arXiv subjects

Christine Ho

Publications and source records attributed to Christine Ho.

3 recordsLinked to original sources

arXiv2024

Label-free subcellular 3D imaging of oocytes and embryos via reflection matrix microscopy

Non-invasive morphological assessment is the cornerstone of oocyte and embryo selection in assisted reproductive technology, yet clinical practice remains limited by two-dimensional, qualitative microscopy. While three-dimensional (3D) fluorescence imaging provides cellular insights, its inherent phototoxicity precludes routine clinical use. Conversely, existing label-free modalities fail to resolve subcellular structures in thick specimens due to two distinct physical barriers: large-scale refractive index heterogeneities, such as the cumulus cells surrounding oocytes, that induce severe aberrations; and short-scale fluctuations, primarily from cytoplasmic lipids, that generate a multiple scattering ``fog''. Here, we report an ultra-fast Reflection Matrix Imaging (RMI) platform designed to overcome these depth and resolution limits. By capturing the back-scattered electromagnetic field for a set of plane-wave illuminations at multiple wavelengths, we record a multi-spectral reflection matrix. From this matrix, we leverage digital adaptive focusing algorithms to computationally compensate for sample-induced aberrations while realigning forward multiple scattering trajectories with the single-scattering contribution. This approach enables label-free 3D visualization of oocytes and blastocysts with an unprecedented subcellular resolution of 300 nm throughout the entire specimen volume. We demonstrate the reliable identification of germinal vesicles and nuclear status in stages previously inaccessible to conventional optics, including imaging through dense cumulus cells. Our method provides a powerful, non-invasive tool for objective grading across all pre-implantation stages, potentially transforming decision-making in clinical IVF.

physics.optics↗

arXiv2022

Ranking hierarchical multi-label classification results with mLPRs

Hierarchical multi-label classification (HMC) has gained considerable attention in recent decades. A seminal line of HMC research addresses the problem in two stages: first, training individual classifiers for each class, then integrating these classifiers to provide a unified set of classification results across classes while respecting the given hierarchy. In this article, we focus on the less attended second-stage question while adhering to the given class hierarchy. This involves addressing a key challenge: how to manage the hierarchical constraint and account for statistical differences in the first-stage classifier scores across different classes to make classification decisions that are optimal under a justifiable criterion. To address this challenge, we introduce a new objective function, called CATCH, to ensure reasonable classification performance. To optimize this function, we propose a decision strategy built on a novel metric, the multidimensional Local Precision Rate (mLPR), which reflects the membership chance of an object in a class given all classifier scores and the class hierarchy. Particularly, we demonstrate that, under certain conditions, transforming the classifier scores into mLPRs and comparing mLPR values for all objects against all classes can, in theory, ensure the class hierarchy and maximize CATCH. In practice, we propose an algorithm HierRank to rank estimated mLPRs under the hierarchical constraint, leading to a ranking that maximizes an empirical version of CATCH. Our approach was evaluated on a synthetic dataset and two real datasets, exhibiting superior performance compared to several state-of-the-art methods in terms of improved decision accuracy.

cs.LG↗

arXiv2018

HierLPR: Decision making in hierarchical multi-label classification with local precision rates

In this article we propose a novel ranking algorithm, referred to as HierLPR, for the multi-label classification problem when the candidate labels follow a known hierarchical structure. HierLPR is motivated by a new metric called eAUC that we design to assess the ranking of classification decisions. This metric, associated with the hit curve and local precision rate, emphasizes the accuracy of the first calls. We show that HierLPR optimizes eAUC under the tree constraint and some light assumptions on the dependency between the nodes in the hierarchy. We also provide a strategy to make calls for each node based on the ordering produced by HierLPR, with the intent of controlling FDR or maximizing F-score. The performance of our proposed methods is demonstrated on synthetic datasets as well as a real example of disease diagnosis using NCBI GEO datasets. In these cases, HierLPR shows a favorable result over competing methods in the early part of the precision-recall curve.

stat.ML↗