Pediatric Imaging Research Articles

Safety and efficacy of ketamine-propofol in pediatric magnetic resonance imaging: A prospective study

Safety and efficacy of ketamine-propofol in pediatric magnetic resonance imaging: A prospective study

Wrist fracture detection using self-supervised learning methodology

Objectives: This study aimed to assist radiologists in faster and more accurate diagnosis by automating bone fracture detection in pediatric trauma wrist radiographic images using self-supervised learning. This addresses data labeling challenges associated with traditional deep learning models in medical imaging. Methods: In this study, we trained the model backbone for feature extraction. Then, we used this backbone to train a complete classification model for classifying images as fracture or non-fracture on the publically available Kaggle and GRAZPERDWRI-DX dataset using ResNet-18 in pediatric wrist radiographs. Results: The resulting output revealed that the model was able to detect fracture and non-fracture images with 94.10% accuracy, 93.21% specificity, and an area under the receiver operating characteristics of 94.12%. Conclusion: This self-supervised model showed a promising approach and paved the way for efficient and accurate fracture detection, ultimately enhancing radiological diagnosis without relying on extensive labeled data.

Combined sedation in pediatric magnetic resonance imaging: determination of median effective dose of intranasal dexmedetomidine combined with oral midazolam

BackgroundThe exact median effective dose (ED50) of intranasal dexmedetomidine combined with oral midazolam sedation for magnetic resonance imaging (MRI) examination in children remains unknow and the aim of this study was to determine the ED50 of their combination.MethodsThis is a prospective dose-finding study. A total of 53 children aged from 2 months to 6 years scheduled for MRI examination from February 2023 to April 2023 were randomly divided into group D (to determine the ED50 of intranasal dexmedetomidine) and group M (to determine the ED50 of oral midazolam). The dosage of dexmedetomidine and midazolam was adjusted according to the modified Dixon’s up-and-down method, and the ED50 was calculated with a probit regression approach.ResultsThe ED50 of intranasal dexmedetomidine when combined with 0.5 mg∙kg− 1 oral midazolam was 0.39 µg∙kg− 1 [95% confidence interval (CI) 0.30 to 0.46 µg∙kg− 1] while the ED50 of oral midazolam was 0.17 mg∙kg− 1 (95% CI 0.01 to 0.29 mg∙kg− 1) when combined with 1 µg∙kg− 1 intranasal dexmedetomidine. The sedation onset time of children with successful sedation in group D was longer than in group M (30.0[25.0, 38.0]vs 19.5[15.0, 35.0] min, P < 0.05). No other adverse effects were observed in the day and 24 h after medication except one dysphoria.ConclusionThis drug combination sedation regimen appears suitable for children scheduled for MRI examinations, offering a more precise approach to guide the clinical use of sedative drugs in children.Trial registrationChinese Clinical Trial Registry, identifier: ChiCTR2300068611(24/02/2023).

Development of a diagnostic support system for distal humerus fracture using artificial intelligence.

