Statistical Bioinformatics Seminar: Lin and Fu

Title: Biologically-informed deep learning for segmentation of subcellular spatial
transcriptomics data 

Speakers: Dr Xiaohang Fu and Dr Yingxin Lin (University of Sydney) 

Abstract: Recent advances in subcellular imaging transcriptomics platforms have enabled
high-resolution spatial mapping of gene expression, while also introducing significant
analytical challenges in accurately identifying cells and assigning transcripts.
Existing methods grapple with cell segmentation, frequently leading to fragmented cells
or oversized cells that capture contaminated expression.  To this end, we present
BIDCell, a data-driven strategy that maximises the utilisation of relevant information,
including single-cell transcriptomics data from public repositories.  BIDCell leverages
a self-supervised deep learning framework that innovatively incorporates cell type and
morphology data through biologically-informed loss functions.  Utilising a comprehensive
evaluation framework consisting of metrics in five complementary categories for cell
segmentation performance, we demonstrate that BIDCell outperforms other state-of-the-art
methods according to many metrics across a variety of tissue types and technology
platforms.  Our findings underscore the potential of BIDCell to significantly enhance
single-cell spatial expression analyses, including cell-cell interactions, enabling
great potential in biological discovery.  

About the speakers: 

Xiaohang Fu received her PhD in Computer Science from The University of Sydney in 2023
and her Bachelor of Engineering (Honors) specializing in Biomedical Engineering with
First Class Honors in 2018 from The University of Auckland.  Currently, she is a
postdoctoral research fellow at the University of Sydney.  Her research interests
include deep learning, medical image classification, segmentation, and analysis.  

Yingxin Lin is a Postdoctoral research associate at the University of Sydney.  She
completed her PhD in Statistics at the University of Sydney in 2022 and her Bachelor of
Science (Honors) in Statistics in 2017 from The University of Sydney.  She is a member
of the School of Mathematics and Statistics and Sydney Precision Data Science Centre.
Her research interests lie broadly in statistical modelling and machine learning for
various omics, biomedical and clinical data.