A 2.5D Cascaded Convolutional Neural Network with Temporal Information for Automatic Mitotic Cell Detection in 4D Microscopic Images

TL;DR

This paper introduces CasDetNet, a 2.5D cascaded CNN that leverages temporal data to improve automatic detection of mitotic cells in 4D microscopic images, reducing false positives and increasing accuracy.

Contribution

The paper presents a novel 2.5D cascaded neural network that effectively incorporates temporal information for mitotic cell detection in 4D images with limited training data.

Findings

Higher precision and recall than existing methods

Effective reduction of false positives

Accurate detection with limited training data

Abstract

In recent years, intravital skin imaging has been increasingly used in mammalian skin research to investigate cell behaviors. A fundamental step of the investigation is mitotic cell (cell division) detection. Because of the complex backgrounds (normal cells), the majority of the existing methods cause several false positives. In this paper, we proposed a 2.5D cascaded end-to-end convolutional neural network (CasDetNet) with temporal information to accurately detect automatic mitotic cell in 4D microscopic images with few training data. The CasDetNet consists of two 2.5D networks. The first one is used for detecting candidate cells with only volume information and the second one, containing temporal information, for reducing false positive and adding mitotic cells that were missed in the first step. The experimental results show that our CasDetNet can achieve higher precision and recall compared to other state-of-the-art methods.