AttenScribble：面向涂鸦监督医学图像分割的注意力相似性学习
AttenScribble: Attentive Similarity Learning for Scribble-Supervised Medical Image Segmentation
AI总结：
针对涂鸦监督医学图像分割缺乏形状与边界信息的问题，本文提出可插拔空间自注意力模块及注意力相似性损失，并结合部分分割损失与掩码CRF进行端到端训练，在ACDC和CHAOS上达到接近全监督性能。
摘要：
深度网络在医学图像分割中的成功很大程度上依赖于大量带标签训练数据。然而，获取密集标注是一个耗时的过程。弱监督方法通常采用成本较低的监督形式，其中涂鸦由于其灵活性，最近开始受到欢迎。然而，由于缺乏形状和边界信息，使用涂鸦训练一个能够在未标注像素上泛化的深度网络极具挑战性。本文提出了一个简单而有效的涂鸦监督学习框架。受基于 transformer 的分割最新进展启发，我们创建了一个可插拔的空间自注意力模块，可附加在任意全卷积网络（FCN）骨干网络的任何内部特征层之上。该模块在保持卷积效率的同时注入全局交互。基于该模块，我们构建了一个由归一化且对称化的注意力导出的相似性度量。这种注意力相似性产生了一种新的正则化损失，强制分割预测与视觉亲和性之间保持一致。该注意力相似性损失优化了 FCN 编码器、注意力映射和模型预测的对齐。最终，所提出的 FCN+Attention 架构可以在三个学习目标组合的引导下进行端到端训练：部分分割损失、定制的掩码条件随机场以及所提出的注意力相似性损失。在公共数据集（ACDC 和 CHAOS）上的大量实验表明，我们的框架不仅优于现有最先进方法，而且取得了接近全监督基准的性能。代码将在论文发表后提供。
英文摘要：
The success of deep networks in medical image segmentation relies heavily on massive labeled training data. However, acquiring dense annotations is a time-consuming process. Weakly-supervised methods normally employ less expensive forms of supervision, among which scribbles started to gain popularity lately thanks to its flexibility. However, due to lack of shape and boundary information, it is extremely challenging to train a deep network on scribbles that generalizes on unlabeled pixels. In this paper, we present a straightforward yet effective scribble supervised learning framework. Inspired by recent advances of transformer based segmentation, we create a pluggable spatial self-attention module which could be attached on top of any internal feature layers of arbitrary fully convolutional network (FCN) backbone. The module infuses global interaction while keeping the efficiency of convolutions. Descended from this module, we construct a similarity metric based on normalized and symmetrized attention. This attentive similarity leads to a novel regularization loss that imposes consistency between segmentation prediction and visual affinity. This attentive similarity loss optimizes the alignment of FCN encoders, attention mapping and model prediction. Ultimately, the proposed FCN+Attention architecture can be trained end-to-end guided by a combination of three learning objectives: partial segmentation loss, a customized masked conditional random fields and the proposed attentive similarity loss. Extensive experiments on public datasets (ACDC and CHAOS) showed that our framework not just out-performs existing state-of-the-art, but also delivers close performance to fully-supervised benchmark. Code will be available upon publication.
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。
