Accurate segmentation of the left atrium (LA) from late gadolinium-enhanced cardiac magnetic resonance (LGE CMR) images is crucial for aiding the treatment of patients with atrial fibrillation. Few-shot learning holds significant potential for achieving accurate LA segmentation with low demand on high-cost labeled LGE CMR data and fast generalization across different centers. However, accurate LA segmentation with few-shot learning is a challenging task due to the low-intensity contrast between the LA and other neighboring organs in LGE CMR images. To address this issue, we propose an Adaptive Dynamic Inference Network (ADINet) that explicitly models the differences between the foreground and background. Specifically, ADINet leverages dynamic collaborative inference (DCI) and dynamic reverse inference (DRI) to adaptively allocate semantic-aware and spatial-specific convolution weights and indication information. These allocations are conditioned on the support foreground and background knowledge, utilizing pixel-wise correlations, for different spatial positions of query images. The convolution weights adapt to different visual patterns based on spatial positions, enabling effective encoding of differences between foreground and background regions. Meanwhile, the indication information adapts to the background visual pattern to reversely decode foreground LA regions, leveraging their spatial complementarity. To promote the learning of ADINet, we propose hierarchical supervision, which enforces spatial consistency and differences between the background and foreground regions through pixel-wise semantic supervision and pixel-pixel correlation supervision. We demonstrated the performance of ADINet on three LGE CMR datasets from different centers. Compared to state-of-the-art methods with ten available samples, ADINet yielded better segmentation performance in terms of four metrics.

中文翻译：

---

少样本左心房分割的自适应动态推理


从晚期钆增强心脏磁共振 (LGE CMR) 图像中准确分割左心房 (LA) 对于帮助治疗房颤患者至关重要。少样本学习在实现准确的 LA 分割方面具有巨大潜力，对高成本标记的 LGE CMR 数据的需求较低，并且在不同中心之间进行快速泛化。然而，由于 LGE CMR 图像中 LA 与其他邻近器官之间的对比度较低，因此通过少样本学习进行准确的 LA 分割是一项具有挑战性的任务。为了解决这个问题，我们提出了一种自适应动态推理网络（ADINet），它可以显式地模拟前景和背景之间的差异。具体来说，ADINet 利用动态协作推理 (DCI) 和动态反向推理 (DRI) 来自适应分配语义感知和空间特定的卷积权重和指示信息。这些分配以支持前景和背景知识为条件，利用像素级相关性，针对查询图像的不同空间位置。卷积权重根据空间位置适应不同的视觉模式，从而能够有效编码前景和背景区域之间的差异。同时，指示信息适应背景视觉模式，利用其空间互补性反向解码前景 LA 区域。为了促进 ADINet 的学习，我们提出了分层监督，通过逐像素语义监督和像素间相关监督来强制背景和前景区域之间的空间一致性和差异。我们在来自不同中心的三个 LGE CMR 数据集上展示了 ADINet 的性能。 与具有十个可用样本的最先进方法相比，ADINet 在四个指标方面产生了更好的分割性能。