Diagnostic Imaging

Chest X-rays are commonly used to help diagnose and manage chest conditions. Artificial intelligence (AI) tools are increasingly being used to support chest X-ray interpretation. However, it is not yet clear whether the timing of AI information affects how clinicians review images, make decisions, and use AI support. This study will look at whether showing AI information before or after a clinician first reviews a chest X-ray changes how they look at the image, how long they take, their interpretation decisions, their confidence, and their trust in AI support. Healthcare professional participants will complete two chest X-ray interpretation sessions in a controlled NHS research setting. During each session, participants will review de-identified chest X-ray images while wearing eye-tracking equipment. Eye-tracking will record where a participant looks on the image and how long they spend looking at different areas. In one session, AI information will be shown before the participant reviews the chest X-ray. In the other session, AI information will be shown after the participant has first reviewed the chest X-ray. The order of these two sessions will be balanced across participants. The study uses de-identified chest X-ray images from existing examinations. It does not involve patients directly, does not change clinical care, and no clinical decisions will be made from the study readings. Participants will also complete a short questionnaire about their experience of using AI support. A separate anonymous survey will collect wider views from clinicians, patients, members of the public, and healthcare staff about the use of AI in chest X-ray interpretation.

FS2 evaluates the diagnostic accuracy and implementation feasibility of an AI-assisted blind-sweep obstetric ultrasound (SPAQ E-con AI), operated by trained non-specialist health workers, for antenatal screening in rural Democratic Republic of the Congo. Primary outcomes are gestational age mean absolute error (Trimester 2 and Trimester 3) with 95% confidence intervals and AI confidence calibration. The reference standard is manual measurement by a reference reader (early ultrasound first; manual BPD if unavailable; last menstrual period is not used). Target enrollment is approximately 1,430 (IRB-approved ceiling 3,000), with early termination permitted upon achievement of pre-specified analysis-plan thresholds. The study is a multi-center prospective Hybrid Type 1 Effectiveness-Implementation design and includes a pre-specified adaptive model-update (Batch 2 cut) plan following FDA PCCP and STARD-AI guidance.

The aim of this study is to assess emergency medicine physician and advanced practice provider (APP) knowledge and technical skill in performance of a point-of-care ultrasound simulation and just-in-time training pathway to determine the feasibility, acceptability, and usability of the ultrasound training program. By performing this study, we hope to create a standardized training model which could potentially facilitate point-of-care ultrasound (POCUS) clinical performance and thereby improve patient care.

Guided Bone Regeneration (GBR) is a widely used technique during dental implant surgery to help rebuild bone around the implant and improve its long-term appearance and stability. This study investigates whether the amount of bone that regrows depends on a person's original bone shape, known as the Individual Phenotypical Dimension (IPD). The aim is to compare the bone stability and overall results between two approaches: adding bone only up to the original bone line (IPD) or adding bone beyond it (over-contour augmentation). Over the course of a year, the study will assess not only bone and soft tissue healing, but also gum blood flow, implant success, and patient satisfaction. There will be two treatment groups in this study - one group will receive bone grafting just up to their natural bone shape, while the other group will receive a slightly larger graft that extends about 3 mm beyond it. Throughout the study CBCT scans will be taken to assess bone changes around the implant area in order to measure how the bone shape and thickness change over time after surgery.

This study aims to evaluate the diagnostic performance and clinical utility of a multimodal medical imaging large model in identifying common systemic diseases. Through a retrospective reader study involving multiple centers, the research will compare the diagnostic accuracy, sensitivity, and specificity of radiologists with and without AI assistance. The goal is to validate the model's robustness and its impact on the diagnostic efficiency of clinicians across diverse healthcare settings.

