TUMCREATE is a multidisciplinary research platform of the Technical University Munich (TUM) at the Singapore Campus for Research Excellence and Technological Enterprise (CREATE). We are joining forces with universities, public agencies, and industry for the advancement of future technologies. Please visit www.tum-create.edu.sg for more information about TUMCREATE.
The CellFACE project is funded by Singapore’s National Research Foundation (NRF). The aims are to establish imaging flow cytometry as a label-free platform technology for routine cellular diagnostics at the point-of-care. To assure success of the interdisciplinary CellFACE project, back-to-back teams between Munich and Singapore are formed. Using co-creational principles engineers and life scientists at TUMCREATE, NTU, and A*STAR cooperate with clinicians at National University Hospital to develop a workflow solution for blood cell analysis to improve acute care diagnostics. Please visit https://www.tum-create.edu.sg/research/cellface for more information about CellFACE.
Project: Study on the Quality Control of Quantitative Phase-Imaging Flow Cytometry Workflows for Acute Care Diagnostics
We seek 2 Master’s students to join our team at TUMCREATE in Singapore, working on the next generation of AI-supported high-throughput blood cell analysis. You will be responsible for integrating a Quality Control (QC) module into our new quantitative phase image processing pipeline. The pipeline aims to introduce real-time analysis, standardize and automate the microscopy & microfluidic framework, and optimize data processing using AI-based reconstruction and object detection models.
Integrate the Quality Control (QC) module into the image processing pipeline to achieve full automation and ensure repeatability of measurements.
Handle blood samples and prepare QC materials, such as sphered and fixed erythrocytes with known morphological and optical features, for conducting QC tests on DHM.
Collaborate with Singaporean industry, clinicians, and engineers to design and implement the QC module, ensuring precise adjustment of the optical focusing plane and checking for any variability in the optical setup and flow characteristics.
Support data annotation for training deep neural networks in reconstruction and object detection models.
Collaborate with the team to optimize the AI-based reconstruction and object detection models for accurate and efficient analysis.
Developing and maintaining Python scripts for data processing, analysis, and integration of the QC module into the pipeline is highly preferred.
Assist in troubleshooting and resolving technical issues related to the pipeline and QC module.
Currently enrolled Master’s students with a Bachelor degree in Computer Science, Electrical Engineering, Biomedical Engineering, or a related field.
Experience in working with image processing pipelines.
BSL-2 lab experience and knowledge of handling blood samples and preparing and testing QC materials.
Strong programming skills in Python and familiarity with relevant libraries and frameworks with an understanding of neural networks and deep learning frameworks are highly preferred.
Proficiency in data annotation and working with large datasets for training deep neural networks.
Solid understanding of image processing algorithms, object detection, and reconstruction techniques.
Ability to collaborate effectively in a team environment, communicate complex ideas clearly, and adapt to changing project requirements.
Experience with version control systems (e.g., Git) and agile development methodologies is a plus.
What TUM CREATE offers you
Intern monthly stipend
Subsidised international travel insurance
Support for work pass fees
A good amount of leave/vacation days
Vibrant, modern, and positive working environment in Singapore
Campus-sited office location with a host of facilities
In-building perks include a gym, game room, and coffee room
Please send your application with CV to Prof. Oliver Hayden (firstname.lastname@example.org) & Kerem Delikoyun (email@example.com)