用于最小标注且无需前置任务的医学图像分割的亲和图引导对比学习
Affinity-Graph-Guided Contractive Learning for Pretext-Free Medical Image Segmentation with Minimal Annotation
AI总结：
提出亲和图引导的半监督对比学习框架Semi-AGCL，通过图块间采样和亲和图损失在无需前置任务下缓解过拟合，仅用5%-10%标注即接近或超越全标注基线。
摘要：
半监督学习（SemiSL）和对比学习（CL）的结合在标注有限的医学图像分割中取得了成功。然而，这些工作通常依赖于缺乏像素级分割所需特异性的前置任务，并且由于标注过少导致监督信号不足，仍面临过拟合问题。因此，本文提出了一种亲和图引导的半监督对比学习框架（Semi-AGCL），通过在学生网络和教师网络之间建立基于亲和图的额外监督信号，实现无需前置任务的最小标注医学图像分割。该框架首先设计了一种由平均图块熵驱动的图块间采样方法，能够在不依赖前置任务的情况下提供稳健的初始特征空间。此外，该框架设计了一种亲和图引导的损失函数，通过利用数据的固有结构来提升所学表示的质量和模型泛化能力，从而缓解过拟合。实验表明，仅使用完整标注集的10%，我们的模型就接近了全标注基线的准确率，偏差仅为2.52%。在仅使用5%标注的严苛条件下，我们的模型在Dice指标上比次优基线高出23.09%，并在极具挑战性的CRAG和ACDC数据集上实现了26.57%的提升。
英文摘要：
The combination of semi-supervised learning (SemiSL) and contrastive learning (CL) has been successful in medical image segmentation with limited annotations. However, these works often rely on pretext tasks that lack the specificity required for pixel-level segmentation, and still face overfitting issues due to insufficient supervision signals resulting from too few annotations. Therefore, this paper proposes an affinity-graph-guided semi-supervised contrastive learning framework (Semi-AGCL) by establishing additional affinity-graph-based supervision signals between the student and teacher network, to achieve medical image segmentation with minimal annotations without pretext. The framework first designs an average-patch-entropy-driven inter-patch sampling method, which can provide a robust initial feature space without relying on pretext tasks. Furthermore, the framework designs an affinity-graph-guided loss function, which can improve the quality of the learned representation and the model generalization ability by exploiting the inherent structure of the data, thus mitigating overfitting. Our experiments indicate that with merely 10% of the complete annotation set, our model approaches the accuracy of the fully annotated baseline, manifesting a marginal deviation of only 2.52%. Under the stringent conditions where only 5% of the annotations are employed, our model exhibits a significant enhancement in performance surpassing the second best baseline by 23.09% on the dice metric and achieving an improvement of 26.57% on the notably arduous CRAG and ACDC datasets.
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。
