K. W. Dunn

The paper provides 3D microscopy volumes with partial manual annotations and synthetically generated volumes for training segmentation methods.

This paper introduces a 3D nuclei centroid detection method using vector flow voting, achieving better performance than existing methods on real microscopy data.

NISNet3D is a deep learning model for 3D nuclear segmentation in fluorescence microscopy images, trained on synthetic data and compared to eight existing methods.

DINAVID provides a cloud-based system for remote 3D microscopy image analysis and visualization, designed to handle large datasets and improve accessibility.

This paper introduces EMR-CNN, a 3D nuclei segmentation method that avoids ground truth annotations and uses ensemble learning and slice fusion for efficient and accurate results.

The paper introduces VTEA, a software tool that integrates machine learning and cytometry analysis for high-content imaging of human kidney tissue to classify cells and analyze their spatial neighborhoods.

The paper describes a pipeline for generating 3D molecular atlases of human kidney biopsies using multi-OMICS and imaging technologies, emphasizing quality control and reproducibility across institutions.

This paper develops a deep learning method using 3D nuclear staining to classify cell types in human kidney tissue without requiring specific markers.

The paper demonstrates PIE-FLIM for simultaneous measurement of two FRET-based biosensor activities in living cells.

This study uses intravital imaging of biosensor-labeled beta cells to monitor ROS dynamics in vivo during diabetes-related stress.