Despite current screening models, enhanced imaging modalities, and treatment regimens, diabetic retinopathy (DR) remains one of the leading causes of vision loss in working age adults. DR can result in irreversible structural and functional retinal damage, leading to visual impairment and reduced quality of life. Given potentially irreversible photoreceptor damage, diagnosis and treatment at the earliest stages will provide the best opportunity to avoid visual disturbances or retinopathy progression. We will review herein the current structural imaging methods used for DR assessment and their capability of detecting DR in the first stages of disease. Imaging tools, such as fundus photography, optical coherence tomography, fundus fluorescein angiography, optical coherence tomography angiography and adaptive optics-assisted imaging will be reviewed. Finally, we describe the future of DR screening programmes and the introduction of artificial intelligence as an innovative approach to detecting subtle changes in the diabetic retina. CLINICAL TRIAL REGISTRATION NUMBER: N/A.

To evaluate how different test set sampling strategies-random selection and balanced sampling-affect the performance of artificial intelligence (AI) models in pediatric wrist fracture detection using radiographs, aiming to highlight the need for standardization in test set design. This retrospective study utilized the open-sourced GRAZPEDWRI-DX dataset of 6091 pediatric wrist radiographs. Two test sets, each containing 4588 images, were constructed: one using a balanced approach based on case difficulty, projection type, and fracture presence and the other a random selection. EfficientNet and YOLOv11 models were trained and validated on 18,762 radiographs and tested on both sets. Binary classification and object detection tasks were evaluated using metrics such as precision, recall, F1 score, AP50, and AP50-95. Statistical comparisons between test sets were performed using nonparametric tests. Performance metrics significantly decreased in the balanced test set with more challenging cases. For example, the precision for YOLOv11 models decreased from 0.95 in the random set to 0.83 in the balanced set. Similar trends were observed for recall, accuracy, and F1 score, indicating that models trained on easy-to-recognize cases performed poorly on more complex ones. These results were consistent across all model variants tested. AI models for pediatric wrist fracture detection exhibit reduced performance when tested on balanced datasets containing more difficult cases, compared to randomly selected cases. This highlights the importance of constructing representative and standardized test sets that account for clinical complexity to ensure robust AI performance in real-world settings. Question Do different sampling strategies based on samples' complexity have an influence in deep learning models' performance in fracture detection? Findings AI performance in pediatric wrist fracture detection significantly drops when tested on balanced datasets with more challenging cases, compared to randomly selected cases. Clinical relevance Without standardized and validated test datasets for AI that reflect clinical complexities, performance metrics may be overestimated, limiting the utility of AI in real-world settings.

Wrong-level spine surgery remains a significant concern in spine surgery, leading to devastating consequences for patients and healthcare systems alike. This comprehensive review aims to analyze the existing literature on wrong-level spine surgery in spine procedures, identifying key factors that contribute to these errors and exploring advanced strategies and technologies designed to prevent them. A systematic literature search was conducted across multiple databases, including PubMed, Scopus, EMBASE, and CINAHL. The selection criteria focused on preclinical and clinical studies that specifically addressed wrong site and wrong level surgeries in the context of spine surgery. The findings reveal a range of contributing factors to wrong-level spine surgeries, including communication failures, inadequate preoperative planning, and insufficient surgical protocols. The review emphasizes the critical role of innovative technologies-such as artificial intelligence, advanced imaging techniques, and surgical navigation systems-alongside established safety protocols like digital checklists and simulation training in enhancing surgical accuracy and preventing errors. In conclusion, integrating advanced technologies and systematic safety protocols is instrumental in reducing the incidence of wrong-level spine surgeries. This review underscores the importance of continuous education and the adoption of innovative solutions to foster a culture of safety and improve surgical outcomes. By addressing the multifaceted challenges associated with these errors, the field can work towards minimizing their occurrence and enhancing patient care.

Exploring the early stages of Alzheimer's disease (AD) is crucial for timely intervention to help manage symptoms and set expectations for affected individuals and their families. However, the study of the early stages of AD involves analysing heterogeneous disease cohorts which may present challenges for some modelling techniques. This heterogeneity stems from the diverse nature of AD itself, as well as the inclusion of undiagnosed or 'at-risk' AD individuals or the presence of comorbidities which differentially affect AD biomarkers within the cohort. Normative modelling is an emerging technique for studying heterogeneous disorders that can quantify how brain imaging-based measures of individuals deviate from a healthy population. The normative model provides a statistical description of the 'normal' range that can be used at subject level to detect deviations, which may relate to pathological effects. In this work, we applied a deep learning-based normative model, pre-trained on MRI scans in the UK Biobank, to investigate ageing and identify abnormal age-related decline. We calculated deviations, relative to the healthy population, in multi-modal MRI data of non-demented individuals in the external EPAD (ep-ad.org) cohort and explored these deviations with the aim of determining whether normative modelling could detect AD-relevant subtle differences between individuals. We found that aggregate measures of deviation based on the entire brain correlated with measures of cognitive ability and biological phenotypes, indicating the effectiveness of a general deviation metric in identifying AD-related differences among individuals. We then explored deviations in individual imaging features, stratified by cognitive performance and genetic risk, across different brain regions and found that the brain regions showing deviations corresponded to those affected by AD such as the hippocampus. Finally, we found that 'at-risk' individuals in the EPAD cohort exhibited increasing deviation over time, with an approximately 6.4 times greater t-statistic in a pairwise t-test compared to a 'super-healthy' cohort. This study highlights the capability of deep normative modelling approaches to detect subtle differences in brain morphology among individuals at risk of developing AD in a non-demented population. Our findings allude to the potential utility of normative deviation metrics in monitoring disease progression.