AI has shown promise in automating and improving various tasks, including medical image analysis. Distal humerus fractures are a critical clinical concern that requires early diagnosis and treatment to avoid complications. The standard diagnostic method involves X-ray imaging, but subtle fractures can be missed, leading to delayed or incorrect diagnoses. Deep learning, a subset of artificial intelligence, has demonstrated the ability to automate medical image analysis tasks, potentially improving fracture identification accuracy and reducing the need for additional and cost-intensive imaging modalities (Schwarz et al. 2023). This study aims to develop a deep learning-based diagnostic support system for distal humerus fractures using conventional X-ray images. The primary objective of this study is to determine whether deep learning can provide reliable image-based fracture detection recommendations for distal humerus fractures. Between March 2017 and March 2022, our tertiary hospital's PACS data were evaluated for conventional radiography images of the anteroposterior (AP) and lateral elbow for suspected traumatic distal humerus fractures. The data set consisted of 4931 images of patients sevenyears and older, after excluding paediatric images below sevenyears due to the absence of ossification centres. Two senior orthopaedic surgeons with 12 + years of experience reviewed and labelled the images as fractured or normal. The data set was split into training sets (79.88%) and validation tests (20.1%). Image pre-processing was performed by cropping the images to 224 × 224 pixels around the capitellum, and the deep learning algorithm architecture used was ResNet18. The deep learning model demonstrated an accuracy of 69.14% in the validation test set, with a specificity of 95.89% and a positive predictive value (PPV) of 99.47%. However, the sensitivity was 61.49%, indicating that the model had a relatively high false negative rate. ROC analysis showed an AUC of 0.787 when deep learning AI was the reference and an AUC of 0.580 when the most senior orthopaedic surgeon was the reference. The performance of the model was compared with that of other orthopaedic surgeons of varying experience levels, showing varying levels of diagnostic precision. The developed deep learning-based diagnostic support system shows potential for accurately diagnosing distal humerus fractures using AP and lateral elbow radiographs. The model's specificity and PPV indicate its ability to mark out occult lesions and has a high false positive rate. Further research and validation are necessary to improve the sensitivity and diagnostic accuracy of the model for practical clinical implementation.

Organisation of paediatric echocardiography laboratories and governance of echocardiography services and training in Europe: current status, disparities, and potential solutions. A survey from the Association for European Paediatric and Congenital Cardiology (AEPC) imaging working group.

There is limited data on the organisation of paediatric echocardiography laboratories in Europe. A structured and approved questionnaire was circulated across all 95 Association for European Paediatric and Congenital Cardiology affiliated centres. The aims were to evaluate: (1) facilities in paediatric echocardiography laboratories across Europe, (2) accredited laboratories, (3) medical/paramedical staff employed, (4) time for echocardiographic studies and reporting, and (5) training, teaching, quality improvement, and research programs. Respondents from forty-three centres (45%) in 22 countries completed the survey. Thirty-six centres (84%) have a dedicated paediatric echocardiography laboratory, only five (12%) of which reported they were European Association of Cardiovascular Imaging accredited. The median number of echocardiography rooms was three (range 1-12), and echocardiography machines was four (range 1-12). Only half of all the centres have dedicated imaging physiologists and/or nursing staff, while the majority (79%) have specialist imaging cardiologist(s). The median (range) duration of time for a new examination was 45 (20-60) minutes, and for repeat examination was 20 (5-30) minutes. More than half of respondents (58%) have dedicated time for reporting. An organised training program was present in most centres (78%), 44% undertake quality assurance, and 79% perform research. Guidelines for performing echocardiography were available in 32 centres (74%). Facilities, staffing levels, study times, standards in teaching/training, and quality assurance vary widely across paediatric echocardiography laboratories in Europe. Greater support and investment to facilitate improvements in staffing levels, equipment, and governance would potentially improve European paediatric echocardiography laboratories.

Enhancing wrist abnormality detection with YOLO: Analysis of state-of-the-art single-stage detection models

Diagnosing and treating abnormalities in the wrist, specifically distal radius, and ulna fractures, is a crucial concern among children, adolescents, and young adults, with a higher incidence rate during puberty. However, the scarcity of radiologists and the lack of specialized training among medical professionals pose a significant risk to patient care. This problem is further exacerbated by the rising number of imaging studies and limited access to specialist reporting in certain regions. This highlights the need for innovative solutions to improve the diagnosis and treatment of wrist abnormalities. Automated wrist fracture detection using object detection has shown potential, but current studies mainly use two-stage detection methods with limited evidence for single-stage effectiveness. This study employs state-of-the-art single-stage deep neural network-based detection models YOLOv5, YOLOv6, YOLOv7, and YOLOv8 to detect wrist abnormalities. Through extensive experimentation, we found that these YOLO models outperform the commonly used two-stage detection algorithm, Faster R-CNN, in fracture detection. Additionally, compound-scaled variants of each YOLO model were compared, with YOLOv8 m demonstrating a highest fracture detection sensitivity of 0.92 and mean average precision (mAP) of 0.95. On the other hand, YOLOv6 m achieved the highest sensitivity across all classes at 0.83. Meanwhile, YOLOv8x recorded the highest mAP of 0.77 for all classes on the GRAZPEDWRI-DX pediatric wrist dataset, highlighting the potential of single-stage models for enhancing pediatric wrist imaging.

