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/

Zendy Plus

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

Zendy Tools

Zendy Open

Cell detection in histopathology images is of great value in clinicalpractice. \textit{Convolutional neural networks} (CNNs) have been applied tocell detection to improve the detection accuracy, where cell annotations arerequired for network training. However, due to the variety and large number ofcells, complete annotations that include every cell of interest in the trainingimages can be challenging. Usually, incomplete annotations can be achieved,where positive labeling results are carefully examined to ensure theirreliability but there can be other positive instances, i.e., cells of interest,that are not included in the annotations. This annotation strategy leads to alack of knowledge about true negative samples. Most existing methods simplytreat instances that are not labeled as positive as truly negative duringnetwork training, which can adversely affect the network performance. In thiswork, to address the problem of incomplete annotations, we formulate thetraining of detection networks as a positive-unlabeled learning problem.Specifically, the classification loss in network training is revised to takeinto account incomplete annotations, where the terms corresponding to negativesamples are approximated with the true positive samples and the other samplesof which the labels are unknown. To evaluate the proposed method, experimentswere performed on a publicly available dataset for mitosis detection in breastcancer cells, and the experimental results show that our method improves theperformance of cell detection given incomplete annotations for training.

Positive-unlabeled Learning for Cell Detection in Histopathology Images with Incomplete Annotations