Advancing Brain Tumor Classification through Fine-Tuned Vision Transformers: A Comparative Study of Pre-Trained Models.

This paper presents a comprehensive study on the classification of brain tumor images using five pre-trained vision transformer (ViT) models, namely R50-ViT-l16, ViT-l16, ViT-l32, ViT-b16, and ViT-b32, employing a fine-tuning approach. The objective of this study is to advance the state-of-the-art in brain tumor classification by harnessing the power of these advanced models. The dataset utilized for experimentation consists of a total of 4855 images in the training set and 857 images in the testing set, encompassing four distinct tumor classes. The performance evaluation of each model is conducted through an extensive analysis encompassing precision, recall, F1-score, accuracy, and confusion matrix metrics. Among the models assessed, ViT-b32 demonstrates exceptional performance, achieving a high accuracy of 98.24% in accurately classifying brain tumor images. Notably, the obtained results outperform existing methodologies, showcasing the efficacy of the proposed approach. The contributions of this research extend beyond conventional methods, as it not only employs cutting-edge ViT models but also surpasses the performance of existing approaches for brain tumor image classification. This study not only demonstrates the potential of ViT models in medical image analysis but also provides a benchmark for future research in the field of brain tumor classification.

The Value of Various Post-Processing Modalities of Diffusion Weighted Imaging in the Detection of Multiple Sclerosis.

Diffusion tensor imaging (DTI) showed its adequacy in evaluating the normal-appearing white matter (NAWM) and lesions in the brain that are difficult to evaluate with routine clinical magnetic resonance imaging (MRI) in multiple sclerosis (MS). Recently, MRI systems have been developed with regard to software and hardware, leading to different proposed diffusion analysis methods such as diffusion tensor imaging, q-space imaging, diffusional kurtosis imaging, neurite orientation dispersion and density imaging, and axonal diameter measurement. These methods have the ability to better detect in vivo microstructural changes in the brain than DTI. These different analysis modalities could provide supplementary inputs for MS disease characterization and help in monitoring the disease's progression as well as treatment efficacy. This paper reviews some of the recent diffusion MRI methods used for the assessment of MS in vivo.

Diagnostic reference level for adult pelvic examination in several hospitals of Taif and Kharaj city, Saudi Arabia.

The current study was aimed to estimate the entrance surface air kerma (ESAK, mGy) for adult patients undergoing conventional radiography of Anteroposterior pelvis examination, and finally to establish a local diagnostic reference level (DRL). A total of 500 patients were exposed to diagnostic radiation in four hospitals (coded A, B, C, and D) in Taif and Kharaj city, Saudi Arabia, with different X-ray equipment specifications. Patient demographic data like age (y), body mass index (BMI) in kg/m2 as well as exposure factors and X-ray tube output were recorded. ESAK (mGy) was first calculated using the exposure data and tube output values, then the ESAK values were used to estimate entrance surface dose (ESD). The average BMI was 23.9 kg/m2. The mean tube potential used in A, B, C, and D hospitals and the corresponding estimated ESD were found to be 74.2, 69.8, 73, 76,7 kVp, and 2.54, 2.64, 2.94, 3.03 mGy respectively. The correlation coefficient between ESAK and BMI was found to be 0.98. When compared to computed radiography (CR), the conventional X-ray digital radiography reduces the radiation exposure in pelvic imaging by a factor of 1.18. The third quartile of median proposed a lower than the DRL of the previous studies.

Measuring Awareness of Infection Control Guidelines for Patients with COVID-19 in Radiology Departments in Saudi Arabia.