Intelligent ultrafast total-body PET for sedation-free pediatric [18F]FDG imaging.

This study aims to develop deep learning techniques on total-body PET to bolster the feasibility of sedation-free pediatric PET imaging. A deformable 3D U-Net was developed based on 245 adult subjects with standard total-body PET imaging for the quality enhancement of simulated rapid imaging. The developed method was first tested on 16 children receiving total-body [18F]FDG PET scans with standard 300-s acquisition time with sedation. Sixteen rapid scans (acquisition time about 3 s, 6 s, 15 s, 30 s, and 75 s) were retrospectively simulated by selecting the reconstruction time window. In the end, the developed methodology was prospectively tested on five children without sedation to prove the routine feasibility. The approach significantly improved the subjective image quality and lesion conspicuity in abdominal and pelvic regions of the generated 6-s data. In the first test set, the proposed method enhanced the objective image quality metrics of 6-s data, such as PSNR (from 29.13 to 37.09, p < 0.01) and SSIM (from 0.906 to 0.921, p < 0.01). Furthermore, the errors of mean standardized uptake values (SUVmean) for lesions between 300-s data and 6-s data were reduced from 12.9 to 4.1% (p < 0.01), and the errors of max SUV (SUVmax) were reduced from 17.4 to 6.2% (p < 0.01). In the prospective test, radiologists reached a high degree of consistency on the clinical feasibility of the enhanced PET images. The proposed method can effectively enhance the image quality of total-body PET scanning with ultrafast acquisition time, leading to meeting clinical diagnostic requirements of lesion detectability and quantification in abdominal and pelvic regions. It has much potential to solve the dilemma of the use of sedation and long acquisition time that influence the health of pediatric patients.

Paediatric Thoracic Imaging in Cystic Fibrosis in the Era of Cystic Fibrosis Transmembrane Conductance Regulator Modulation.

Cystic fibrosis (CF) is one of the most common progressive life-shortening genetic conditions worldwide. Ground-breaking translational research has generated therapies that target the primary cystic fibrosis transmembrane conductance regulator (CFTR) defect, known as CFTR modulators. A crucial aspect of paediatric CF disease is the development and progression of irreversible respiratory disease in the absence of clinical symptoms. Accurate thoracic diagnostics have an important role to play in this regard. Chest radiographs are non-specific and insensitive in the context of subtle changes in early CF disease, with computed tomography (CT) providing increased sensitivity. Recent advancements in imaging hardware and software have allowed thoracic CTs to be acquired in paediatric patients at radiation doses approaching that of a chest radiograph. CFTR modulators slow the progression of CF, reduce the frequency of exacerbations and extend life expectancy. In conjunction with advances in CT imaging techniques, low-dose thorax CT will establish a central position in the routine care of children with CF. International guidelines regarding the choice of modality and timing of thoracic imaging in children with CF are lagging behind these rapid technological advances. The continued progress of personalised medicine in the form of CFTR modulators will promote the emergence of personalised radiological diagnostics.

Safety and therapeutic efficacy of 577 nm yellow solid krypton laser for retinopathy of prematurity; A prospective pilot study.

