Reimagining service delivery in the agentic era with Google Public Sector
cloud.google.com·21h ago
AI Research
arXiv CS.AI·Jun 9·5 min read
Comparative evaluation of training strategies using partially labelled datasets for segmentation of white matter hyperintensities and stroke lesions in FLAIR MRI
✦ Why It Matters
Engineers can apply these training strategies to improve deep learning models for medical image segmentation tasks.
Key Takeaways
- Explore pseudolabelling for training models with partially labelled datasets.
- Utilize the combined dataset of 2,052 MRI volumes for better training.
- Focus on improving segmentation accuracy for clinical applications.
- Consider the implications of automated tools for large-scale research.
How It Works
The study employed a deep learning model that utilized pseudolabelling, where the model generates labels for unannotated data based on its predictions. This approach allows the model to learn from both labelled and unlabelled data, effectively increasing the training dataset size and improving segmentation accuracy.