基于多注意力交叉蒸馏的半监督病理图像分割
Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions
AI总结：
本文提出基于多注意力交叉蒸馏的半监督病理图像分割方法CDMA，通过MTNet三分支注意力网络与交叉解码器知识蒸馏及不确定性最小化，有效利用未标注图像，在DigestPath数据集上优于八种先进SSL方法。
摘要：
病理图像分割是实现准确癌症诊断的关键步骤。然而，为训练获取此类图像的密集标注既耗费人力又耗时。为解决这一问题，半监督学习（SSL）具有降低标注成本的潜力，但面临大量未标注训练图像的挑战。本文提出了一种基于多注意力交叉蒸馏（CDMA）的新型SSL方法，以有效利用未标注图像。首先，我们提出了一种多注意力三分支网络（MTNet），该网络由一个编码器和一个三分支解码器组成，每个分支使用不同的注意力机制，从不同方面校准特征以生成多样化的输出。其次，我们在三个解码器分支之间引入交叉解码器知识蒸馏（CDKD），使它们能够相互学习软标签，从而减轻训练中错误伪标签的负面影响。此外，对三个分支的平均预测应用不确定性最小化，进一步正则化未标注图像上的预测并促进分支间一致性。我们提出的CDMA在公开的DigestPath数据集上与八种最先进的SSL方法进行了比较，实验结果表明，在不同标注比例下，我们的方法均优于其他方法。代码可在\href{https://github.com/HiLab-git/CDMA}{https://github.com/HiLab-git/CDMA.}获取。
英文摘要：
Segmentation of pathological images is a crucial step for accurate cancer diagnosis. However, acquiring dense annotations of such images for training is labor-intensive and time-consuming. To address this issue, Semi-Supervised Learning (SSL) has the potential for reducing the annotation cost, but it is challenged by a large number of unlabeled training images. In this paper, we propose a novel SSL method based on Cross Distillation of Multiple Attentions (CDMA) to effectively leverage unlabeled images. Firstly, we propose a Multi-attention Tri-branch Network (MTNet) that consists of an encoder and a three-branch decoder, with each branch using a different attention mechanism that calibrates features in different aspects to generate diverse outputs. Secondly, we introduce Cross Decoder Knowledge Distillation (CDKD) between the three decoder branches, allowing them to learn from each other's soft labels to mitigate the negative impact of incorrect pseudo labels in training. Additionally, uncertainty minimization is applied to the average prediction of the three branches, which further regularizes predictions on unlabeled images and encourages inter-branch consistency. Our proposed CDMA was compared with eight state-of-the-art SSL methods on the public DigestPath dataset, and the experimental results showed that our method outperforms the other approaches under different annotation ratios. The code is available at \href{https://github.com/HiLab-git/CDMA}{https://github.com/HiLab-git/CDMA.}
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。