To evaluate the outcome of 577 nm yellow solid krypton laser as an independent treatment modality for Retinopathy of Prematurity. Prospective, non-comparative, non-randomized, interventional. A prospective pilot study was conducted on 30 treatment eyes with retinopathy of prematurity (ROP) who underwent treatment with a 577 nm yellow solid state krypton laser. 3nethraNEO pediatric retinal imaging system was used to screen these infants born between March to August 2022. Pre procedure data such as gestational age (weeks), birth weight (g), and exposure to risk factors were recorded. Power (mW), exposure duration (msec), and number of laser spots administered were noted. Pain was assessed using the Neonatal Pain/Agitation and Sedation Scale (N-PASS). Post procedure data such as regression, persistence or reactivation of disease, and adverse effects were looked for. All eyes were followed up for a period of 3 months. Chi-square test, Fisher's exact test. Out of 30 eyes, 09 (30%) had type I and 21 (70%) had non-type I ROP. In type I disease, the mean power used was 88+/-10 mW with exposure duration of 130+/-27 msec and an average number of 890+/-260 burns were administered. In non-type I disease, the mean power used was 87+/-10 mW with an exposure duration of 150 ms and an average number of 900+/-290 burns were administered. The mean pain score calculated was 5 in type I and 6 in non-type I ROP. All eyes showed regression of disease after treatment. 577 nm yellow solid krypton laser was safe and effective in treating retinopathy of prematurity disease.

Construction and validation of an infant chest phantom for paediatric computed tomography

Paediatric imaging protocols should be carefully optimised to maintain the desired image quality while minimising the delivered patient dose. A paediatric chest phantom was designed, constructed and evaluated to optimise chest CT examinations for infants. The phantom was designed to enable dosimetry and image quality measurements within the anthropomorphic structure. It was constructed using tissue equivalent materials to mimic thoracic structures of infants, aged 0–6 months. The phantom materials were validated across a range of diagnostic tube voltages with resulting CT numbers found equivalent to paediatric tissues observed via a survey of clinical paediatric chest studies. The phantom has been successfully used to measure radiation dose and evaluate various image quality parameters for paediatric specific protocols.

Quantitative Skeletal Imaging and Image-Based Modeling in Pediatric Orthopaedics.

Musculoskeletal imaging serves a critical role in clinical care and orthopaedic research. Image-based modeling is also gaining traction as a useful tool in understanding skeletal morphology and mechanics. However, there are fewer studies on advanced imaging and modeling in pediatric populations. The purpose of this review is to provide an overview of recent literature on skeletal imaging modalities and modeling techniques with a special emphasis on current and future uses in pediatric research and clinical care. While many principles of imaging and 3D modeling are relevant across the lifespan, there are special considerations for pediatric musculoskeletal imaging and fewer studies of 3D skeletal modeling in pediatric populations. Improved understanding of bone morphology and growth during childhood in healthy and pathologic patients may provide new insight into the pathophysiology of pediatric-onset skeletal diseases and the biomechanics of bone development. Clinical translation of 3D modeling tools developed in orthopaedic research is limited by the requirement for manual image segmentation and the resources needed for segmentation, modeling, and analysis. This paper highlights the current and future uses of common musculoskeletal imaging modalities and 3D modeling techniques in pediatric orthopaedic clinical care and research.

Incidental Thalamic Lesions Identified on Brain MRI in Pediatric and Young Adult Patients: Imaging Features and Natural History.

Nonspecific, localized thalamic signal abnormalities of uncertain significance are occasionally found on pediatric brain MR imaging. The goal of this study is to describe the MR imaging appearance and natural history of these lesions in children and young adults. This retrospective study evaluated clinically acquired brain MR imaging examinations obtained from February 1995 to March 2022 at a large, tertiary care pediatric hospital. Examinations with non-mass-like and nonenhancing thalamic lesions were identified based on term search of MR imaging reports. A total of 221 patients formed the initial group for imaging assessment. Additional exclusions during imaging review resulted in 171 patients. Imaging appearance and size changes were assessed at baseline and at follow-up examinations. A total of 171 patients (102 male) at a median age of 11 years (range: 1-23 years), 568 MR imaging examinations, and 180 thalamic lesions were included. Median time from baseline to the last follow-up MR imaging was 542 days (range: 46-5730 days). No lesion enhanced at any time point. On imaging follow-up, 11% of lesions (18/161) became smaller, 10% (16/161) resolved, 73% (118/161) remained stable, and 6% (9/161) increased in size at some point during evaluation. Median time interval from baseline to enlargement was 430 days (range: 136-1074 days). Most incidental, non-mass-like thalamic signal abnormalities were stable, decreased in size, or resolved on follow-up imaging and are likely of no clinical significance. Surveillance strategies with longer follow-up intervals may be adequate in the management of such findings.

Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images.

Model initialization techniques are vital for improving the performance and reliability of deep learning models in medical computer vision applications. While much literature exists on non-medical images, the impacts on medical images, particularly chest X-rays (CXRs) are less understood. Addressing this gap, our study explores three deep model initialization techniques: Cold-start, Warm-start, and Shrink and Perturb start, focusing on adult and pediatric populations. We specifically focus on scenarios with periodically arriving data for training, thereby embracing the real-world scenarios of ongoing data influx and the need for model updates. We evaluate these models for generalizability against external adult and pediatric CXR datasets. We also propose novel ensemble methods: F-score-weighted Sequential Least-Squares Quadratic Programming (F-SLSQP) and Attention-Guided Ensembles with Learnable Fuzzy Softmax to aggregate weight parameters from multiple models to capitalize on their collective knowledge and complementary representations. We perform statistical significance tests with 95% confidence intervals and p-values to analyze model performance. Our evaluations indicate models initialized with ImageNet-pretrained weights demonstrate superior generalizability over randomly initialized counterparts, contradicting some findings for non-medical images. Notably, ImageNet-pretrained models exhibit consistent performance during internal and external testing across different training scenarios. Weight-level ensembles of these models show significantly higher recall (p<0.05) during testing compared to individual models. Thus, our study accentuates the benefits of ImageNet-pretrained weight initialization, especially when used with weight-level ensembles, for creating robust and generalizable deep learning solutions.

Benchmarking non-attendance patterns in paediatric medical imaging: A retrospective cohort study spotlighting First Nations children

IntroductionNon-attendance at Medical Imaging (MI) appointments can result in inefficiencies in healthcare resource allocation, increased financial burdens, and lead to potential barriers to effective healthcare delivery. We evaluated factors associated with non-attendance of MI appointments for children including variables: gender; age groups; residential postcodes; Indigenous status; appointment dates; appointment reminders and socio-economic status. MethodRetrospective cohort study of children with scheduled MI appointments at a Tertiary paediatric hospital in Australia, between January and December 2022. Data were extracted from the Radiology Information System and integrated with socio-economic census data through linking with postcode. Chi-squared, and logistic regression analysis were performed to identify significant predictors of non-attendance. ResultsOut of 17,962 scheduled outpatient appointments, 6.2 % did not attend. Males were less likely to attend than females (7.3 % vs. 5.8 %; p < 0.001). Older children had the highest frequency of non-attendance (p < 0.001). First Nations identified children had a higher likelihood of non-attendance at 14.5 % compared to non-First Nations at 5.8 %, and the odds ratio (OR) of First Nation children not attending was 2.54 (CI 2.13–3.03; p < 0.001) higher than non-First Nations children. Children from areas of disadvantage were less likely to attend (p < 0.001). Bone mineral densitometry had the highest odds of non-attendance (19.4 % of bookings) compared to other imaging modalities (p < 0.001). ConclusionThe following characteristics were associated with non-attendance: older male gender, residing in areas of socio-economic disadvantage, or identifying as First Nations Australians. By reviewing these findings with the cultural and professional experience of our Indigenous co-author, we have identified some strategies for improving attendance amongst First Nations children. Implications for practiceFactors associated with non-attendance, or “missed opportunities for care”, provide opportunities for intervention to improve attendance for vulnerable groups of children who require medical imaging.

Evaluation of claims data from a commercial value-based insurance product shows pediatric imaging is not a major driver of overall or pediatric healthcare expenditures.

