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

We compare a set of convolutional neural network (CNN) architectures for thetask of segmenting and detecting human sperm cells in an image taken from asemen sample. In contrast to previous work, samples are not stained or washedto allow for full sperm quality analysis, making analysis harder due toclutter. Our results indicate that training on full images is superior totraining on patches when class-skew is properly handled. Full image trainingincluding up-sampling during training proves to be beneficial in deep CNNs forpixel wise accuracy and detection performance. Predicted sperm cells are foundby using connected components on the CNN predictions. We investigateoptimization of a threshold parameter on the size of detected components. Ourbest network achieves 93.87% precision and 91.89% recall on our test datasetafter thresholding outperforming a classical mage analysis approach.

Convolutional neural networks for segmentation and object detection of human semen