View Proposal
-
Proposer
-
Marta Vallejo
-
Title
-
Advanced deep learning methods for virtual H&E staining with fluorescence lifetime imaging microscopy - In collaboration with University of Edinburgh
-
Goal
-
Gaining hands-on experience in AI for clinical practice. Work towards a publication if results are of enough quality
-
Description
- H&E staining, the “gold standard” for cancer detection and diagnosis, is a routine test in clinical cancer pathology. Previous work has shown that fluorescence lifetime microscopic images can be directly translated into virtual H&E staining with superior quality (Wang, 2024), allowing rapid and precise cancer diagnosis without requiring the conventional tissue staining procedure. This project aims to explore advanced deep-learning methods for optimal virtual H&E staining, which includes but is not limited to, vision transformers or diffusion models.
Wang, Q., Akram, A.R., Dorward, D.A., Talas, S., Monks, B., Thum, C., Hopgood, J.R., Javidi, M. and Vallejo, M., 2024. Deep learning-based virtual H& E staining from label-free autofluorescence lifetime images. npj Imaging, 2(1), p.17.
- Resources
-
Real clinical dataset
-
Background
-
Good programming skills. Knowledge of machine learning. Willingness to learn.
-
Url
-
-
Difficulty Level
-
High
-
Ethical Approval
-
Full
-
Number Of Students
-
2
-
Supervisor
-
Marta Vallejo
-
Keywords
-
deep learning, lung cancer
-
Degrees
-
Bachelor of Science in Computer Science
Master of Engineering in Software Engineering
Master of Science in Artificial Intelligence
Master of Science in Artificial Intelligence with SMI
Master of Science in Computing (2 Years)
Master of Science in Data Science
Master of Science in Software Engineering
Bachelor of Science in Computing Science
Bachelor of Science in Statistical Data Science