arXiv subjects

Lauren O'Donnell

Publications and source records attributed to Lauren O'Donnell.

5 recordsLinked to original sources

arXiv2026

Multinuclear fingerprinting

We developed a new magnetic resonance imaging method called multinuclear fingerprinting (MNF) which leverages simultaneously-acquired proton (1H) and sodium (23Na) data to generate seven quantitative maps of the whole brain: proton density (PD), T1 and T2 relaxation times from water, and tissue sodium concentration (TSC), T1, T2short and T2long from Na+ ions. MNF consists of two parts: (1) simultaneous 1H/23Na magnetic resonance fingerprinting (MRF), and (2) a super-resolution (SR) algorithm to increase the 23Na resolution to match the 1H resolution. It was tested on the brain of seven healthy subjects at 7 T, with a final resolution of 1.5x1.5x5 mm3 for all maps acquired in 13 min. MNF could provide new fundamental insights into the inter-relationship between morphology (i.e. tissue structure from the 1H maps) and physiology (i.e. ion homeostasis from the 23Na maps) in vivo to help improve our understanding of the human brain in general, and to study neuropathologies and their treatments. Since all 1H/23Na MRF data is acquired simultaneously, all images are exactly co-registered with identical spatial and temporal resolutions. MNF could be useful in future longitudinal studies for assessing local time-dependent and conjoint 1H/23Na MR changes during tasks or interventions. MNF was initially developed for neuroimaging, but it can be adapted to any other parts of the body.

physics.med-ph↗

arXiv2022

DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis

We present a novel weakly-supervised framework for classifying whole slide images (WSIs). WSIs, due to their gigapixel resolution, are commonly processed by patch-wise classification with patch-level labels. However, patch-level labels require precise annotations, which is expensive and usually unavailable on clinical data. With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label. To address this issue, we posit that WSI analysis can be effectively conducted by integrating information at both high magnification (local) and low magnification (regional) levels. We auto-encode the visual signals in each patch into a latent embedding vector representing local information, and down-sample the raw WSI to hardware-acceptable thumbnails representing regional information. The WSI label is then predicted with a Dual-Stream Network (DSNet), which takes the transformed local patch embeddings and multi-scale thumbnail images as inputs and can be trained by the image-level label only. Experiments conducted on two large-scale public datasets demonstrate that our method outperforms all recent state-of-the-art weakly-supervised WSI classification methods.

cs.CV↗

arXiv2021

CellTrack R-CNN: A Novel End-To-End Deep Neural Network for Cell Segmentation and Tracking in Microscopy Images

Cell segmentation and tracking in microscopy images are of great significance to new discoveries in biology and medicine. In this study, we propose a novel approach to combine cell segmentation and cell tracking into a unified end-to-end deep learning based framework, where cell detection and segmentation are performed with a current instance segmentation pipeline and cell tracking is implemented by integrating Siamese Network with the pipeline. Besides, tracking performance is improved by incorporating spatial information into the network and fusing spatial and visual prediction. Our approach was evaluated on the DeepCell benchmark dataset. Despite being simple and efficient, our method outperforms state-of-the-art algorithms in terms of both cell segmentation and cell tracking accuracies.

cs.CV↗

arXiv2020

Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting

Unsupervised domain adaptation (UDA) for nuclei instance segmentation is important for digital pathology, as it alleviates the burden of labor-intensive annotation and domain shift across datasets. In this work, we propose a Cycle Consistency Panoptic Domain Adaptive Mask R-CNN (CyC-PDAM) architecture for unsupervised nuclei segmentation in histopathology images, by learning from fluorescence microscopy images. More specifically, we first propose a nuclei inpainting mechanism to remove the auxiliary generated objects in the synthesized images. Secondly, a semantic branch with a domain discriminator is designed to achieve panoptic-level domain adaptation. Thirdly, in order to avoid the influence of the source-biased features, we propose a task re-weighting mechanism to dynamically add trade-off weights for the task-specific loss functions. Experimental results on three datasets indicate that our proposed method outperforms state-of-the-art UDA methods significantly, and demonstrates a similar performance as fully supervised methods.

cs.CV↗

arXiv2020

TRAKO: Efficient Transmission of Tractography Data for Visualization

Fiber tracking produces large tractography datasets that are tens of gigabytes in size consisting of millions of streamlines. Such vast amounts of data require formats that allow for efficient storage, transfer, and visualization. We present TRAKO, a new data format based on the Graphics Layer Transmission Format (glTF) that enables immediate graphical and hardware-accelerated processing. We integrate a state-of-the-art compression technique for vertices, streamlines, and attached scalar and property data. We then compare TRAKO to existing tractography storage methods and provide a detailed evaluation on eight datasets. TRAKO can achieve data reductions of over 28x without loss of statistical significance when used to replicate analysis from previously published studies.

eess.IV↗