arXiv 2308.161452023-08-31cs.CV

CircleFormer：基于圆形查询与注意力的全切片图像圆形细胞核检测

CircleFormer: Circular Nuclei Detection in Whole Slide Images with Circle Queries and Attention

Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences（中国科学院合肥物质科学研究院智能机械研究所）；Institutes of Physical Science and Information Technology, Anhui University（安徽大学物质科学与信息技术研究院）；School of Computer and Artificial Intelligence, Zhengzhou University（郑州大学计算机与人工智能学院）

Hengxu Zhang, Pengpeng Liang, Zhiyong Sun, Bo Song, Erkang Cheng

备注：: Accepted at MICCAI 2023

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出CircleFormer，一种基于Transformer的圆形目标检测方法，通过圆形查询与交叉注意力及gCIoU损失，在MoNuSeg数据集上实现优于现有方法的圆形细胞核检测与分割。

摘要：

基于CNN和基于Transformer的边界框表示目标检测已在计算机视觉和医学图像分析中被广泛研究，但医学图像中的圆形目标检测仍未被充分探索。受近期用于肾病理学中球状肾小球检测的基于无锚点CNN的圆形目标检测方法（CircleNet）启发，本文提出CircleFormer，一种基于Transformer的圆形医学目标检测方法，采用动态锚点圆。具体地，Transformer解码器中具有圆形表示的查询迭代地优化圆形目标检测结果，并引入圆形交叉注意力模块来计算圆形查询与图像特征之间的相似性。此外，提出广义圆形IoU（gCIoU）作为圆形目标检测的新回归损失。我们的方法还可通过向CircleFormer添加简单分割分支轻松推广到分割任务。我们在公共MoNuSeg数据集上评估了圆形细胞核检测与分割方法，实验结果表明，与最先进方法相比，我们的方法取得了有竞争力的性能。通过消融研究验证了各组件的有效性。代码已发布在https://github.com/zhanghx-iim-ahu/CircleFormer。

英文摘要：

Both CNN-based and Transformer-based object detection with bounding box representation have been extensively studied in computer vision and medical image analysis, but circular object detection in medical images is still underexplored. Inspired by the recent anchor free CNN-based circular object detection method (CircleNet) for ball-shape glomeruli detection in renal pathology, in this paper, we present CircleFormer, a Transformer-based circular medical object detection with dynamic anchor circles. Specifically, queries with circle representation in Transformer decoder iteratively refine the circular object detection results, and a circle cross attention module is introduced to compute the similarity between circular queries and image features. A generalized circle IoU (gCIoU) is proposed to serve as a new regression loss of circular object detection as well. Moreover, our approach is easy to generalize to the segmentation task by adding a simple segmentation branch to CircleFormer. We evaluate our method in circular nuclei detection and segmentation on the public MoNuSeg dataset, and the experimental results show that our method achieves promising performance compared with the state-of-the-art approaches. The effectiveness of each component is validated via ablation studies as well. Our code is released at https://github.com/zhanghx-iim-ahu/CircleFormer.

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。