Artificial intelligence (AI) studies show promise in enhancing accuracy and efficiency in mammographic screening programs worldwide. However, its integration into clinical workflows faces several challenges, including unintended errors, the need for professional training, and ethical concerns. Notably, specific frameworks for AI imaging in breast cancer screening are still lacking. This study aims to identify the challenges associated with implementing AI in breast screening programs and to apply the Consolidated Framework for Implementation Research (CFIR) to discuss a practical governance framework for AI in this context. Three electronic databases (PubMed, Embase, and MEDLINE) were searched using combinations of the keywords "artificial intelligence," "regulation," "governance," "breast cancer," and "screening." Original studies evaluating AI in breast cancer detection or discussing challenges related to AI implementation in this setting were eligible for review. Findings were narratively synthesized and subsequently mapped directly onto the constructs within the CFIR. A total of 1240 results were retrieved, with 20 original studies ultimately included in this systematic review. The majority (n=19) focused on AI-enhanced mammography, while 1 addressed AI-enhanced ultrasound for women with dense breasts. Most studies originated from the United States (n=5) and the United Kingdom (n=4), with publication years ranging from 2019 to 2023. The quality of papers was rated as moderate to high. The key challenges identified were reproducibility, evidentiary standards, technological concerns, trust issues, as well as ethical, legal, societal concerns, and postadoption uncertainty. By aligning these findings with the CFIR constructs, action plans targeting the main challenges were incorporated into the framework, facilitating a structured approach to addressing these issues. This systematic review identifies key challenges in implementing AI in breast cancer screening, emphasizing the need for consistency, robust evidentiary standards, technological advancements, user trust, ethical frameworks, legal safeguards, and societal benefits. These findings can serve as a blueprint for policy makers, clinicians, and AI developers to collaboratively advance AI adoption in breast cancer screening. PROSPERO CRD42024553889; https://tinyurl.com/mu4nwcxt.

Ultrasound localization microscopy (ULM) has revolutionized microvascular imaging by breaking the acoustic diffraction limit. However, different ULM workflows depend heavily on distinct prior knowledge, such as the impulse response and empirical selection of parameters (e.g., the number of microbubbles (MBs) per frame M), or the consistency of training-test dataset in deep learning (DL)-based studies. We hereby propose a general ULM pipeline that reduces priors. Our approach leverages a DL model that simultaneously distills microbubble signals and reduces speckle from every frame without estimating the impulse response and M. Our method features an efficient channel attention vision transformer (ViT) and a progressive learning strategy, enabling it to learn global information through training on progressively increasing patch sizes. Ample synthetic data were generated using the k-Wave toolbox to simulate various MB patterns, thus overcoming the deficiency of labeled data. The ViT output was further processed by a standard radial symmetry method for sub-pixel localization. Our method performed well on model-unseen public datasets: one in silico dataset with ground truth and four in vivo datasets of mouse tumor, rat brain, rat brain bolus, and rat kidney. Our pipeline outperformed conventional ULM, achieving higher positive predictive values (precision in DL, 0.88-0.41 vs. 0.83-0.16) and improved accuracy (root-mean-square errors: 0.25-0.14 λ vs. 0.31-0.13 λ) across a range of signal-to-noise ratios from 60 dB to 10 dB. Our model could detect more vessels in diverse in vivo datasets while achieving comparable resolutions to the standard method. The proposed ViT-based model, seamlessly integrated with state-of-the-art downstream ULM steps, improved the overall ULM performance with no priors.

