for cell analysis with deep learning.

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 investigate the impact of bottom-up and top-down factors on saliency prediction from real routine exams. By combining the eye tracking data from pathologists with computed saliency models, we assess algorithms reliability in identifying clinically relevant cells. RESULTS: The proposed cell-specific CNN model outperforms all other saliency prediction methods, particularly regarding the number of false positives. Our algorithm also detects the most clinically relevant cells, which are among the three top salient regions, with accuracy above 98% for all diseases, except carcinoma (87%). Bottom-up methods performed satisfactorily, with saliency maps that enabled ROI detection above 75% for carcinoma and 86% for other pathologies. CONCLUSIONS: ROIs extraction using our saliency prediction methods enabled ranking the most relevant clinical areas within the image, a viable data reduction strategy to guide automatic analyses of Pap smear slides. Top-down factors for saliency prediction on cell images increases the accuracy of the estimated maps while bottom-up algorithms proved to be useful for predicting the cytopathologist's eye fixations depending on parameters, such as the number of false positive and negative. Our contributions are: comparison among 13 state-of-the-art saliency models to cytopathologists' visual attention and deliver a method that the associate the most conspicuous regions to clinically relevant cells.

Deep learning for cell image segmentation and ranking.

Ninety years after its invention, the Pap test continues to be the most used method for the early identification of cervical precancerous lesions. In this test, the cytopathologists look for microscopic abnormalities in and around the cells, which is a time-consuming and prone to human error task. This paper introduces computational tools for cytological analysis that incorporate cell segmentation deep learning techniques. These techniques are capable of processing both free-lying and clumps of abnormal cells with a high overlapping rate from digitized images of conventional Pap smears. Our methodology employs a preprocessing step that discards images with a low probability of containing abnormal cells without prior segmentation and, therefore, performs faster when compared with the existing methods. Also, it ranks outputs based on the likelihood of the images to contain abnormal cells. We evaluate our methodology on an image database of conventional Pap smears from real scenarios, with 108 fields-of-view containing at least one abnormal cell and 86 containing only normal cells, corresponding to millions of cells. Our results show that the proposed approach achieves accurate results (MAP = 0.936), runs faster than existing methods, and it is robust to the presence of white blood cells, and other contaminants.