Deep learning-based automated bone age estimation for Saudi patients on hand radiograph images: a retrospective study.

PURPOSE: In pediatric medicine, precise estimation of bone age is essential for skeletal maturity evaluation, growth disorder diagnosis, and therapeutic intervention planning. Conventional techniques for determining bone age depend on radiologists' subjective judgments, which may lead to non-negligible differences in the estimated bone age. This study proposes a deep learning-based model utilizing a fully connected convolutional neural network(CNN) to predict bone age from left-hand radiographs. METHODS: The data set used in this study, consisting of 473 patients, was retrospectively retrieved from the PACS (Picture Achieving and Communication System) of a single institution. We developed a fully connected CNN consisting of four convolutional blocks, three fully connected layers, and a single neuron as output. The model was trained and validated on 80% of the data using the mean-squared error as a cost function to minimize the difference between the predicted and reference bone age values through the Adam optimization algorithm. Data augmentation was applied to the training and validation sets yielded in doubling the data samples. The performance of the trained model was evaluated on a test data set (20%) using various metrics including, the mean absolute error (MAE), median absolute error (MedAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The code of the developed model for predicting the bone age in this study is available publicly on GitHub at https://github.com/afiosman/deep-learning-based-bone-age-estimation . RESULTS: Experimental results demonstrate the sound capabilities of our model in predicting the bone age on the left-hand radiographs as in the majority of the cases, the predicted bone ages and reference bone ages are nearly close to each other with a calculated MAE of 2.3 [1.9, 2.7; 0.95 confidence level] years, MedAE of 2.1 years, RMAE of 3.0 [1.5, 4.5; 0.95 confidence level] years, and MAPE of 0.29 (29%) on the test data set. CONCLUSION: These findings highlight the usability of estimating the bone age from left-hand radiographs, helping radiologists to verify their own results considering the margin of error on the model. The performance of our proposed model could be improved with additional refining and validation.

Enhancing radiation safety awareness and practices among female radiographers: a comprehensive approach.

OBJECTIVE: This study evaluates the level of radiation safety awareness and adherence to protective practices among pregnant female radiographers in the United Arab Emirates, aiming to identify gaps and develop targeted interventions for enhancing occupational safety. METHODS: Employing a cross-sectional design, the study surveyed 133 female radiographers using a self-developed questionnaire covering demographics, awareness and knowledge, workplace practices, communication, and satisfaction. RESULTS: The survey showed high awareness among radiographers, with 97% acknowledging radiation risks during pregnancy, although 42.9% had not received formal training. Concerns over long-term health effects were significant, with 66.2% of participants worried about potential impacts. Despite these concerns, 83.5% had been informed about radiation risks and protective measures, indicating active information provision in many workplaces. However, inconsistencies in information dissemination across different work settings were noted. CONCLUSIONS: The findings highlight the need for standardized radiation safety protocols for pregnant radiographers. The variability in safety training and information dissemination suggests the importance of establishing uniform safety practices. Recommendations include developing comprehensive education and training programs for pregnant radiographers, ensuring open communication for radiation safety and pregnancy-related concerns, and enforcing clear guidelines for workplace accommodations.

Optimizing CT Abdomen-Pelvis Scan Radiation Dose: Examining the Role of Body Metrics (Waist Circumference, Hip Circumference, Abdominal Fat, and Body Mass Index) in Dose Efficiency.

Objective: This study investigates the correlation between patient body metrics and radiation dose in abdominopelvic CT scans, aiming to identify significant predictors of radiation exposure. Methods: Employing a cross-sectional analysis of patient data, including BMI, abdominal fat, waist, abdomen, and hip circumference, we analyzed their relationship with the following dose metrics: the CTDIvol, DLP, and SSDE. Results: Results from the analysis of various body measurements revealed that BMI, abdominal fat, and waist circumference are strongly correlated with increased radiation doses. Notably, the SSDE, as a more patient-centric dose metric, showed significant positive correlations, especially with waist circumference, suggesting its potential as a key predictor for optimizing radiation doses. Conclusions: The findings suggest that incorporating patient-specific body metrics into CT dosimetry could enhance personalized care and radiation safety. Conclusively, this study highlights the necessity for tailored imaging protocols based on individual body metrics to optimize radiation exposure, encouraging further research into predictive models and the integration of these metrics into clinical practice for improved patient management.

