Retinal Optical Coherence Tomography (OCT) segmentation is essential for diagnosing pathology. Traditional methods focus on either spatial or spectral domains, overlooking their combined dependencies. We propose a triple-encoder network that integrates CNNs for spatial features, Fast Fourier Convolution (FFC) for spectral features, and attention mechanisms to capture global relationships across both domains. Attention fusion modules integrate convolution and cross-attention to further enhance features. Our method achieves an average Dice score improvement from 0.855 to 0.864, outperforming prior work.

翻译：视网膜光学相干断层扫描（OCT）分割对于病理诊断至关重要。传统方法通常仅关注空间域或光谱域，忽略了二者之间的联合依赖关系。我们提出了一种三重编码器网络，该网络集成了用于提取空间特征的卷积神经网络（CNN）、用于提取光谱特征的快速傅里叶卷积（FFC），以及用于捕获跨域全局关系的注意力机制。注意力融合模块整合了卷积与交叉注意力，以进一步增强特征表示。我们的方法将平均Dice分数从0.855提升至0.864，优于现有方法。