Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA, USA.
Sir Run Run Shaw Hospital, Zhejiang University School of Medicine and Institute of Translational Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
Med Phys. 2018 Nov;45(11):4942-4954. doi: 10.1002/mp.13189. Epub 2018 Oct 10.
Denoising has been a challenging research subject in medical imaging, since the suppression of noise conflicts with the preservation of texture and edges. To address this challenge, we develop a content-oriented sparse representation (COSR) method for denoising in computed tomography (CT).
An image is segmented into a number of content areas and each of them consists of similar material. Having been ex-painted, each content area is sparsely coded using the dictionary learnt from patches extracted from the corresponding content area. By constraining sparsity, noise is suppressed and the final image is formed by aggregating all denoised content areas. The performance of COSR method is examined with images simulated by computer and generated by multidetector row CT (MDCT), cone beam CT (CBCT), and micro-CT, in which water phantom, anthropomorphic phantom, a human subject, and a small animal are engaged, using the figures of merit, such as standard division (SD), contrast to noise ratio (CNR), and thresholded edge keeping index (EKI ) and structural similarity index (SSIM). In addition, the optimization of performance by parameter tuning is also investigated.
Quantitatively gauged by metrics of noise, EKI and SSIM, the performance evaluation shows that the proposed COSR method is effective in denoising (>50% reduction in noise) while it outperforms the conventional sparse representation method in preservation of texture and edge by ~20% (gauged by SSIM). It has also been shown that the COSR method is tolerable to inaccuracy in content area segmentation and variation in dictionary learning. Moreover, the computational efficiency of COSR can be substantially improved using prelearnt dictionaries.
The COSR method would find its utility in clinical and preclinical applications, such as low-dose CT, image segmentation, registration, and computer-aided diagnosis. The proposal of COSR denoising is of innovation and significance in the theory and practice of denoising in medical imaging. A demonstration code package is available at https://github.com/xiehq/COSR.
在医学成像中，去噪一直是一个具有挑战性的研究课题，因为噪声的抑制与纹理和边缘的保留相冲突。为了解决这个挑战，我们开发了一种面向内容的稀疏表示（COSR）方法，用于计算机断层扫描（CT）中的去噪。
将图像分割成若干内容区域，每个区域由相似的物质组成。在被绘制之后，每个内容区域都使用从相应内容区域提取的补丁学习到的字典进行稀疏编码。通过约束稀疏性，可以抑制噪声，并通过聚合所有去噪的内容区域来形成最终的图像。使用计算机模拟的图像以及由多排 CT（MDCT）、锥形束 CT（CBCT）和微 CT 生成的图像来检验 COSR 方法的性能，其中涉及水模体、人体模体、人体和小动物，使用了诸如标准偏差（SD）、对比噪声比（CNR）、阈值边缘保持指数（EKI）和结构相似性指数（SSIM）等度量标准。此外，还研究了通过参数调整来优化性能。
通过噪声、EKI 和 SSIM 等指标进行定量评估，性能评估表明，所提出的 COSR 方法在去噪方面是有效的（噪声降低超过 50%），同时在保持纹理和边缘方面优于传统的稀疏表示方法（通过 SSIM 衡量提高了约 20%）。还表明，COSR 方法对内容区域分割的不准确性和字典学习的变化具有一定的容忍度。此外，使用预学习的字典可以大大提高 COSR 的计算效率。
COSR 方法将在临床和临床前应用中找到其用途，例如低剂量 CT、图像分割、配准和计算机辅助诊断。COSR 去噪的提出在医学成像中的去噪理论和实践方面具有创新性和意义。一个演示代码包可在 https://github.com/xiehq/COSR 上获得。