Vein of Galen aneurysmal malformation associated with brain abscess: A computed tomography case report.

Vein of Galen malformation (VGM) is a rare congenital, uncommon intracerebral vascular anomaly rarely complicated with the development of brain abscess as secondary to primary infection or after endovascular treatment. We report a very rare finding of a vein of Galen aneurysm associated with a large brain abscess at the time of diagnosis. A 12-year-old boy with a high-grade fever, severe headache, and recurrent episodes of convulsions came into the radiology department of Kassala Advanced Diagnostic Center. On a Siemens 16-slice scanner, brain non-contrast enhanced computed tomography (NECT) and contrast enhanced CT (CECT) was used to determine the source of the acute headache and convulsions which revealed a right frontal peripherally enhancing cystic lesion measuring 5.7 × 4.7 × 5.3 cm2 surrounded by massive vasogenic edema causing mass effect with midline shift to the left side by 1.5 cm suggestive of brain abscess. There is evidence of another avidly enhancing lesion seen within the third ventricle continuous with a straight sinus surrounded by extensive vascular loops consistent with an aneurysm of the vein of Galen, it was causing compression of the cerebral aqueduct with upstream mild hydrocephalus with dilated both lateral ventricles. Late presentation, diagnosis, and treatment also lead to an increase in the morbidities and mortalities of such case conditions. Urgent intervention should be considered for better outcomes.

The impact of different imaging modalities in diagnosis and management of patient with dural arteriovenous fistula: A rare case report.

In vascular neurosurgery, dural arteriovenous fistulas (DAVFs) are a difficult, challenging condition whose natural history and therapy are still debated. This case report presented a 30-year-old male patient who experienced intermittent headaches for two months, along with gradual weakness in all four limbs, resulting in quadriplegia. Magnetic resonance imaging (MRI), computed tomography (CT), and digital subtraction angiography (DSA) played a significant role in the diagnosis of the patient, in which the final diagnosis was vascular myelopathy due to Dural arteriovenous fistula (DAVF). A successful embolization procedure of arteriovenous fistula using balloon-assisted liquid embolic agents, through branches of the right occipital artery was performed, resulting in complete obliteration of the fistula. In order to improve the neurovascular symptoms that had previously been reported, the patient was effectively undergoing rehabilitation, with notable progress.

A triple kidney: Coexistence of normal left kidney and mal-rotated horseshoe anomaly: A rare case report.

The occurrence of triple kidneys, involving a normal kidney and a malrotation horseshoe kidney, is an extremely infrequent condition. This case report demonstrates a triple, mal-rotated horseshoe kidneys coexist with an upper junction stone, alongside a normal left kidney showing normal Doppler vascularity, as observed in an ultrasound examination for 18-year-old male complaints of diffuse periumbilical pain and burning micturition. Laboratory investigation revealed normal creatinine level, and presence of urinary tract infection. Management option for this case are antibiotic therapy and surgical intervention for horseshoe kidney stone. Regular monitoring of kidney function, other radiographic imaging studies, and follow-up to assess the efficacy of the treatment, and detect any further complications are essential.

Olecranon stress fracture in a gymnastics player: Insight into an early detection and integrated care approach: Case report.

We describe a case report of a 13 year-old a gymnastic athlete who was diagnosed with an olecranon stress fracture associated with mild medial epicondyle apophysitis, Following a brief review of the literature on this case, the researchers call attention to the significance of and imaging assessment especially MR in determining the correct diagnosis and identifying concomitant injuries. MRI findings concluded firstly a marked bone marrow edema seen at the posterior medial aspect of the olecranon with linear low signal traversing the olecranon related to a stress fracture. Secondly, subchondral linear low signal and bone marrow edema at the radial head related to another stress fracture/reaction injury. Thirdly, bone marrow edema at the medial apophysis with overlying soft tissue edema suggestive for medial epicondylitis.

The efficacy of machine learning models in lung cancer risk prediction with explainability.

Among many types of cancers, to date, lung cancer remains one of the deadliest cancers around the world. Many researchers, scientists, doctors, and people from other fields continuously contribute to this subject regarding early prediction and diagnosis. One of the significant problems in prediction is the black-box nature of machine learning models. Though the detection rate is comparatively satisfactory, people have yet to learn how a model came to that decision, causing trust issues among patients and healthcare workers. This work uses multiple machine learning models on a numerical dataset of lung cancer-relevant parameters and compares performance and accuracy. After comparison, each model has been explained using different methods. The main contribution of this research is to give logical explanations of why the model reached a particular decision to achieve trust. This research has also been compared with a previous study that worked with a similar dataset and took expert opinions regarding their proposed model. We also showed that our research achieved better results than their proposed model and specialist opinion using hyperparameter tuning, having an improved accuracy of almost 100% in all four models.

