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

arXiv: https://arxiv.org/abs/2405.01701 · HTML: https://mlsanity.com/paper/2405.01701/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 5 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 2 of 2)

- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Breaking the Barrier: Selective Uncertainty-based Active Learning for Medical Image Segmentation](https://mlsanity.com/paper/2401.16298/) (2024)

## Built on by (most cited first, 3 of 3)

- [Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2](https://mlsanity.com/paper/2408.06970/) (2024)
- [CellMamba: Adaptive Mamba for Accurate and Efficient Cell Detection](https://mlsanity.com/paper/2512.21803/) (2025)
- [End-to-End Cell Detection via Instance-aware Graph Modeling](https://mlsanity.com/paper/2609.15354/) (2026)

## Abstract (arXiv)

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.