Backprojection Wiener deconvolution for computed tomographic reconstruction

CT image denoising methods for image quality improvement and radiation dose reduction

With the ever-increasing use of computed tomography (CT), concerns about its radiation dose have become a significant public issue. To address the need for radiation dose reduction, CT denoising methods have been widely investigated and applied in low-dose CT images. Numerous noise reduction algorithms have emerged, such as iterative reconstruction and most recently, deep learning (DL)-based approaches. Given the rapid advancements in Artificial Intelligence techniques, we recognize the need for a comprehensive review that emphasizes the most recently developed methods. Hence, we have performed a thorough analysis of existing literature to provide such a review. Beyond directly comparing the performance, we focus on pivotal aspects, including model training, validation, testing, generalizability, vulnerability, and evaluation methods. This review is expected to raise awareness of the various facets involved in CT image denoising and the specific challenges in developing DL-based models.

Computed Tomography Image Features under Denoising Algorithm for Benign and Malignant Diagnosis of Renal Parenchymal Tumor

To improve the quality of computed tomography (CT) images and provide help for benign and malignant diagnosis of renal parenchymal tumors, the independent component analysis (ICA) denoising algorithm was used. An improved ICA X-ray CT (X-CT) medical image denoising algorithm was proposed. ICA provided a higher signal-to-noise ratio for CT image denoising. Forty patients with renal tumor were selected as the observation group. The CT image performance of patients was evaluated by the denoising algorithm and compared with the wavelet transform algorithm, and the peak signal-to-noise ratio of the proposed algorithm was analyzed and compared. The results showed that among the 40 patients with renal tumors, 12 were renal clear cell carcinoma cases and 28 were cystic renal carcinoma cases. The accuracy of the enhanced CT image was 93.8%, and that of the CT image using the denoising algorithm was 96.3%; the difference between the two was significant (P < 0.05). The peak signal-to-noise ratio (PSNR) of the algorithm proposed was higher than the PSNR values of CT and noisy images. The PSNR of the proposed algorithm was significantly higher than that of mean filtering. The root mean square error (RMSE) algorithm of the proposed algorithm was significantly lower than that of the mean algorithm in image data processing (P < 0.05), which showed the superiority of the proposed algorithm. Enhanced CT can be staged significantly. In conclusion, the algorithm had a significant effect on the edge contour of detailed features, and the accuracy of CT images based on intelligent calculation was significantly higher than that of conventional CT images for benign and malignant renal parenchyma tumors, which was worth promoting in clinical diagnosis.