Secondary Sjögren's syndrome in a rheumatoid arthritis patient: A case report and review of literature.

Secondary Sjogren's syndrome (sSS) is a medical condition that occurs in individuals with autoimmune diseases such as systemic lupus erythematosus (SLE) and rheumatoid arthritis. It predominantly affects females rather than males. We present a case of a 32-year-old female with a 3-year history of rheumatoid arthritis (RA) who presented to the internal medicine and rheumatology clinic with several complaints, including swelling and tenderness in her left jaw, dry mouth (xerostomia), irritated eyes (xerophthalmia), severe joint pain, and a decreased in saliva production. The blood tests demonstrate the presence of anti-SSA and anti-SSB autoantibodies and elevation of total leukocyte count (TLC), erythrocyte sedimentation rate (ESR), and C-reactive protein (CRP) levels, indicating inflammation. A high-frequency ultrasound confirmed the diagnosis of Secondary Sjogren's syndrome grade II, specifically affecting the left parotid gland (PG).

Evaluation of the Impact of Artificial Intelligence on Clinical Practice of Radiology in Saudi Arabia.

Background: Artificial Intelligence (AI) is becoming integral to the health sector, particularly radiology, because it enhances diagnostic accuracy and optimizes patient care. This study aims to assess the awareness and acceptance of AI among radiology professionals in Saudi Arabia, identifying the educational and training needs to bridge knowledge gaps and enhance AI-related competencies. Methods: This cross-sectional observational study surveyed radiology professionals across various hospitals in Saudi Arabia. Participants were recruited through multiple channels, including direct invitations, emails, social media, and professional societies. The survey comprised four sections: demographic details, perceptions of AI, knowledge about AI, and willingness to adopt AI in clinical practice. Results: Out of 374 radiology professionals surveyed, 45.2% acknowledged AI's significant impact on their field. Approximately 44% showed enthusiasm for AI adoption. However, 58.6% reported limited AI knowledge and inadequate training, with 43.6% identifying skill development and the complexity of AI educational programs as major barriers to implementation. Conclusion: While radiology professionals in Saudi Arabia are generally positive about integrating AI into clinical practice, significant gaps in knowledge and training need to be addressed. Tailored educational programs are essential to fully leverage AI's potential in improving medical imaging practices and patient care outcomes.

Persistent Mullerian duct syndrome with polycystic ovary in a young adult: A rare case report.

Persistent Mullerian Duct Syndrome (PMDS) is a type of pseudohermaphroditism that occurs in males. It is an autosomal recessive type of familial disease that is commonly associated with a history of consanguinity. We have documented this case of a 22-year-old adult male who came with acute right iliac pain; after an ultrasound scan and hormone investigations, he was diagnosed with polycystic ovarian syndrome (PCOS).

Monkeypox genome mutation analysis using a timeseries model based on long short-term memory.

Monkeypox is a double-stranded DNA virus with an envelope and is a member of the Poxviridae family's Orthopoxvirus genus. This virus can transmit from human to human through direct contact with respiratory secretions, infected animals and humans, or contaminated objects and causing mutations in the human body. In May 2022, several monkeypox affected cases were found in many countries. Because of its transmitting characteristics, on July 23, 2022, a nationwide public health emergency was proclaimed by WHO due to the monkeypox virus. This study analyzed the gene mutation rate that is collected from the most recent NCBI monkeypox dataset. The collected data is prepared to independently identify the nucleotide and codon mutation. Additionally, depending on the size and availability of the gene dataset, the computed mutation rate is split into three categories: Canada, Germany, and the rest of the world. In this study, the genome mutation rate of the monkeypox virus is predicted using a deep learning-based Long Short-Term Memory (LSTM) model and compared with Gated Recurrent Unit (GRU) model. The LSTM model shows "Root Mean Square Error" (RMSE) values of 0.09 and 0.08 for testing and training, respectively. Using this time series analysis method, the prospective mutation rate of the 50th patient has been predicted. Note that this is a new report on the monkeypox gene mutation. It is found that the nucleotide mutation rates are decreasing, and the balance between bi-directional rates are maintained.

