A5025024029- Cutaneous Melanoma Detection and Management
- AI in cancer detection
- Gene expression and cancer classification
- Multiple Sclerosis Research Studies
- Mycobacterium research and diagnosis
- Digital Imaging for Blood Diseases
- Time Series Analysis and Forecasting
Cooperative Trials Group for Neuro-Oncology
2023-2024
The University of Sydney
2023
Accurately measuring the evolution of Multiple Sclerosis (MS) with magnetic resonance imaging (MRI) critically informs understanding disease progression and helps to direct therapeutic strategy. Deep learning models have shown promise for automatically segmenting MS lesions, but scarcity accurately annotated data hinders progress in this area. Obtaining sufficient from a single clinical site is challenging does not address heterogeneous need model robustness. Conversely, collection multiple...
Background and introduction Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative without sharing raw data. Despite great success, FL's applications remain suboptimal in neuroimage tasks such as lesion segmentation multiple sclerosis (MS), due variance characteristics imparted by different scanners acquisition parameters. Methods In this work, we propose the first FL MS framework via two effective re-weighting mechanisms....
Quantifying relationships between components of a complex system is critical to understanding the rich network interactions that characterize behavior system. Traditional methods for detecting pairwise dependence time series, such as Pearson correlation, Granger causality, and mutual information, are computed directly in space measured time-series values. But systems which mediated by statistical properties series (`time-series features') over longer timescales, this approach can fail...
Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative without sharing raw data. Despite great success, FL's performance is limited multiple sclerosis (MS) lesion segmentation tasks, due variance in characteristics imparted by different scanners and acquisition parameters. In this work, we propose the first FL MS framework via two effective re-weighting mechanisms. Specifically, a learnable weight assigned each local node during...
Accurately measuring the evolution of Multiple Sclerosis (MS) with magnetic resonance imaging (MRI) critically informs understanding disease progression and helps to direct therapeutic strategy. Deep learning models have shown promise for automatically segmenting MS lesions, but scarcity accurately annotated data hinders progress in this area. Obtaining sufficient from a single clinical site is challenging does not address heterogeneous need model robustness. Conversely, collection multiple...