Active Learning Enabled Low-cost Cell Image Segmentation Using Bounding Box Annotation

TL;DR

This paper introduces an active learning framework that uses bounding box annotations combined with a novel model to significantly reduce data annotation costs in cell image segmentation.

Contribution

It presents a new box-supervised learning method (YOLO-SAM) integrated into an active learning framework to minimize annotation effort.

Findings

Reduces annotation time by over 90% compared to traditional methods.

Effectively combines YOLOv8 and SAM for box-supervised segmentation.

Uses MC DropBlock to train with fewer annotated samples.

Abstract

Cell image segmentation is usually implemented using fully supervised deep learning methods, which heavily rely on extensive annotated training data. Yet, due to the complexity of cell morphology and the requirement for specialized knowledge, pixel-level annotation of cell images has become a highly labor-intensive task. To address the above problems, we propose an active learning framework for cell segmentation using bounding box annotations, which greatly reduces the data annotation cost of cell segmentation algorithms. First, we generate a box-supervised learning method (denoted as YOLO-SAM) by combining the YOLOv8 detector with the Segment Anything Model (SAM), which effectively reduces the complexity of data annotation. Furthermore, it is integrated into an active learning framework that employs the MC DropBlock method to train the segmentation model with fewer box-annotated samples. Extensive experiments demonstrate that our model saves more than ninety percent of data annotation time compared to mask-supervised deep learning methods.