一种基于注意力的医学图像合成生成模型
An Attentive-based Generative Model for Medical Image Synthesis
AI总结：
针对多切片非配对医学图像跨模态合成难题，提出融合双重对比损失、注意力机制与 K-means 分组训练的 ADC-cycleGAN，PSNR 与 SSIM 达到最优。
摘要：
磁共振（MR）和计算机断层扫描（CT）成像是诊断疾病和规划治疗的宝贵工具。然而，辐射暴露和成本等限制可能会限制某些成像模态的可及性。为解决这一问题，医学图像合成可从一种模态生成另一种模态，但当数据集中存在多个切片时，许多现有模型难以实现高质量图像合成。本研究提出一种基于注意力的双重对比生成模型，称为 ADC-cycleGAN，可从具有多个切片的非配对数据合成医学图像。该模型将双重对比损失项与 CycleGAN 损失相结合，以确保合成图像能够与源域区分开。此外，生成器中引入注意力机制，从通道和空间两个域提取信息丰富的特征。为提升处理多个切片时的性能，使用 $K$-means 算法将数据集聚类为 $K$ 个组，每组用于训练一个独立的 ADC-cycleGAN。实验结果表明，所提出的 ADC-cycleGAN 模型生成的样本可与其他最先进的生成模型相媲美，并取得最高的 PSNR 和 SSIM 值，分别为 19.04385 和 0.68551。我们在 https://github.com/JiayuanWang-JW/ADC-cycleGAN 发布代码。
英文摘要：
Magnetic resonance (MR) and computer tomography (CT) imaging are valuable tools for diagnosing diseases and planning treatment. However, limitations such as radiation exposure and cost can restrict access to certain imaging modalities. To address this issue, medical image synthesis can generate one modality from another, but many existing models struggle with high-quality image synthesis when multiple slices are present in the dataset. This study proposes an attention-based dual contrast generative model, called ADC-cycleGAN, which can synthesize medical images from unpaired data with multiple slices. The model integrates a dual contrast loss term with the CycleGAN loss to ensure that the synthesized images are distinguishable from the source domain. Additionally, an attention mechanism is incorporated into the generators to extract informative features from both channel and spatial domains. To improve performance when dealing with multiple slices, the $K$-means algorithm is used to cluster the dataset into $K$ groups, and each group is used to train a separate ADC-cycleGAN. Experimental results demonstrate that the proposed ADC-cycleGAN model produces comparable samples to other state-of-the-art generative models, achieving the highest PSNR and SSIM values of 19.04385 and 0.68551, respectively. We publish the code at https://github.com/JiayuanWang-JW/ADC-cycleGAN.
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。
