This study aimed to improve the quality of ultrasound images by modeling an algorithm using a non-local means (NLM) noise-reduction approach to achieve precise quality control and accurate diagnosis of thyroid nodules. An ATS-539 multipurpose phantom was used to scan the dynamic range and gray-scale measurement regions, which are most closely related to the noise level. A convex-type 3.5-MHz frequency probe is used for scanning according to ATS regulations. In addition, ultrasound images of human thyroid nodules were obtained using a linear probe. An algorithm based on the NLM noise-reduction approach was modeled based on the intensity and relative distance of adjacent pixels in the image, and conventional filtering methods for image quality improvement were designed as a comparison group. When the NLM algorithm was applied to the image, the contrast-to-noise ratio and coefficient of variation values improved by 28.62% and 19.54 times, respectively, compared with those of the noisy images. In addition, the image improvement efficiency of the NLM algorithm was superior to that of conventional filtering methods. Finally, the applicability of the NLM algorithm to human thyroid images using a high-frequency linear probe was validated. We demonstrated the efficiency of the proposed algorithm in ultrasound images and the possibility of capturing improved images in the dynamic range and gray-scale region for quality control parameters.

Low-dose exposure and work convenience are required for mobile X-ray systems during the COVID-19 pandemic. We investigated a novel X-ray detector (FXRD-4343FAW, VIEWORKS, Anyang, Korea) composed of a thin-film transistor based on amorphous silicon with a flexible plastic substrate. This detector is composed of a thallium-doped cesium iodide scintillator with a pixel size of 99 μm, pixel matrix of 4316 × 4316, and weight of 2.95 kg. The proposed detector has the advantages of high-noise characteristics and low weight, which provide patients and workers with an advantage in terms of the dose and work efficiency, respectively. We performed a quantitative evaluation and an experiment to demonstrate its viability. The modulation transfer function, noise power spectrum, and detective quantum efficiency were identified using the proposed and comparative detectors, according to the International Electrotechnical Commission protocol. Additionally, the contrast-to-noise ratio and coefficient of variation were investigated using a human-like phantom. Our results indicate that the proposed detector efficiently increases the image performance in terms of noise characteristics. The detailed performance evaluation demonstrated that the outcomes of the use of the proposed detector confirmed the viability of mobile X-ray devices that require low doses. Consequently, the novel FXRD-4343FAW X-ray detector is expected to improve the image quality and work convenience in extended radiography.

Alzheimer’s disease (AD) is the most common progressive neurodegenerative disease. ¹⁸F-fluorodeoxyglucose positron emission tomography (¹⁸F-FDG PET) is widely used to predict AD using a deep learning model. However, the effects of noise and blurring on ¹⁸F-FDG PET images were not considered. The performance of a classification model trained using raw, deblurred (by the fast total variation deblurring method), or denoised (by the median modified Wiener filter) ¹⁸F-FDG PET images without or with cropping around the limbic system area using a 3D deep convolutional neural network was investigated. The classification model trained using denoised whole-brain ¹⁸F-FDG PET images achieved classification performance (0.75/0.65/0.79/0.39 for sensitivity/specificity/F1-score/Matthews correlation coefficient (MCC), respectively) higher than that with raw and deblurred ¹⁸F-FDG PET images. The classification model trained using cropped raw ¹⁸F-FDG PET images achieved higher performance (0.78/0.63/0.81/0.40 for sensitivity/specificity/F1-score/MCC) than the whole-brain ¹⁸F-FDG PET images (0.72/0.32/0.71/0.10 for sensitivity/specificity/F1-score/MCC, respectively). The ¹⁸F-FDG PET image deblurring and cropping (0.89/0.67/0.88/0.57 for sensitivity/specificity/F1-score/MCC) procedures were the most helpful for improving performance. For this model, the right middle frontal, middle temporal, insula, and hippocampus areas were the most predictive of AD using the class activation map. Our findings demonstrate that ¹⁸F-FDG PET image preprocessing and cropping improves the explainability and potential clinical applicability of deep learning models.

The purpose of this study was to investigate the viability of the proposed method in preventing the loss of metallic components including the clip and coil in cerebral computed tomography angiography (CTA). Forty patients undergoing surgery for aneurysms carried metallic materials. The proposed method is based on conventional bone subtraction CTA (BS-CTA) system. Briefly, the position of metal components was determined using the threshold value and a region of interest (ROI). An appropriate threshold was used to separate the background from the target materials based on the Otsu method. A three-dimensional (3D) rendering was performed from the proposed BS-CTA data carrying the extracted target information. The accuracy of clip and coil region measured using the dice similarity coefficient (DSC) and bidirectional Hausdorff distance (HD) is reported. The metallic components of the proposed BS-CTA were significantly visualized in various patient cases. Quantitative evaluation using the proposed method is based on the mean DSC of 0.93 with a standard deviation (SD) of ±0.05 (e.g., maximum value = 0.99, minimum value = 0.75, 95% confidence interval (CI) = 0.91 to 0.95, and all p < 0.05). The mean HD was 1.50 voxels with an SD of ± 0.58 (e.g., maximum value = 5.95, minimum value = 0.12, 95% CI = 1.10 to 1.90, and all p < 0.05). The proposed method demonstrates effective segmentation of the metallic component and application to the existing conventional BS-CTA system.