This work proposes the basic reference data of occupational dose management and statistical dose distribution with the classification of radiation work groups though analysis of occupational dose distribution. Data on occupational radiation exposure from medical and scientific usage of radiation in Korea Institute of Radiological and Medical Sciences for the years 2002-11 are presented and evaluated with the characteristic tendency of radiation working groups. The results of occupational radiation exposure were measured by personal dosemeters. The monitored occupational exposure dose data were evaluated according to the average effective dose and collective dose. The most annual average effective dose for all occupational radiation workers was under 1 mSv. Considering the dose distribution of each department, most overexposure workers worked in radiopharmaceutical product facilities, nuclear medicine department and radiation oncology department. In addition, no monitored workers were found to have received an occupational exposure over 50 mSv in single year or 100 mSv in this period. Although the trend of occupational exposure was controlled <1 mSv after 2007 and the radiation protection status was sufficient, it was consistently necessary to optimise and reduce the occupational radiation exposure.
Continual Learning (CL) for malware classification tackles the rapidly evolving nature of malware threats and the frequent emergence of new types. Generative Replay (GR)-based CL systems utilize a generative model to produce synthetic versions of past data, which are then combined with new data to retrain the primary model. Traditional machine learning techniques in this domain often struggle with catastrophic forgetting, where a model's performance on old data degrades over time. In this paper, we introduce a GR-based CL system that employs Generative Adversarial Networks (GANs) with feature matching loss to generate high-quality malware samples. Additionally, we implement innovative selection schemes for replay samples based on the model's hidden representations. Our comprehensive evaluation across Windows and Android malware datasets in a class-incremental learning scenario -- where new classes are introduced continuously over multiple tasks -- demonstrates substantial performance improvements over previous methods. For example, our system achieves an average accuracy of 55% on Windows malware samples, significantly outperforming other GR-based models by 28%. This study provides practical insights for advancing GR-based malware classification systems. The implementation is available at \url {https://github.com/MalwareReplayGAN/MalCL}\footnote{The code will be made public upon the presentation of the paper}.
In this study, we optimized the σ-values of a block matching and 3D filtering (BM3D) algorithm to reduce noise in magnetic resonance images. Brain T2-weighted images (T2WIs) were obtained using the BrainWeb simulation program and Rician noise with intensities of 0.05, 0.10, and 0.15. The BM3D algorithm was applied to the optimized BM3D algorithm and compared with conventional noise reduction algorithms using Gaussian, median, and Wiener filters. The clinical feasibility was assessed using real brain T2WIs from the Alzheimer’s Disease Neuroimaging Initiative. Quantitative evaluation was performed using the contrast-to-noise ratio, coefficient of variation, structural similarity index measurement, and root mean square error. The simulation results showed optimal image characteristics and similarity at a σ-value of 0.12, demonstrating superior noise reduction performance. The optimized BM3D algorithm showed the greatest improvement in the clinical study. In conclusion, applying the optimized BM3D algorithm with a σ-value of 0.12 achieved efficient noise reduction.
According to the International Electro-technical Commission, manufacturers of X-ray equipment should indicate the number of radiation doses to which a patient can be exposed. Dose–area product (DAP) meters are readily available devices that provide dose indices. Collimators are the most commonly employed radiation beam restrictors in X-ray equipment. DAP meters are attached to the lower surface of a collimator. A DAP meter consists of a chamber and electronics. This separation makes it difficult for operators to maintain the accuracy of a DAP meter. Developing a comprehensive system that has a DAP meter in place of a mirror in the collimator would be effective for measuring, recording the dose and maintaining the quality of the DAP meter. This study was conducted through experimental measurements and a simulation. A DAP meter built into a collimator was found to be feasible when its reading was multiplied by a correction factor.
Noise in computed tomography (CT) is inevitably generated, which lowers the accuracy of disease diagnosis. The non-local means approach, a software technique for reducing noise, is widely used in medical imaging. In this study, we propose a noise reduction algorithm based on fast non-local means (FNLMs) and apply it to CT images of a phantom created using 3D printing technology. The self-produced phantom was manufactured using filaments with similar density to human brain tissues. To quantitatively evaluate image quality, the contrast-to-noise ratio (CNR), coefficient of variation (COV), and normalized noise power spectrum (NNPS) were calculated. The results demonstrate that the optimized smoothing factors of FNLMs are 0.08, 0.16, 0.22, 0.25, and 0.32 at 0.001, 0.005, 0.01, 0.05, and 0.1 of noise intensities, respectively. In addition, we compared the optimized FNLMs with noisy, local filters and total variation algorithms. As a result, FNLMs showed superior performance compared to various denoising techniques. Particularly, comparing the optimized FNLMs to the noisy images, the CNR improved by 6.53 to 16.34 times, COV improved by 6.55 to 18.28 times, and the NNPS improved by 10
In low-dose computed tomography (LDCT), lung segmentation effectively improves the accuracy of lung cancer diagnosis. However, excessive noise is inevitable in LDCT, which can decrease lung segmentation accuracy. To address this problem, it is necessary to derive an optimized kernel size when using the median modified Wiener filter (MMWF) for noise reduction. Incorrect application of the kernel size can result in inadequate noise removal or blurring, degrading segmentation accuracy. Therefore, various kernel sizes of the MMWF were applied in this study, followed by region-growing-based segmentation and quantitative evaluation. In addition to evaluating the segmentation performance, we conducted a similarity assessment. Our results indicate that the greatest improvement in segmentation performance and similarity was at a kernel size 5 × 5. Compared with the noisy image, the accuracy, F1-score, intersection over union, root mean square error, and peak signal-to-noise ratio using the optimized MMWF were improved by factors of 1.38, 33.20, 64.86, 7.82, and 1.30 times, respectively. In conclusion, we have demonstrated that by applying the MMWF with an appropriate kernel size, the optimization of noise and blur reduction can enhance segmentation performance.
With the introduction of digital radiography, patients undergoing radiographic procedures are subject to being overexposed to radiation. Therefore, it is necessary to estimate the absorbed organ dose and the effective dose, which are significant for patient health, along with body type. During chest radiographic examinations conducted in 899 patients for screening, the absorbed dose of the 13 major organs, the average whole-body dose, and two effective doses weighted by factors published in ICRP 60 and ICRP 103 were calculated on the basis of patient information such as height, weight and examination condition, including kilovolt potential, focus-skin distance and entrance surface dose (ESD), using a PC-based Monte Carlo program simulation. It was found that dose per unit ESD had a tendency to decrease with body mass index (BMI). In particular, the absorbed dose for most organs was larger at high voltages (140 kVp) than at low voltages (120 kVp, 100 kVp). In addition, the effective dose which was based on ICRP 60 and ICRP 103 also represented the same tendency in respect of BMI and tube voltage.
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)