The Faculty of Applied Science & Engineering Research Office announced the recipients of the 2023-2025 Joint EMHSeed & XSeed Funding Program.
Initiated in 2015, the Joint Seed Program is an interdivisional research funding program designed to promote multi-disciplinary research and catalyze new innovative partnerships between researchers from the Faculty of Applied Science & Engineering and those from outside of Engineering. The recipients for this year will undertake unique and innovative research initiatives ranging from surgical micro-robots to equitable healthcare and medical imaging.
Six Arts & Science faculty members were among the recipients.
A&S XSeed Winners
Constructing the Human Olfactory System Ex Vivo
Co-Applicants: Michael Garton (BME) & Ting Li (Astronomy & Astrophysics)
This research partnership will develop the first portable device that encapsulates the entire human olfactory system on a microfluidic chip. It will be integrated with a bio-machine interface that allows smell to be encoded electronically. These fluorescent-intensity channels can be connected to an artificial neural network with a multitude of potential applications, including, diagnosing Parkinson’s disease using smell.
Evaluating the Risk of Nanomedicines on Brain Function Using the Zebrafish Model
Co-Applicants: Kai Huang (MSE) & Qian Lin (Cell & Systems Biology)
Nanomedicine has emerged as a promising tool for the treatment of various diseases, including cancer and neurodegenerative diseases, yet the potential risks of these medicines on brain function remain poorly understood. This project will investigate the impact of nanomedicines on brain function using the zebrafish model. The results will provide valuable insights into the impact of nanomedicines on brain function and inform the development of safe nanomedicines for the treatment of neurological diseases.
The Open Quantum MOF Database
Co-Applicants: Mohamad Moosavi (ChemE) & Anatole von-Lilienfeld (Chemistry)
Metal-organic frameworks (MOFs) are porous crystalline materials with high chemical tunability that show promising performance for a wide range of sustainability applications, including carbon capture and hydrogen storage. However, the accuracy and success of these methods are tied to the availability of data. MOF properties have been computed using inexpensive, low-accuracy methods. This project aims to dramatically expand the range of available materials’ properties and enhance the accuracy of available data. This database will then be made publicly available through the Open Quantum MOF Database. This effort aims to enable AI-guided design and discovery of MOFs for a wide range of applications in the future.
Mechanical Stimulus-Triggered Controlled Release of RNA Nanoparticles from Implantable Polymeric Depots for Localized Treatments
Co-Applicants: Omar Khan (BME) & Helen Tran (Chemistry)
Movement-related chronic immunological conditions that cause inflammation and tissue degradation are an on-going and incurable condition often treated orally through medication, which is not as targeted or effective. This project combines anti-inflammatory mRNA nanoparticles and stimuli-responsive polymers to create injectable nanoparticle depots that treat inflammation directly in the joint.
Towards Home Monitoring of Heart Failure Patients Via Robust and Unbiased Spatial Frequency Domain Imaging
Co-Applicants: Ofer Levi (BME) & David Lindell (Computer Science)
Structured light imaging is a powerful tool but fails to account for differences in skin pigmentation, resulting in a significant bias for darker-skinned patients. Among the relevant techniques, spatial frequency domain imaging (SFDI) has become popular. This project addresses these limitations by developing a differentiable, end-to-end model of light transport in structured light imaging systems. Combining this model with machine learning techniques will allow learning illumination patterns to minimize reconstruction error. This model will capture variations in skin pigmentation vs. tissue depth, mitigating bias in reconstruction accuracy. This will significantly improve the quantitative accuracy and equity of SDFI systems, resulting in a viable tool for non-contact evaluation of tissue oxygenation and physiology changes in heart patients.
Regulating the AI Lifecycle: A Multidisciplinary Perspective
Co-Applicants: Shurui Zhou (ECE) & Boris Babic (Philosophy and Statistical Sciences)
This project hopes to gain a better understanding of how to design the needed regulatory infrastructure for machine learning-based medical products through empirical and field experiments with industry partners and qualitative studies with a broad range of stakeholders developing medical machine learning products. This will shed insight on future research directions in this interdisciplinary area of medical AI regulation.