发表机构
Igor Sikorsky Kyiv Polytechnic Institute; STACC OÜ; Better Medicine OÜ（伊戈尔·西科尔斯基基辅理工学院; STACC OÜ; Better Medicine OÜ）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对显微图像重叠细胞实例分割的难题，提出基于查询的模型QCell，通过实例重组模块与对比查询对齐损失实现全局推理，在ISBI2014等基准上优于现有方法，还构建了类器官数据集基准。
AI 中文摘要
显微图像中重叠细胞的实例分割极具挑战性，因为半透明结构会在重叠区域产生弱边界和混合视觉证据。现有方法通过局部感兴趣区域或形状先验解决该问题，但缺乏对重叠对象的全局推理。本文提出QCell，一种新型基于查询的模型，用于消除显微场景中细胞实例的重叠。该方法包含两个核心部分：（i）实例重组模块，在隐空间中分解并重组查询表示，使模型能在重叠情况下推理完整对象结构；（ii）对比查询对齐损失，结合独特实例特征学习与重叠细胞查询的分离。此外，本文还引入了新的类器官（Organoid）数据集基准用于重叠细胞分割。实验结果显示，QCell在多个基准上均优于现有最优方法，在ISBI2014数据集上实现了2.2的平均精度（AP）提升和2.7的联合交集（AJI）提升，代码可在指定URL获取。
英文摘要
Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this through local regions of interest or shape priors but lack global reasoning across overlapping objects. We present QCell, a novel query-based model that de-overlaps cell instances in microscopy scenes. Our approach combines (i) an instance recombination module that decomposes and recombines query representations in latent space, enabling the model to reason about complete object structure under overlap, and (ii) a contrastive query alignment objective that combines distinctive instance feature learning and separation of overlapping cell queries. We additionally introduce a new Organoid dataset benchmark for overlapping cell segmentation. We show that QCell outperforms state-of-the-art methods across multiple benchmarks, achieving +2.2 AP and +2.7 AJI on ISBI2014. Code is available at https://github.com/SlavkoPrytula/QCell
CommentsAccepted at the British Machine Vision Conference (BMVC) 2026. Project page/code/models/dataset: https://slavkoprytula.github.io/QCell/
