HisynSeg：基于图像混合合成与一致性正则化的弱监督组织病理图像分割
HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
AI总结：
HisynSeg通过图像混合合成与自监督一致性正则化，将组织病理图像的弱监督分割转化为全监督问题，在三个数据集上取得最先进性能。
摘要：
组织语义分割是计算病理学中的关键任务之一。为避免获取像素级标注的高昂成本和繁重劳动，大量研究尝试采用类激活图（CAM）这一弱监督学习方案来实现像素级组织分割。然而，基于CAM的方法容易受到欠激活和过激活问题的影响，导致分割性能不佳。为解决这一问题，我们提出了一种新颖的基于图像混合合成与一致性正则化的组织病理图像弱监督语义分割框架，称为HisynSeg。具体而言，生成带有像素级掩码的合成组织病理图像用于全监督模型训练，其中基于Mosaic变换和Bézier掩码生成提出了两种合成策略。此外，开发了一个图像滤波模块以保证合成图像的真实性。为了进一步避免模型对偶发合成伪影的过拟合，我们还提出了一种新颖的自监督一致性正则化，使没有分割掩码的真实图像能够监督分割模型的训练。通过整合所提出的技术，HisynSeg框架成功地将弱监督语义分割问题转化为全监督问题，大幅提高了分割精度。在三个数据集上的实验结果表明，所提方法达到了最先进的性能。代码可在 https://github.com/Vison307/HisynSeg 获取。
英文摘要：
Tissue semantic segmentation is one of the key tasks in computational pathology. To avoid the expensive and laborious acquisition of pixel-level annotations, a wide range of studies attempt to adopt the class activation map (CAM), a weakly-supervised learning scheme, to achieve pixel-level tissue segmentation. However, CAM-based methods are prone to suffer from under-activation and over-activation issues, leading to poor segmentation performance. To address this problem, we propose a novel weakly-supervised semantic segmentation framework for histopathological images based on image-mixing synthesis and consistency regularization, dubbed HisynSeg. Specifically, synthesized histopathological images with pixel-level masks are generated for fully-supervised model training, where two synthesis strategies are proposed based on Mosaic transformation and Bézier mask generation. Besides, an image filtering module is developed to guarantee the authenticity of the synthesized images. In order to further avoid the model overfitting to the occasional synthesis artifacts, we additionally propose a novel self-supervised consistency regularization, which enables the real images without segmentation masks to supervise the training of the segmentation model. By integrating the proposed techniques, the HisynSeg framework successfully transforms the weakly-supervised semantic segmentation problem into a fully-supervised one, greatly improving the segmentation accuracy. Experimental results on three datasets prove that the proposed method achieves a state-of-the-art performance. Code is available at https://github.com/Vison307/HisynSeg.
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。
