Enhancing Cell Segmentation in human cellular Using Weak Learning Techniques
by Hassan Eshkiki| Departments | Computer Science |
|---|---|
| Description | This project aims to develop and apply weak learning techniques to improve cell segmentation in human cellular networks. This research will focus on leveraging weak learning to enhance the accuracy and efficiency of cell segmentation algorithms. The project will utilize image data from complex cellular networks, which are challenging to segment using conventional methods. By integrating weak learning approaches, we aim to create robust segmentation pipelines that can accurately identify and quantify individual cells within these networks. You will be require implement the developed algorithms in real-world biological research, focusing on applications such as disease modeling and drug discovery. Collaborate with biomedical researchers to validate the effectiveness of the proposed methods. This project aligns with ongoing advancements in AI and biomedical research, contributing to future funding opportunities and interdisciplinary collaborations. The outcomes will support high-impact publications and foster partnerships with industry leaders in AI and healthcare. |
| Preparation | Caraffini, Fabio, Hassan Eshkiki, Mostafa Mohammadpour, Nikol Sullo, and Christopher George. "Towards Improving Single-Cell Segmentation In Heterogeneous Configurations Of Cardiomyocyte Networks." Lecture Notes in Computer Science 2024: 104-117. Wills JW, Robertson J, Tourlomousis P, Gillis CMC, Barnes CM, Miniter M, Hewitt RE, Bryant CE, Summers HD, Powell JJ, Rees P. Label-free cell segmentation of diverse lymphoid tissues in 2D and 3D. Cell Rep Methods. 2023 Feb 2;3(2):100398. doi: 10.1016/j.crmeth.2023.100398. PMID: 36936072; PMCID: PMC10014308. |
| Project Categories | Artificial Intelligence (AI) |
| Project Keywords | Computer Vision, Machine Learning |
| |
| Level 6 (Undergraduate Year 3) | yes |
| Level 7 (Masters) | yes |
| Level 8 (PhD) | yes |