Convolutional neural networks for segmentation and object detection of human semen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

We compare a set of convolutional neural network (CNN) architectures for the task of segmenting and detecting human sperm cells in an image taken from a semen sample. In contrast to previous work, samples are not stained or washed to allow for full sperm quality analysis, making analysis harder due to clutter. Our results indicate that training on full images is superior to training on patches when class-skew is properly handled. Full image training including up-sampling during training proves to be beneficial in deep CNNs for pixel wise accuracy and detection performance. Predicted sperm cells are found by using connected components on the CNN predictions. We investigate optimization of a threshold parameter on the size of detected components. Our best network achieves 93.87% precision and 91.89% recall on our test dataset after thresholding outperforming a classical image analysis approach.

Original languageEnglish
Title of host publicationImage Analysis : 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, June 12–14, 2017, Proceedings, Part I
EditorsPuneet Sharma, Filippo Maria Bianchi
Number of pages10
VolumePart 1
Publication date2017
ISBN (Print)978-3-319-59125-4
ISBN (Electronic)978-3-319-59126-1
Publication statusPublished - 2017
Event20th Scandinavian Conference on Image Analysis - Tromsø, Norway
Duration: 12 Jun 201714 Jun 2017
Conference number: 20


Conference20th Scandinavian Conference on Image Analysis
SeriesLecture notes in computer science

    Research areas

  • Convolutional neural networks, Deep learning, Fertility examination, Human sperm, Segmentation


ID: 184142886