The goal of this observational study is to compare the diagnostic performance of three detection methods for approximal carious lesions in primary molars among pediatric patients aged 4-10 years. The study focuses on children in three age groups: 4-6 years, 6-8 years, and 8-10 years. The main questions it aims to answer are: * Are the sensitivity, specificity, accuracy, and area under the curve (AUC) different across the three diagnostic techniques (bitewing radiography, near-infrared light transillumination, and their combination)? * Are these diagnostic parameters influenced by patient age? * Which technique yields the highest level of patient acceptance? Researchers will compare the three diagnostic approaches to determine whether age influences diagnostic performance and patient acceptance. Participants will: * Be examined using bitewing radiography and near-infrared light transillumination * Undergo tooth separation for 7 days using orthodontic elastic separators * Receive clinical examination of the target approximal surface * Be asked to rate their experience using the Simplified Facial Pain Scale (S-FPS)

This study aims to develop and validate a contrast-enhanced CT-based deep-learning model for automatic and accurate preoperative discrimination between T1-T2 and T3 renal cell carcinoma. By quantifying the model's diagnostic performance on an independent test set-using AUC, sensitivity, specificity, positive/negative predictive values, and decision-curve analysis-we will establish a decision-support tool that can be seamlessly integrated into clinical PACS, thereby reducing staging errors, refining surgical planning, and improving patient outcomes.

This is an open label, longitudinal Phase 3 study of prostate specific membrane antigen (PSMA) positron emission tomography (PET) combined with magnetic resonance imaging (MRI) compared to standard of care (SOC) for the detection of prostate cancer (PCa).

The goal of this study is to learn if AI-generated video explanations help people better understand their radiology reports. The main question it aims to answer is: Do AI-generated videos help participants understand their medical imaging results better than written reports alone? Participants will send their own radiology images and written reports to the research team; receive a personalized AI-generated video that explains their results in easy-to-understand language; watch their video explanation (about 1-5 minutes long); and complete 15-minute online survey about how well the video helped them understand their results.

Coronary computed tomography angiography (CCTA) is a widely accepted initial diagnostic test for individuals suspected of having chronic coronary syndromes. However, there is limited evidence supporting its use in the acute setting. So far, no large-scale randomized trial has examined the performance of CCTA as an alternative to invasive coronary angiography (ICA) in individuals with non-ST-segment elevation myocardial infarction (NSTEACS). If CCTA were to replace ICA as a routine procedure for individuals with NSTEACS, it could reduce the risk of complications related to ICA, improve patient comfort, expedite decision-making, and reduce healthcare expenses and interhospital transfers.

The study consists of collecting measurement data of the rachis in pregnant women and the subsequent outcome of her delivery. This will make it possible to validate a non-invasive imaging technique through software that can be used to study this anatomical curve proposing a new measurement method for the angle of lordosis. Finally, with the research data, the investigators will try to find a correlation between these variables (angle of lordosis and delivery outcome.

Tuberculosis (TB) is one of the top ten causes of death worldwide with approximately 10 million cases globally and 1.2 million deaths. Sub-Saharan Africa carries the highest burden of TB. South Africa has one of the highest HIV and TB rates worldwide with an HIV prevalence rate in adults of 19% and a TB case notification rate of 615/100,000 in 2019. Over many years, focus has been paid to pulmonary TB and extrapulmonary TB (EPTB) has received only little attention even though it accounts for almost a quatre of all TB cases. The diagnosis of EPTB remains challenging simply because sample collection requires invasive procedures in the absence of a blood-based diagnostic test. Spinal TB (spondylitis or spondylodiscitis caused by Mycobacterium tuberculosis) - often known as Pott's disease - accounts for up to 10% of EPTB and affects young children, people with HIV-coinfection and elderly, and often leads to lifelong debilitating disease due to devastating deformation of the spine and compression of neural structures. Little is known with regards to the extent of disease and isolated TB spine as well as a disseminated form of TB spine have been described. The latter presents with a spinal manifestation plus disseminations to other organs such as the lungs, pleura, lymph nodes, the GIT or urinary tract or even the brain. In the Spinal TB X cohort, the investigators aim to describe the clinical phenotype of spinal TB using whole body PET/CT and identify a specific gene expression profile for the different stages of dissemination and compare findings to previously described signatures for latent and active pulmonary TB. A blood-based test for spinal TB would lead to earlier diagnosis and treatment in all settings globally and improve treatment outcome of this devastating disease.