Semi-supervised Cell Detection in Time-lapse Images Using Temporal Consistency

TL;DR

This paper introduces a semi-supervised approach for cell detection in time-lapse microscopy images that leverages temporal consistency and tracking to reduce annotation effort while maintaining high accuracy.

Contribution

It presents a novel semi-supervised method that uses tracking and pseudo-labeling to improve cell detection with minimal labeled data.

Findings

Achieved superior results compared to other semi-supervised methods.

Effective in seven different public dataset conditions.

Reduces annotation requirements significantly.

Abstract

Cell detection is the task of detecting the approximate positions of cell centroids from microscopy images. Recently, convolutional neural network-based approaches have achieved promising performance. However, these methods require a certain amount of annotation for each imaging condition. This annotation is a time-consuming and labor-intensive task. To overcome this problem, we propose a semi-supervised cell-detection method that effectively uses a time-lapse sequence with one labeled image and the other images unlabeled. First, we train a cell-detection network with a one-labeled image and estimate the unlabeled images with the trained network. We then select high-confidence positions from the estimations by tracking the detected cells from the labeled frame to those far from it. Next, we generate pseudo-labels from the tracking results and train the network by using pseudo-labels. We evaluated our method for seven conditions of public datasets, and we achieved the best results relative to other semi-supervised methods. Our code is available at https://github.com/naivete5656/SCDTC