Initiatives to reduce healthcare expenditures often focus on imaging, suggesting that imaging is a major driver of cost. To evaluate medical expenditures and determine if imaging was a major driver in pediatric as compared to adult populations. We reviewed all claims data for members in a value-based contract between a commercial insurer and a healthcare system for calendar years 2021 and 2022. For both pediatric (<18 years of age) and adult populations, we analyzed average per member per year (PMPY) medical expenditures related to imaging as well as other categories of large medical expenses. Average PMPY expenditures were compared between adult and pediatric patients. Children made up approximately 20% of members and 21% of member months but only 8-9% of expenditures. Imaging expenditures in pediatric members were 0.2% of the total healthcare spend and 2.9% of total pediatric expenditures. Imaging expenditures per member were seven times greater in adults than children. The rank order of imaging expenditures and imaging modalities was also different in pediatric as compared to adult members. Evaluation of claims data from a commercial value-based insurance product shows that pediatric imaging is not a major driver of overall, nor pediatric only, healthcare expenditures.

Exploring the Feasibility of At-Home Lung Ultra-Portable Ultrasound: Parent-Performed Pediatric Lung Imaging.

To determine if caregivers would be able to successfully perform in home lung ultrasounds on their children without direct supervision after undergoing a basic tutorial that would allow for expert interpretation. A prospective exploratory single-center cohort study was conducted on patients (0-18 years) presenting to a pediatric emergency department with a respiratory complaint or COVID-related illness. Caregivers underwent a brief hands-on session and were instructed to scan the lungs daily for 7 days. Images were assessed using a modified POCUS IQ score. Descriptive statistics were used to describe the data and bivariate analysis was used to compare groups. Eighteen patients were enrolled; the average age of the parent scanner was 31.9 years and 78% were female. Of all participants, 77.8% scanned on day one. Parents were able to successfully perform some part of the daily scan session for an average of 3.8 out of 7 days. The average POCUS IQ score overall was 6.7 (out of 12). Our study demonstrates the feasibility and acceptability of caregiver ability to obtain adequate lung ultrasound images, at home under no guidance, using the Butterfly iQ probe. Further studies are needed to investigate the accessibility of ultra-portable ultrasound and the ability to integrate with the at-home hospital model, specifically in the pediatric population.

Reducing pediatric total-body PET/CT imaging scan time with multimodal artificial intelligence technology.

This study aims to decrease the scan time and enhance image quality in pediatric total-body PET imaging by utilizing multimodal artificial intelligence techniques. A total of 270 pediatric patients who underwent total-body PET/CT scans with a uEXPLORER at the Sun Yat-sen University Cancer Center were retrospectively enrolled. 18F-fluorodeoxyglucose (18F-FDG) was administered at a dose of 3.7 MBq/kg with an acquisition time of 600s. Short-term scan PET images (acquired within 6, 15, 30, 60 and 150s) were obtained by truncating the list-mode data. A three-dimensional (3D) neural network was developed with a residual network as the basic structure, fusing low-dose CT images as prior information, which were fed to the network at different scales. The short-term PET images and low-dose CT images were processed by the multimodal 3D network to generate full-length, high-dose PET images. The nonlocal means method and the same 3D network without the fused CT information were used as reference methods. The performance of the network model was evaluated by quantitative and qualitative analyses. Multimodal artificial intelligence techniques can significantly improve PET image quality. When fused with prior CT information, the anatomical information of the images was enhanced, and 60s of scan data produced images of quality comparable to that of the full-time data. Multimodal artificial intelligence techniques can effectively improve the quality of pediatric total-body PET/CT images acquired using ultrashort scan times. This has the potential to decrease the use of sedation, enhance guardian confidence, and reduce the probability of motion artifacts.

Basics for Pediatric Brain Tumor Imaging: Techniques and Protocol Recommendations.