Due to the contagious nature of the COVID-19 virus, healthcare workers are at a great risk of infection. Since medical imaging plays a significant part in the healthcare system and is often used in the diagnosis of potential COVID-19 patients, the radiology personnel are at a very high risk of becoming infected. PURPOSE: This study aims to assess the enforcement of infection control guidelines for patients with COVID-19 during medical imaging procedures and raise awareness of infection control in different hospitals in Saudi Arabia. METHODS: A total of 128 responses were collected from four hospitals across Saudi Arabia using a new structured questionnaire, which was created for health workers by the WHO specifically for this purpose. Data were collected during the COVID-19 pandemic in April 2020. RESULTS: Most participants correctly followed the guidelines of the WHO and Centers for Disease Control and Prevention (CDC) on infection control in the X-ray and general radiology departments. Guideline awareness was higher among magnetic resonance imaging (MRI) and computerised tomography (CT) radiographers, which reduced the risk of future infections. Out of the total respondents, 98.4% stated that they had received formal training in hand hygiene. Only 40.6% of participants, however, knew that respiratory droplets are the primary mode of transmission of the virus from person to person. CONCLUSION: The knowledge of healthcare professionals in the radiology department regarding infection control needs to be continually assessed. A focus on educational interventions on infection control is required in order to maintain well-informed medical staff.

The Impact of the COVID-19 Pandemic on Medical Imaging Case Volumes in Aseer Region: A Retrospective Study.

COVID-19 has had a significant impact on global health systems. The aim of this study was to evaluate how imaging volumes and imaging types in radiology departments have been affected by the COVID-19 pandemic across different locations. METHODS: Imaging volumes in the Aseer region (in the south of Saudi Arabia) across main hospitals were reviewed retrospectively including all cases referred from different locations (outpatient, inpatient and emergency departments). Data for years 2019 and 2020 were compared. The mean monthly cases were compared using a t-test. RESULTS: The total imaging volumes in 2019 were 205,805 compared to 159,107 in 2020 with a 22.7% overall reduction. A substantial decline was observed in both the April to June and the July to September periods of approximately 42.9% and 44.4%, respectively. With respect to location, between April and June, the greatest decline was observed in outpatient departments (76% decline), followed by emergency departments (25% decline), and the least impact was observed in inpatient departments, with only 6.8% decline over the same period. According to modality type, the greatest decreases were reported in nuclear medicine, ultrasound, MRI, and mammography, by 100%, 76%, 74%, and 66%, respectively. Our results show a statistically significant (p-value ≤ 0.05) decrease of cases in 2020 compared to 2019, except for mammography procedures. CONCLUSION: There has been a significant decline in radiology volumes due to COVID-19. The overall reduction in radiology volumes was dependent on the stage/period of lockdown, location, and imaging modality.

Prevalence and predictors of non-alcoholic fatty liver disease in tertiary care hospital of Taif, Saudi Arabia: A retrospective study.

BACKGROUND: The prevalence of nonalcoholic fatty liver disease (NAFLD) in Saudi Arabia is predicted to exceed 30% by 2030. NAFLD leads to liver fibrosis, thus increasing morbidity and health care burden. Obesity and diabetes have been strongly associated with NAFLD in different cities in Saudi Arabia. OBJECTIVES: Therefore, we aim to determine the prevalence rate of NAFLD and specific risk factors for NAFLD among patients of tertiary care hospital of Taif city. MATERIAL AND METHODS: We retrospectively analyzed the medical records of patients for two years, between Feb 2017 and Feb 2019, (n = 100) referred to the hepatology clinic at King Abdulaziz Specialist Hospital in Taif. The diagnosis of NAFLD was based on the radiology report for patients who were aged >20 years old. Other parameters including fasting blood glucose (FBG), platelets count, alanine transaminase (ALT), aspartate transaminase (AST) and total bilirubin were statistically analyzed. RESULTS: We found that 40% (P < 0.05) of all patients had NAFLD. The results revealed that a significantly high number of patients with NAFLD have high FBG levels (75%, P < 0.0001) and total bilirubin (P < 0.05). Meanwhile, platelet count was significantly reduced in patients with NAFLD (P < 0.05). CONCLUSION: NAFLD can be a serious health problem in the Taif region. In addition, high FBG is a significant specific risk factor for NAFLD. Health care providers should pay more attention to limiting the prevalence of NAFLD and its risk factors.