A5024596558- Phonocardiography and Auscultation Techniques
- ECG Monitoring and Analysis
- Immunotherapy and Immune Responses
- Image Processing Techniques and Applications
- Single-cell and spatial transcriptomics
- EEG and Brain-Computer Interfaces
- Cell Image Analysis Techniques
- CAR-T cell therapy research
- Heart Rate Variability and Autonomic Control
- Advanced Fluorescence Microscopy Techniques
Stanford University
2021-2023
University of California, Berkeley
2019
The immune phenotype of a tumour is key predictor its response to immunotherapy1-4. Patients who respond checkpoint blockade generally present with immune-inflamed5-7 tumours that are highly infiltrated by T cells. However, not all inflamed therapy, and even lower rates occur among lack cells (immune desert) or spatially exclude the periphery lesion excluded)8. Despite importance these phenotypes in patients, little known about their development, heterogeneity dynamics owing technical...
We propose 3KG, a physiologically-inspired contrastive learning approach that generates views using 3D augmentations of the 12-lead electrocardiogram. evaluate representation quality by fine-tuning linear layer for downstream task 23-class diagnosis on PhysioNet 2020 challenge training data and find 3KG achieves $9.1\%$ increase in mean AUC over best self-supervised baseline when trained $1\%$ labeled data. Our empirical analysis shows combining spatial temporal produces strongest...
Recent advances in fluorescence imaging technology such as adaptive optics lattice light-sheet microscopy (AO-LLSM) allow live of three dimensional (3D) tissues at super-resolution 4D (xyzt) seconds frame rates [1]. The resulting datasets contain novel biology but are higher and much larger (100s GB / 3D movie) than traditional (e.g. confocal) microscopy. New tools methods necessary to segment quantify these the library pyLattice [2]. Here we present pyLattice_deepLearning, an image...