This review provides an overview of the current state of pediatric brain tumor imaging, emphasizing the role of various imaging sequences and highlighting the advantages of standardizing protocols for pediatric brain tumor imaging in diagnosis and treatment response evaluation. Basic anatomical sequences such as pre- and post-contrast 3D T1-weighted, T2-weighted, fluid-attenuated inversion recovery, T2*-weighted, and diffusion-weighted imaging (DWI), are fundamental for assessing tumor location, extent, and characteristics. Advanced techniques like DWI, diffusion tensor imaging, perfusion imaging, magnetic resonance spectroscopy, and functional MRI offer insights into cellularity, vascularity, metabolism, and function. To enhance consistency and quality, standardized protocols for pediatric brain tumor imaging have been recommended by expert groups. Special considerations for pediatric patients, including the minimization of anesthesia exposure and gadolinium contrast agent usage, are essential to ensure patient safety and comfort. Staying up-to-date with diagnostic imaging techniques can contribute to improved communication, outcomes, and patient care in the field of pediatric neurooncology.

Convolutional neural network-based analysis of pediatric chest X-ray images for pneumonia detection

Detection of pneumonia is generally done using chest X-ray images, traditionally assessed manually by radiologists. However, this method has limitations, including the potential for human error, variability in interpretation, and a shortage of skilled professionals, particularly in resource-limited settings. Prompted by these challenges and the increasing potential of machine learning in medical diagnostics, we investigated the efficacy of advanced computational models in distinguishing between normal and pneumonia-affected lung images. We hypothesized that an adapted version of the VGG16 model, a convolutional neural network (CNN), would outperform the standard VGG16 and simpler Multilayer Perceptrons (MLPs) in terms of accuracy and reliability. Utilizing a dataset from the Guangzhou Women and Children’s Medical Center, we evaluated the performance of these three models on pediatric chest X-ray images. The MLP showed moderate effectiveness with 78.4% accuracy but struggled with complex image data. The standard VGG16 achieved better results with 90.9% accuracy but displayed overfitting tendencies. The adapted VGG16 model, with reduced filter sizes and dropout layers, demonstrated the highest accuracy at 95.6%, indicating superior performance and stability. These findings suggest that tailored deep learning models like the adapted VGG16 can significantly enhance pneumonia diagnosis from chest X-ray images, offering a balance of accuracy, efficiency, and generalizability. This advancement holds substantial implications for improving diagnostic processes in pediatric healthcare, particularly in settings with limited resources.

The Impact of Simulation-Based Training on Self-Efficacy in Sedation for Pediatric Magnetic Resonance Imaging.

In Japan, approximately 35% of facilities experience sedation-related complications for pediatric magnetic resonance imaging (MRI), including severe complications such as respiratory and cardiac arrests. In the medical education field, simulation improves not only the quality of real emergency response but also health care workers' self-efficacy. Individuals with high self-efficacy are better prepared at handling diverse conditions. However, there is no research examining the impact of sedation simulation for pediatric MRI on the self-efficacy of health care workers. This study aimed to retrospectively investigate the impact of sedation simulation for pediatric MRI on the self-efficacy of health care workers in sedation. The study was conducted on August 18, 2023, and enrolled pediatricians, nurses, and radiological technologists. The impact of sedation simulation for pediatric MRI on the participants was analyzed using confidence scale scores and part of the Pediatric Resuscitation and Escalation of Care Self-Efficacy Scale (PRSES), before and after sedation simulation for pediatric MRI. Eighteen participants (six pediatricians, six nurses, and six radiological technologists) were included in this study. Regarding confidence scale scores, a significant improvement was observed in the overall group (P = 0.002) and among the nurses (P = 0.0036). Regarding the item 'When confronted with a clinically deteriorating child, I know how to ask for assistance' of PRSES, a significant improvement was observed in the overall group (P = 0.0035) and among the radiological technologists (P = 0.048). There's a potential for sedation simulation for pediatric MRI to increase the self-efficacy of health care workers in MRI sedation. Our findings suggest that this training has a valuable role in preparing health care workers to practice sedation for pediatric MRI.