The application of artificial intelligence (AI) technology has realized the transformation of people's production and lifestyle, and also promoted the rapid development of the medical field. At present, the application of intelligence in the medical field is increasing. Using its advanced methods and technologies of AI, this paper aims to realize the integration of medical imaging-aided diagnosis system and AI, which is helpful to analyze and solve the loopholes and errors of traditional artificial diagnosis in the diagnosis of pulmonary nodules. Drawing on the principles and rules of image segmentation methods, the construction and optimization of a medical image-aided diagnosis system is carried out to realize the precision of the diagnosis system in the diagnosis of pulmonary nodules. In the diagnosis of pulmonary nodules carried out by traditional artificial and medical imaging-assisted diagnosis systems, 231 nodules with pathology or no change in follow-up for more than two years were also tested in 200 cases. The results showed that the AI software detected a total of 881 true nodules with a sensitivity of 99.10% (881/889). The radiologists detected 385 true nodules with a sensitivity of 43.31% (385/889). The sensitivity of AI software in detecting non-calcified nodules was significantly higher than that of radiologists (99.01% vs 43.30%, P < 0.001), and the difference was statistically significant.

Evaluate an Artificial Intelligence (AI) system in breast screening through stratified results across age, breast density, ethnicity and screening centres, from different UK regions. A large-scale retrospective study evaluating two variations of using AI as an independent second reader in double reading was executed. Stratifications were conducted for clinical and operational metrics. Data from 306 839 mammography cases screened between 2017 and 2021 were used and included three different UK regions.The impact on safety and effectiveness was assessed using clinical metrics: cancer detection rate and positive predictive value, stratified according to age, breast density and ethnicity. Operational impact was assessed through reading workload and recall rate, measured overall and per centre.Non-inferiority was tested for AI workflows compared with human double reading, and when passed, superiority was tested. AI interval cancer (IC) flag rate was assessed to estimate additional cancer detection opportunity with AI that cannot be assessed retrospectively. The AI workflows passed non-inferiority or superiority tests for every metric across all subgroups, with workload savings between 38.3% and 43.7%. The AI standalone flagged 41.2% of ICs overall, ranging between 33.3% and 46.8% across subgroups, with the highest detection rate for dense breasts. Human double reading and AI workflows showed the same performance disparities across subgroups. The AI integrations maintained or improved performance at all metrics for all subgroups while achieving significant workload reduction. Moreover, complementing these integrations with AI as an additional reader can improve cancer detection. The granularity of assessment showed that screening with the AI-system integrations was as safe as standard double reading across heterogeneous populations.

Ultrasonography and D-dimer testing are established modalities for evaluating potential lower extremity deep venous thrombosis (DVT). The ThinkSono Guidance system is an AI based software allowing non-ultrasound trained providers to perform compression ultrasounds for evaluation by remote interpreters. This study evaluates its clinical utilisation and potential reduction of venous duplexes and waiting times. Patients with suspected DVTs were prospectively recruited through the institution's emergency department. Patients underwent an AI guided two region proximal DVT compression examination by non-ultrasound trained providers using the ThinkSono Guidance system and D-dimer testing. Ultrasound images remotely reviewed by the on call radiologist were rated for diagnostic quality; all images of sufficient quality were assessed as either "Compressible/no proximal DVT" or "Inadequate imaging/possible DVT". All patients assessed as "compressible" with negative D-dimers were discharged. All other patients were sent for a venous duplex scan. Time to diagnosis, sensitivity, and specificity of ThinkSono Guidance against D-dimers and full duplex scans were calculated. Fifty three patients (average age 56 ± 18 years, 45% females) were scanned with ThinkSono Guidance by one of three non-ultrasound trained providers. All scans were of diagnostic quality. ThinkSono Guidance with radiologist review yielded 45 negative DVT diagnoses (85%). Seventeen of these with negative D-dimers were discharged (32%), 28 required duplex ultrasound testing per trial protocol (23 due to positive D-dimers, five due to unavailability of D-dimer). All of these duplexes were negative (100% sensitivity). Eight patients were suspected to have DVT by the reviewing radiologist, and duplex confirmed DVT in six patients (96% ThinkSono Guidance specificity, 36% D-dimer specificity). ThinkSono Guidance scans averaged 6.75 minutes for scan and review. The median time from scan initiation to review was 37.5 minutes. This suggests a significant proportion of patients with suspected DVT could safely avoid duplex ultrasound and D-dimer testing using the ThinkSono system, setting the basis for a novel AI assisted diagnostic pathway.

Artificial intelligence applications in oncology imaging often struggle with diagnosing rare tumors. We identify significant gaps in detecting uncommon thyroid cancer types with ultrasound, where scarce data leads to frequent misdiagnosis. Traditional augmentation strategies do not capture the unique disease variations, hindering model training and performance. To overcome this, we propose a text-driven generative method that fuses clinical insights with image generation, producing synthetic samples that realistically reflect rare subtypes. In rigorous evaluations, our approach achieves substantial gains in diagnostic metrics, surpasses existing methods in authenticity and diversity measures, and generalizes effectively to other private and public datasets with various rare cancers. In this work, we demonstrate that text-guided image augmentation substantially enhances model accuracy and robustness for rare tumor detection, offering a promising avenue for more reliable and widespread clinical adoption.