当前位置: X-MOL 学术Comput. Biol. Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Neighborhood evaluator for efficient super-resolution reconstruction of 2D medical images
Computers in Biology and Medicine ( IF 7.0 ) Pub Date : 2024-02-28 , DOI: 10.1016/j.compbiomed.2024.108212
Zijia Liu 1 , Jing Han 2 , Jiannan Liu 2 , Zhi-Cheng Li 3 , Guangtao Zhai 1
Affiliation  

Deep learning-based super-resolution (SR) algorithms aim to reconstruct low-resolution (LR) images into high-fidelity high-resolution (HR) images by learning the low- and high-frequency information. Experts’ diagnostic requirements are fulfilled in medical application scenarios through the high-quality reconstruction of LR digital medical images. Medical image SR algorithms should satisfy the requirements of arbitrary resolution and high efficiency in applications. However, there is currently no relevant study available. Several SR research on natural images have accomplished the reconstruction of resolutions without limitations. However, these methodologies provide challenges in meeting medical applications due to the large scale of the model, which significantly limits efficiency. Hence, we suggest a highly effective method for reconstructing medical images at any desired resolution. Statistical features of medical images exhibit greater continuity in the region of neighboring pixels than natural images. Hence, the process of reconstructing medical images is comparatively less challenging. Utilizing this property, we develop a neighborhood evaluator to represent the continuity of the neighborhood while controlling the network’s depth. The suggested method has superior performance across seven scales of reconstruction, as evidenced by experiments conducted on panoramic radiographs and two external public datasets. Furthermore, the proposed network significantly decreases the parameter count by over and the computational workload by over compared to prior researches. On large-scale reconstruction, the inference speed can be enhanced by over . The novel proposed SR strategy for medical images performs efficient reconstruction at arbitrary resolution, marking a significant breakthrough in the field. The given scheme facilitates the implementation of SR in mobile medical platforms.

中文翻译:


用于二维医学图像高效超分辨率重建的邻域评估器



基于深度学习的超分辨率(SR)算法旨在通过学习低频和高频信息将低分辨率(LR)图像重建为高保真高分辨率(HR)图像。通过LR数字医学图像的高质量重建,满足医疗应用场景中专家的诊断需求。医学图像SR算法应满足应用中任意分辨率和高效率的要求。但目前尚无相关研究。一些针对自然图像的超分辨率研究已经完成了无限制的分辨率重建。然而,由于模型规模庞大,这些方法在满足医疗应用方面提出了挑战,这极大地限制了效率。因此,我们提出了一种以任何所需分辨率重建医学图像的高效方法。与自然图像相比,医学图像的统计特征在相邻像素区域表现出更大的连续性。因此,重建医学图像的过程相对不那么具有挑战性。利用这个特性,我们开发了一个邻域评估器来表示邻域的连续性,同时控制网络的深度。正如在全景射线照片和两个外部公共数据集上进行的实验所证明的那样,所建议的方法在七个重建尺度上具有优异的性能。此外,与之前的研究相比,所提出的网络显着减少了参数数量和计算工作量。在大规模重建时,推理速度可以提高超过 。 提出的新颖的医学图像 SR 策略可以在任意分辨率下进行高效重建,标志着该领域的重大突破。该方案有利于SR在移动医疗平台中的实施。
更新日期:2024-02-28
down
wechat
bug