English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automated detection of cervical cancer cells or cell clumps has the potentialto significantly reduce error rate and increase productivity in cervical cancerscreening. However, most traditional methods rely on the success of accuratecell segmentation and discriminative hand-crafted features extraction. Recentlythere are emerging deep learning-based methods which train convolutional neuralnetworks (CNN) to classify image patches, but they are computationallyexpensive. In this paper we propose an efficient CNN-based object detectionmethods for cervical cancer cells/clumps detection. Specifically, we utilizethe state-of-the-art two-stage object detection method, the Faster-RCNN withFeature Pyramid Network (FPN) as the baseline and propose a novel comparisondetector to deal with the limited data problem. The key idea is that classifythe proposals by comparing with the reference samples of each category inobject detection. In addition, we propose to learn the reference samples of thebackground from data instead of manually choosing them by some heuristic rules.Experimental results show that the proposed Comparison Detector yieldssignificant improvement on the small dataset, achieving a mean AveragePrecision (mAP) of 26.3% and an Average Recall (AR) of 35.7%, both improvingabout 20 points compared to the baseline. Moreover, Comparison Detectorimproved AR by 4.6 points and achieved marginally better performance in termsof mAP compared with baseline model when training on the medium dataset. Ourmethod is promising for the development of automation-assisted cervical cancerscreening systems. Code is available athttps://github.com/kuku-sichuan/ComparisonDetector.

Comparison-Based Convolutional Neural Networks for Cervical Cell/Clumps Detection in the Limited Data Scenario