Started My FYP - Estimation of ECM Signatures in Fiber Probe Images

I have commenced my Final Year Research Project, focusing on a novel deep learning framework to automate Extracellular Matrix (ECM) quantification from noisy fiber probe imagery.

Project Overview

While Second Harmonic Generation (SHG) imaging is the gold standard for analyzing collagen, traditional table-top microscopes are restricted to ex-vivo analysis. To enable in-vivo assessment, our research addresses the significant domain shift and degraded image quality inherent to fiber-optic probes.

My Contribution

I am leading the development of a CycleGAN-based domain adaptation pipeline for unpaired image-to-image translation. My work focuses on:

Cross-modality registration between high-fidelity microscopy and fiber probe domains
Surrogate modeling to bridge the gap between different imaging modalities
Accurate prediction of collagen Directional Variance (DV) from degraded fiber probe images

Research Significance

This project aims to revolutionize in-vivo collagen analysis by making high-quality ECM quantification possible with portable fiber-optic probes, potentially transforming clinical diagnostics and tissue assessment procedures.

Supervision Team

I’m fortunate to work under the guidance of an exceptional supervision team:

Dr. Chamira Edussooriya (University of Moratuwa, Sri Lanka)
Dr. Ranga Rodrigo (University of Moratuwa, Sri Lanka)
Dr. Dushan Wadduwage (Old Dominion University, USA)
Dr. Einstein Gnanatheepam (Tufts University, USA)

Bridging the gap between laboratory-grade microscopy and portable clinical imaging through advanced deep learning techniques.

Excited to contribute to the advancement of biomedical imaging and AI applications in healthcare!