GRED: Graph-Regularized 3D Shape Reconstruction from Highly Anisotropic and Noisy Images
This addresses the bottleneck of time-consuming manual segmentation in large-scale biological experiments, but appears incremental as it builds on existing techniques.
The paper tackles automated segmentation of cell nuclei from highly anisotropic and noisy 3D microscopy images, showing that the tool is as accurate as manual annotation and greatly reduces registration time.
Analysis of microscopy images can provide insight into many biological processes. One particularly challenging problem is cell nuclear segmentation in highly anisotropic and noisy 3D image data. Manually localizing and segmenting each and every cell nuclei is very time consuming, which remains a bottleneck in large scale biological experiments. In this work we present a tool for automated segmentation of cell nuclei from 3D fluorescent microscopic data. Our tool is based on state-of-the-art image processing and machine learning techniques and supports a friendly graphical user interface (GUI). We show that our tool is as accurate as manual annotation but greatly reduces the time for the registration.