Exploring Radiographers' Engagement in Research: Motivation and Barriers in Five Arab Countries.

(1) Background: This study aims to comprehensively understand the motivations driving radiographers in five Arab countries to engage in research. (2) Methods: A cross-sectional study employing an anonymous online survey was conducted for 12 weeks from May to July 2023. The study sample consisted of 250 radiographers, with equal representation from Iraq, the Kingdom of Saudi Arabia, Palestine, Sudan, and the United Arab Emirates. (3) Results: Overall, the participants showed limited involvement in research-related activities in all five countries, particularly in presenting at conferences and publishing in peer-reviewed journals. Most participants believed research positively impacts their professional development (34.8%) and patient care and outcomes (40%). The participants perceived professional development (36.4%) as a key motivator for research engagement. A significant majority (81.6%) expressed motivation to start research in clinical practice. A total of 66.8% found research opportunities available during clinical practice. Barriers included time constraints (56%), limited resources (47.2%), and lack of support and skills (33.2% and 32%, respectively). (4) Conclusion: This study emphasises the need for targeted strategies to enhance research engagement among radiographers in the Arab region. Addressing barriers, such as time constraints and resource limitations, while leveraging intrinsic motivators, such as professional development, is crucial for fostering a culture of research-driven excellence in radiography.

Assessment of the Knowledge and Practice of Infection Control among Radiographers in Saudi Arabia: A Cross-Sectional Survey Study.

Effective control of healthcare-associated infections (HAIs) involves a collaborative effort among various healthcare stakeholders, including healthcare workers, patients, and professionals. Radiographers, as essential members of the healthcare team, play a crucial role in HAI prevention by diligently adhering to standard infection control precautions (SICP) and maintaining a high level of knowledge regarding infection control procedures. The study aimed to assess the knowledge and practice of radiographers concerning infection control in radiology departments in Saudi Arabia. METHODS: A descriptive cross-sectional study was conducted in Saudi Arabia in the period from February to May 2022, with data collected using an online survey in the form of a google forms questionnaire disseminated through social media as an electronic link and including the patient's demographic characteristic such as age, gender, education level, experience, and prior infection control training and multiple closed ended questions to assess knowledge of standard infection control precautions and the practice of infection control. Overall, 113 participants responded to the survey and entered their responses directly, and the data were analyzed using the SPSS (statistical package for social science). RESULTS: The study revealed that the mean score of knowledge and awareness of the practice of infection control among radiographers in Saudi Arabia was (63.0 and 61.9, respectively), which were considered moderate levels. Females were significantly more knowledgeable about infection control and more aware of the practice than males (p-values = 0.019). The participants who previously attended courses of infection control training had a significantly higher score with a mean rank of (60.9) than those who had not (43.4), (p-value = 0.013). The radiographers' level of experience, age, and academic qualification had no significant influence on overall knowledge and practice of infection control (p-values > 0.05). CONCLUSIONS: In Saudi Arabia, radiographers have a moderate level of knowledge and practice of infection control. There is a need for an ongoing training and education program for practicing radiographers to ensure they perform better in infection control measures.

The impact of health volunteering of radiology students on improving their self-skills and practical capabilities in the Kingdom of Saudi Arabia.

Background: Volunteering is a beneficial activity with a wide range of positive outcomes, from the individual to the communal level. In many ways, volunteering has a positive impact on the development of a volunteer's personality and experience. This study aimed to evaluate the impact of health volunteering on improving the self-skills and practical capacities of students in the western region of the Kingdom of Saudi Arabia. Materials and methods: The study was a descriptive cross-sectional electronic web-based survey that was submitted on a web-based questionnaire; 183 students answered the survey, and then, the data were analyzed using SPSS. Results: This study shows that 95.6% of participants agree and strongly agree that the health volunteering experience was useful, 2.7% of the participants neither agree nor disagree, and 1.6% disagree and strongly disagree. Regarding the distribution of the participants on skills learned from volunteering experience, the largest proportion of student (36.1%) volunteers in the health sector acquired communication skills and the smallest proportion of student (14.8%) volunteers in the acquired time management skills. Regarding the disadvantages, 81.4% of the participants do not think there were any disadvantages to their previous health volunteering experience, while only 18.6% of them think there were any disadvantages to their previous health volunteering experience. Additionally, the study found that the type of the sector affects the skills acquired from health volunteering. Conclusion: Research revealed that the majority considered volunteering a great experience. Volunteering increased the self-skills and practical capacities of radiology students, which proved the hypothesis.

