RCNN-SliceNet: A Slice and Cluster Approach for Nuclei Centroid Detection in Three-Dimensional Fluorescence Microscopy Images

TL;DR

This paper introduces RCNN-SliceNet, a scalable 3D nuclei centroid detection method that combines 2D slice detection with hierarchical clustering, effectively addressing limitations of existing 3D microscopy analysis techniques.

Contribution

The paper presents a novel approach integrating 2D detection and 3D clustering for nuclei centroid detection in microscopy volumes, trained on synthetic data and effective on real data.

Findings

Accurately detects nuclei centroids in 3D microscopy images.

Effective on various real 3D microscopy datasets.

Addresses limitations of existing 2D and segmentation-based methods.

Abstract

Robust and accurate nuclei centroid detection is important for the understanding of biological structures in fluorescence microscopy images. Existing automated nuclei localization methods face three main challenges: (1) Most of object detection methods work only on 2D images and are difficult to extend to 3D volumes; (2) Segmentation-based models can be used on 3D volumes but it is computational expensive for large microscopy volumes and they have difficulty distinguishing different instances of objects; (3) Hand annotated ground truth is limited for 3D microscopy volumes. To address these issues, we present a scalable approach for nuclei centroid detection of 3D microscopy volumes. We describe the RCNN-SliceNet to detect 2D nuclei centroids for each slice of the volume from different directions and 3D agglomerative hierarchical clustering (AHC) is used to estimate the 3D centroids of nuclei in a volume. The model was trained with the synthetic microscopy data generated using Spatially Constrained Cycle-Consistent Adversarial Networks (SpCycleGAN) and tested on different types of real 3D microscopy data. Extensive experimental results demonstrate that our proposed method can accurately count and detect the nuclei centroids in a 3D microscopy volume.