Master Assignment
[B] Temporal Surgical Video Segmentation for Medical Dataset Curation
Type: Master EE/CS/HMI
Period: TBD
Student: (Unassigned)
If you are interested, please contact :
Project Background:
As the use of AI in healthcare grows, high-quality, well-curated datasets are essential for developing reliable models. In particular, surgical video datasets provide invaluable insights for training AI systems to understand surgical procedures. However, manually segmenting these long, complex videos is time-consuming and prone to errors, making it a prime candidate for automation using machine learning.
Project Overview:
- Develop temporal segmentation models for surgical videos to automatically identify key surgery phases.
- Focus on curating medical datasets, enabling more accurate and efficient AI-driven analysis.
- Apply deep learning and time-series analysis techniques to handle the complexities of surgical video data.
Why Join?
- Be part of a high-impact project that has the potential to improve patient care through better AI models.
- Work at the intersection of machine learning, computer vision, and healthcare, gaining valuable experience in medical AI applications.
- Collaborate with a team of interdisciplinary experts and contribute to real-world solutions in the medical technology field.
Who Should Apply?
- Students with a strong background in machine learning and computer vision.
- Those interested in applying their skills to medical applications.
- Enthusiasts of AI for healthcare, seeking to make a tangible impact in medical research and patient outcomes.