arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.01410cs.CVq-bio.QM
收藏

CellSeg1:使用一张训练图像实现鲁棒细胞分割

CellSeg1: Robust Cell Segmentation with One Training Image

School of Computer Science, Wuhan University(武汉大学计算机学院)

Peilin Zhou, Bo Du, Yongchao Xu

AI总结:

本文提出 CellSeg1,通过对 SAM 进行低秩适配,仅用单张图像中几十个细胞标注即可实现鲁棒分割,并在19个数据集上达到可比多图训练模型的性能。

摘要:

细胞分割的最新趋势已转向用通用模型处理多样的细胞形态和成像模态。然而,对于不断涌现的细胞类型和成像技术,这些模型仍需数百或数千个带标注细胞进行微调。我们提出 CellSeg1,这是一种实用方案,仅用1张图像中的几十个细胞标注,即可分割任意形态和模态的细胞。通过采用 Segment Anything Model(SAM)的 Low-Rank Adaptation(低秩适配),我们实现了鲁棒的细胞分割。在19个多样化细胞数据集上测试时,仅用1张图像训练的 CellSeg1 在0.5 IoU下取得0.81的平均mAP,表现可与使用500多张图像训练的现有模型相媲美。它还在 TissueNet 的跨数据集测试中展现出更优的泛化能力。我们发现,对几十个大小不一、密集排列的细胞进行高质量标注,是有效分割的关键。CellSeg1 以最少的标注成本为细胞分割提供了高效解决方案。

英文摘要:

Recent trends in cell segmentation have shifted towards universal models to handle diverse cell morphologies and imaging modalities. However, for continuously emerging cell types and imaging techniques, these models still require hundreds or thousands of annotated cells for fine-tuning. We introduce CellSeg1, a practical solution for segmenting cells of arbitrary morphology and modality with a few dozen cell annotations in 1 image. By adopting Low-Rank Adaptation of the Segment Anything Model (SAM), we achieve robust cell segmentation. Tested on 19 diverse cell datasets, CellSeg1 trained on 1 image achieved 0.81 average mAP at 0.5 IoU, performing comparably to existing models trained on over 500 images. It also demonstrated superior generalization in cross-dataset tests on TissueNet. We found that high-quality annotation of a few dozen densely packed cells of varied sizes is key to effective segmentation. CellSeg1 provides an efficient solution for cell segmentation with minimal annotation effort.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