摘要： 在临床医学领域,患者组织切片的病理学分析是评估复杂疾病的金标准。传统的超分辨率(SR)方法在处理病理图像时,常因无法有效捕捉图像中的细微结构和纹理导致重建效果不佳。为解决这一问题,提出一种基于并联注意力机制的超分辨率生成式对抗网络算法(PASRGAN)。该算法通过通道和空间注意力机制的并联运行,有效解决了传统注意力机制的信息分散问题。此外,引入特征分组和通道混洗(shuffle)策略,在保持低计算开销的前提下提升特征多样性,从而显著提升病理图像的重建性能。鉴于现有的病理图像超分辨率研究大多是在模拟数据集上进行的,无法完全揭示现实图像超分辨率的挑战,因此基于Camelyon16数据集构建真实低分辨率(LR)与高分辨率(HR)图像对,验证算法在病理图像超分辨率任务中的优越性。实验结果表明,与当前超分辨率算法(如ESRGAN、CWT-Net、Histo-Diffusion和URCDM)相比,PASRGAN的峰值信噪比(PSNR)、结构相似性系数(SSIM)和感知指标(PI)分别达到25.33 dB、0.665 9和5.14,均优于对比算法。同时,PASRGAN的参数量和浮点运算次数(FLOPs)分别为1.08×10⁷和4.89×10⁹,显著低于传统方法,验证了其在计算效率上的优势。消融实验进一步验证了并联注意力机制、shuffle操作以及生成器和判别器结构的有效性。

关键词: 深度学习, 病理图像, 超分辨率重建, 注意力机制, 生成对抗网络

Abstract: In the field of clinical medicine, the pathological analysis of patient tissue sections is considered the gold standard for assessing complex diseases. Traditional Super-Resolution (SR) methods often fail to effectively capture fine structures and textures in pathological images, leading to suboptimal reconstruction performance. To address this issue, this study proposes a novel super-resolution generative adversarial network based on a parallel attention mechanism, referred to as Parallel Attention Super-Resolution Generative Adversarial Network (PASRGAN). The proposed algorithm adopts parallel execution of channel and spatial attention mechanisms to overcome the information dispersion issues inherent in traditional attention mechanisms. Furthermore, a feature grouping and channel shuffle strategy is introduced, which enhances feature diversity while maintaining low computational costs, thereby significantly improving the reconstruction performance of pathological images. Considering that most existing super-resolution studies on pathological images are conducted on simulated datasets that fail to fully reflect the challenges of real-world image degradation, this study constructs paired Low-Resolution (LR) and High-Resolution (HR) image datasets based on the Camelyon16 dataset to validate the effectiveness of the proposed algorithm in real-world scenarios. Experimental results demonstrate that, compared to state-of-the-art super-resolution methods (e.g., ESRGAN, CWT-Net, Histo-Diffusion, and URCDM), PASRGAN achieves superior performance with a Peak Signal-to-Noise Ratio (PSNR) of 25.33 dB, Structural Similarity Index Measure (SSIM) of 0.665 9, and Perceptual Index (PI) of 5.14. Additionally, PASRGAN achieves significantly lower parameter complexity (1.08×10⁷) and Floating-Point Operations (FLOPs) (4.89×10⁹) than traditional methods, confirming its computational efficiency. Ablation studies further analyze the contributions of the parallel attention mechanism, shuffle operation, and improvements in the generator and discriminator structures to verify their effectiveness.

Key words: deep learning, pathological image, Super-Resolution (SR) reconstruction, attention mechanism, Generative Adversarial Network (GAN)

中图分类号: 

• TP18