Super-resolution plays an essential role in medical imaging because it provides an alternative way to achieve high spatial resolutions and image quality with no extra acquisition costs. In the past few decades, the rapid development of deep neural networks has promoted super-resolution performance with novel network architectures, loss functions and evaluation metrics. Specifically, vision transformers dominate a broad range of computer vision tasks, but challenges still exist when applying them to low-level medical image processing tasks. This paper proposes an efficient vision transformer with residual dense connections and local feature fusion, aiming to achieve efficient single-image super-resolution (SISR) of medical modalities. Moreover, we implement a general-purpose perceptual loss with manual control for image quality improvements of desired aspects by incorporating prior knowledge of medical image segmentation. Compared with state-of-the-art methods on four public medical image datasets, the proposed method achieves the best PSNR scores of 6 modalities among seven modalities in total. It leads to an average improvement of $+0.09$ dB PSNR with only 38\% parameters of SwinIR. On the other hand, the segmentation-based perceptual loss increases $+0.14$ dB PSNR on average for SOTA methods, including CNNs and vision transformers. Additionally, we conduct comprehensive ablation studies to discuss potential factors for the superior performance of vision transformers over CNNs and the impacts of network and loss function components.
翻译:超分辨率在医学成像中发挥着不可或缺的作用,因为它提供了一种实现高空间分辨率和图像质量的替代方法,而没有额外的获取成本。在过去几十年中,深神经网络的迅速发展促进了超分辨率性能,带来了新型网络结构、损失功能和评估指标。具体地说,视觉变压器主导着广泛的计算机视觉任务,但在应用这些变压器执行低水平的医疗图像处理任务时仍然存在挑战。本文件建议建立一个高效的视觉变压器,具有残留的密集连接和本地特征融合,目的是实现医疗模式的高效单一图像超分辨率(SISR),目的是实现高效的单一图像超分辨率(SISR)。此外,我们实施了通用感知觉损失,同时通过将医学图像分解的先前知识、损失功能和评估度提高图像质量。与四个公共医学图像数据集中最先进的方法相比,拟议方法在七个模式中共达到6种最佳的PSNRR评分。这导致SWSB PSNR平均改善值,只有38°Z的参数。另一方面,我们基于部分的视觉变影变影功能研究,包括SIS的SO+ODA的变影变动功能,我们的SL的SLA的变影学的变影变影变影学的SO14的功能研究,我们的SL的视觉的变换的变影的视觉的视觉的视觉的变影的变影的变影的变的变的变的变的变的变的变的变的变的变的变的变的变的功能,包括SMA的功能,我们的变式的变换的变换的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式的变式