DenseMP：面向小样本医学图像分割的无监督稠密预训练
DenseMP: Unsupervised Dense Pre-training for Few-shot Medical Image Segmentation
AI总结：
针对小样本医学图像分割训练数据稀缺易过拟合的问题，提出含两阶段无监督稠密预训练的DenseMP流水线，可提升PA-Net性能，在Abd-CT、Abd-MRI数据集上达SOTA。
摘要：
小样本医学图像语义分割在医学图像分析领域至关重要。然而现有方法受训练阶段数据稀缺的困扰，易导致过拟合。为缓解该问题，我们提出一种新型无监督稠密小样本医学图像分割模型训练流水线DenseMP，其核心依托无监督稠密预训练。DenseMP包含两个不同阶段：（1）感知分割的稠密对比预训练；（2）感知小样本的超像素引导稠密预训练。两个阶段协同生成专为小样本医学图像分割设计的预训练初始模型，后续可在目标数据集上微调。我们提出的流水线显著提升了公认的小样本分割模型PA-Net的性能，在Abd-CT与Abd-MRI数据集上取得了当前最优结果。代码将在录用后发布。
英文摘要：
Few-shot medical image semantic segmentation is of paramount importance in the domain of medical image analysis. However, existing methodologies grapple with the challenge of data scarcity during the training phase, leading to over-fitting. To mitigate this issue, we introduce a novel Unsupervised Dense Few-shot Medical Image Segmentation Model Training Pipeline (DenseMP) that capitalizes on unsupervised dense pre-training. DenseMP is composed of two distinct stages: (1) segmentation-aware dense contrastive pre-training, and (2) few-shot-aware superpixel guided dense pre-training. These stages collaboratively yield a pre-trained initial model specifically designed for few-shot medical image segmentation, which can subsequently be fine-tuned on the target dataset. Our proposed pipeline significantly enhances the performance of the widely recognized few-shot segmentation model, PA-Net, achieving state-of-the-art results on the Abd-CT and Abd-MRI datasets. Code will be released after acceptance.
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。
