arXiv subjects

Hyungsoon Im

Publications and source records attributed to Hyungsoon Im.

3 recordsLinked to original sources

arXiv2023

Molecular fingerprinting of biological nanoparticles with a label-free optofluidic platform

Label-free detecting multiple analytes in a high-throughput fashion has been one of the long-sought goals in biosensing applications. Yet, for all-optical approaches, interfacing state-of-the-art label-free techniques with microfluidics tools that can process small volumes of sample with high throughput, and with surface chemistry that grants analyte specificity, poses a critical challenge to date. Here, we introduce an optofluidic platform that brings together state-of-the-art digital holography with PDMS microfluidics by using supported lipid bilayers as a surface chemistry building block to integrate both technologies. Specifically, this platform fingerprints heterogeneous biological nanoparticle populations via a multiplexed label-free immunoaffinity assay with single particle sensitivity. Herein, we first thoroughly characterise the robustness and performance of the platform, and then apply it to profile four distinct ovarian cell-derived extracellular vesicle populations over a panel of surface protein biomarkers, thus developing a unique biomarker fingerprint for each cell line. We foresee that our approach will find many applications where routine and multiplexed characterisation of biological nanoparticles is required.

q-bio.QM↗

arXiv2022

Adversarial confound regression and uncertainty measurements to classify heterogeneous clinical MRI in Mass General Brigham

Automated disease detection in neuroimaging holds promise to improve the diagnostic ability of radiologists, but routinely collected clinical data frequently contains technical and demographic confounding factors that cause data to both differ between sites and be systematically associated with the disease of interest, thus negatively affecting the robustness of diagnostic models. There is a critical need for diagnostic deep learning models that can train on such imbalanced datasets without being influenced by these confounds. In this work, we introduce a novel deep learning architecture, MUCRAN (Multi-Confound Regression Adversarial Network), to train a deep learning model on clinical brain MRI while regressing demographic and technical confounding factors. We trained MUCRAN using 17,076 clinical T1 Axial brain MRIs collected from Massachusetts General Hospital before 2019 and demonstrated that MUCRAN could successfully regress major confounding factors in the vast clinical data. We also applied a method for quantifying uncertainty across an ensemble of these models to automatically exclude out-of-distribution data in the AD detection. By combining MUCRAN and the uncertainty quantification method, we showed consistent and significant increases in the AD detection accuracy for newly collected MGH data (post-2019) and for data from other hospitals. MUCRAN offers a generalizable approach for heterogenous clinical data for deep-learning-based automatic disease detection.

cs.LG↗

arXiv2019

Evolution Strategies Converges to Finite Differences

Since the debut of Evolution Strategies (ES) as a tool for Reinforcement Learning by Salimans et al. 2017, there has been interest in determining the exact relationship between the Evolution Strategies gradient and the gradient of a similar class of algorithms, Finite Differences (FD).(Zhang et al. 2017, Lehman et al. 2018) Several investigations into the subject have been performed, investigating the formal motivational differences(Lehman et al. 2018) between ES and FD, as well as the differences in a standard benchmark problem in Machine Learning, the MNIST classification problem(Zhang et al. 2017). This paper proves that while the gradients are different, they converge as the dimension of the vector under optimization increases.

cs.NE↗