Li Hongyan, Wan Zhonglin
School of Computer and Information, City College of Dongguan University of Technology, Dongguan, China.
Department of Finance and Economics, Dongguan Polytechnic, Dongguan, China.
Ann Transl Med. 2021 Sep;9(18):1422. doi: 10.21037/atm-21-3529.
Computed tomography (CT) is an advanced medical imaging technology. The images obtained by CT are helpful for improving diagnostic accuracy. Currently, CT is widely used in clinical settings for diagnosis and health examinations. However, full angle CT scanning has the disadvantage of causing radiation damage to the human body. Sparse angle projection CT scanning is the most effective way to minimize this damage, but the quality of the reconstructed image is reduced. Therefore, it is important to improve the reconstructed image quality produced by sparse angle projection.
In this paper, we focused on the algebraic reconstruction algorithm. To reduce the accumulation of random noise, we formulated a modified algebraic reconstruction algorithm. Firstly, the algebraic reconstruction algorithm was used to compute two consecutive results, and then the weighted sum of these two results was used to correct the reconstructed image, and an iterative result was obtained. Using this method, we aimed to reduce the noise accumulation caused by iteration.
In this study, 20 angle projections were used for the reconstruction. The experimental object was the Shepp-Logan phantom test image. The experiments were implemented under two conditions: without noise and with noise. The peak signal to noise ratio (PSNR) and the mean squared error (MSE) of the reconstructed image from projections without noise were 76.0896 and 0.0016, respectively. The PSNR and MSE of the reconstructed image from projections with noise were 75.8263 and 0.0017, respectively. The reconstructed performance was superior to the previous algebraic reconstruction algorithm.
The performance of the proposed method was superior to other algorithms, which confirms that noise accumulation caused by iteration can be effectively reduced by the weighted summation of two consecutive reconstruction results. Moreover, the reconstruction performance under noisy projection is superior to other algorithms, which demonstrates that the proposed method improves anti-noise performance.
计算机断层扫描（CT）是一种先进的医学成像技术。CT获得的图像有助于提高诊断准确性。目前，CT在临床诊断和健康检查中广泛应用。然而，全角度CT扫描存在对人体造成辐射损伤的缺点。稀疏角度投影CT扫描是将这种损伤降至最低的最有效方法，但重建图像的质量会降低。因此，提高稀疏角度投影产生的重建图像质量很重要。
在本文中，我们重点研究代数重建算法。为了减少随机噪声的积累，我们制定了一种改进的代数重建算法。首先，使用代数重建算法计算两个连续结果，然后使用这两个结果的加权和来校正重建图像，从而获得一个迭代结果。使用这种方法，我们旨在减少迭代引起的噪声积累。
在本研究中，使用20个角度投影进行重建。实验对象是Shepp-Logan体模测试图像。实验在两种条件下进行：无噪声和有噪声。无噪声投影重建图像的峰值信噪比（PSNR）和均方误差（MSE）分别为76.0896和0.0016。有噪声投影重建图像的PSNR和MSE分别为75.8263和0.0017。重建性能优于先前的代数重建算法。
所提方法的性能优于其他算法，这证实了通过两个连续重建结果的加权求和可以有效减少迭代引起的噪声积累。此外，有噪声投影下的重建性能优于其他算法，这表明所提方法提高了抗噪声性能。