How Different Preparation Techniques Affect MRI-Induced Anxiety of MRI Patients: A Preliminary Study.

BACKGROUND: Magnetic resonance imaging (MRI) exams may cause patients to feel anxious before or during the scan, which affects the scanning outcome and leads to motion artifacts. Adequate preparation can effectively alleviate patients' anxiety before the scan. We aimed to assess the effect of different preparation methods on MRI-induced anxiety: We conducted a prospective randomized study on MRI patients between March and May 2022. We divided 30 patients into two groups: the control group, which received routine preparation (RP), and the experimental group, which received video preparation (VP). We used the State-Trait Anxiety Inventory (STAI) to measure anxiety levels before and after the interventions. We assessed patients' self-satisfaction after the scan: After preparation, VP (STAI mean = 10.7500) and RP (STAI mean = 12.7857), we observed a significant association between the pre- and post-STAI results in VP (p = 0.025). The effects of both methods in decreasing anxiety were more significant for first-timers (p = 0.009 in RP/0.014 in VP). We noted high satisfaction levels for both forms of preparation. The VP technique was superior in reducing patient anxiety, especially in first-time MRI patients. Hence, VP techniques can be used in different clinical settings to reduce anxiety and facilitate patients' understanding of the instructions given.

Breast Cancer Classification by Using Multi-Headed Convolutional Neural Network Modeling.

Breast cancer is one of the most widely recognized diseases after skin cancer. Though it can occur in all kinds of people, it is undeniably more common in women. Several analytical techniques, such as Breast MRI, X-ray, Thermography, Mammograms, Ultrasound, etc., are utilized to identify it. In this study, artificial intelligence was used to rapidly detect breast cancer by analyzing ultrasound images from the Breast Ultrasound Images Dataset (BUSI), which consists of three categories: Benign, Malignant, and Normal. The relevant dataset comprises grayscale and masked ultrasound images of diagnosed patients. Validation tests were accomplished for quantitative outcomes utilizing the exhibition measures for each procedure. The proposed framework is discovered to be effective, substantiating outcomes with only raw image evaluation giving a 78.97% test accuracy and masked image evaluation giving 81.02% test precision, which could decrease human errors in the determination cycle. Additionally, our described framework accomplishes higher accuracy after using multi-headed CNN with two processed datasets based on masked and original images, where the accuracy hopped up to 92.31% (±2) with a Mean Squared Error (MSE) loss of 0.05. This work primarily contributes to identifying the usefulness of multi-headed CNN when working with two different types of data inputs. Finally, a web interface has been made to make this model usable for non-technical personals.

Artificial Intelligence in Pediatric Cardiology: A Scoping Review.

The evolution of AI and data science has aided in mechanizing several aspects of medical care requiring critical thinking: diagnosis, risk stratification, and management, thus mitigating the burden of physicians and reducing the likelihood of human error. AI modalities have expanded feet to the specialty of pediatric cardiology as well. We conducted a scoping review searching the Scopus, Embase, and PubMed databases covering the recent literature between 2002-2022. We found that the use of neural networks and machine learning has significantly improved the diagnostic value of cardiac magnetic resonance imaging, echocardiograms, computer tomography scans, and electrocardiographs, thus augmenting the clinicians' diagnostic accuracy of pediatric heart diseases. The use of AI-based prediction algorithms in pediatric cardiac surgeries improves postoperative outcomes and prognosis to a great extent. Risk stratification and the prediction of treatment outcomes are feasible using the key clinical findings of each CHD with appropriate computational algorithms. Notably, AI can revolutionize prenatal prediction as well as the diagnosis of CHD using the EMR (electronic medical records) data on maternal risk factors. The use of AI in the diagnostics, risk stratification, and management of CHD in the near future is a promising possibility with current advancements in machine learning and neural networks. However, the challenges posed by the dearth of appropriate algorithms and their nascent nature, limited physician training, fear of over-mechanization, and apprehension of missing the 'human touch' limit the acceptability. Still, AI proposes to aid the clinician tomorrow with precision cardiology, paving a way for extremely efficient human-error-free health care.