Three Dimensional Fluorescence Microscopy Image Synthesis and Segmentation

TL;DR

This paper presents a novel 3D deep learning nuclei segmentation approach that uses synthetically generated volumes for training, overcoming the challenge of manual annotation in large microscopy datasets.

Contribution

It introduces a synthetic data generation method using cycle-consistent adversarial networks for effective 3D nuclei segmentation in fluorescence microscopy images.

Findings

Successful segmentation of nuclei across various datasets

Synthetic training data improves deep learning segmentation performance

Demonstrates feasibility of using synthetic data for 3D microscopy analysis

Abstract

Advances in fluorescence microscopy enable acquisition of 3D image volumes with better image quality and deeper penetration into tissue. Segmentation is a required step to characterize and analyze biological structures in the images and recent 3D segmentation using deep learning has achieved promising results. One issue is that deep learning techniques require a large set of groundtruth data which is impractical to annotate manually for large 3D microscopy volumes. This paper describes a 3D deep learning nuclei segmentation method using synthetic 3D volumes for training. A set of synthetic volumes and the corresponding groundtruth are generated using spatially constrained cycle-consistent adversarial networks. Segmentation results demonstrate that our proposed method is capable of segmenting nuclei successfully for various data sets.