Computer-Assisted Sperm Analysis (CASA) using Deep Learning
In this project, students will be assigned to develop deep-learning solutions to analyze sperm videos.
Master
Computer-assisted reproductive health and discovering new and clever ways of analyzing multimodal sperm datasets is a popular research direction to overcome time-consuming, costly, and subjective manual sperm analysis. In addition to good analysis performance, the efficiency of the algorithms is an essential fact in this domain because artificial reproduction is performed in real-time and therefore requires real-time feedback. Some sub-projects are listed below.
Analyzing sperm samples (VISEM, VISEM-tracking dataset) using DL
Simulating sperm motility and morphology using synthetic data
Goal
- Analyze sperm samples (VISEM, VISEM-tracking dataset) using DL
- Simulate sperm motility and morphology using synthetic data
Learning outcome
- Interdisciplinary research
- Machine learning / AI
- Performing research with advanced deep learning algorithms and real-world applications
Qualifications
- Hard-working
- Motivated
- Interested in learning (the rest can be learned during the thesis work)
Supervisors
- Pål Halvorsen
- Michael Riegler
- Vajira Thambawita
- Steven Hicks
References
- VISEM-Tracking - Dataset for tracking human sperms
- Machine Learning-Based Analysis of Sperm Videos and Participant Data for Male Fertility Prediction
- Extracting temporal features into a spatial domain using autoencoders for sperm video analysis
- Stacked dense optical flows and dropout layers to predict sperm motility and morphology
