College of Artificial Intelligence, Nankai University, Tianjin 300350, China; Institute of Intelligence Technology and Robotic Systems, Shenzhen Research Institute of Nankai University, Shenzhen 518083, China.
College of Artificial Intelligence, Nankai University, Tianjin 300350, China; Institute of Intelligence Technology and Robotic Systems, Shenzhen Research Institute of Nankai University, Shenzhen 518083, China.
Comput Med Imaging Graph. 2023 Jul;107:102247. doi: 10.1016/j.compmedimag.2023.102247. Epub 2023 May 18.
High-quality and high-resolution magnetic resonance (MR) images can provide more details for diagnosis and analyses. Recently, MR images guided neurosurgery has become an emerging technique in clinics. Unlike other medical imaging techniques, it is impossible to achieve both real-time imaging and high image quality in MR imaging. The real-time performance is closely related to the nuclear magnetic equipment itself as well as the collection strategy of the k space data. Optimizing the imaging time cost via the corresponding algorithm is harder than enhancing image quality. Further, in reconstructing low-resolution and noise-rich MR images, getting relatively high-definition and resolution MR images as references are difficult or impossible. In addition, the existing methods are restricted in learning the controllable functions under the supervision of known degradation types and levels. As a result, severely bad results are inevitable when the modeling assumptions are far apart from the actual situation. To address these problems, we propose a novel adaptive adjustment method based on real MR images via opinion-unaware measurements for real super-resolution (AOURSR). It can estimate the degree of blur and noise from the test image itself using two scores. These two scores can be considered pseudo labels to train the adaptive adjustable degradation estimation module. Then, the outputs of the above model are used as the inputs of the conditional network to tweak the generated results. Thus, the results can be automatically adjusted via the whole dynamic model. Extensive experimental results show that the proposed AOURSR is superior to state-of-the-art methods on benchmarks quantitatively and visually.
高质量和高分辨率的磁共振（MR）图像可以提供更多的诊断和分析细节。最近，MR 图像引导神经外科已成为临床新兴技术。与其他医学成像技术不同，MR 成像不可能同时实现实时成像和高图像质量。实时性能与磁共振设备本身以及 k 空间数据的采集策略密切相关。通过相应的算法优化成像时间成本比增强图像质量更难。此外，在重建低分辨率和噪声丰富的 MR 图像时，很难或不可能获得相对高清晰度和分辨率的 MR 图像作为参考。此外，现有的方法在学习已知退化类型和水平的监督下的可控功能方面受到限制。因此，当建模假设与实际情况相差很大时，必然会产生严重的不良结果。为了解决这些问题，我们提出了一种新的基于真实 MR 图像的自适应调整方法，该方法通过无意见测量进行无监督真实超分辨率（AOURSR）。它可以使用两个分数从测试图像本身估计模糊度和噪声的程度。这两个分数可以被认为是伪标签，以训练自适应可调退化估计模块。然后，上述模型的输出被用作条件网络的输入来调整生成的结果。因此，通过整个动态模型可以自动调整结果。大量实验结果表明，所提出的 AOURSR 在基准测试中在定量和定性上均优于最先进的方法。
