This randomized clinical trial evaluates whether interaction with a large language model–based chatbot is more effective than existing public health resources for increasing parents' intent to vaccinate their child against human papillomavirus (HPV).

This study assesses the integration of frontier large language models including tools such as optical character recognition (OCR) into the scientific peer review process to detect invisible text injection in an article under review.

JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, spoke with Nigam Shah, MBBS, PhD, a professor of medicine at Stanford University and chief data scientist at Stanford Health Care, about the integration of AI into electronic health records for JAMA+ AI Conversations.

This nonrandomized clinical trial reports data from developing and validating a smartphone-based, media-facilitated artificial intelligence system for self-screening for ocular surface malignancies in the general population.

This diagnostic study compares the accuracy of artificial intelligence algorithms vs human evaluators across varying expertise levels for skin lesion diagnosis, including rare and atypical cases, in a realistic clinical context.

This Viewpoint discusses advertising in artificial intelligence (AI)–powered clinical decision support tools and stresses the importance of adopting and policing advertising policies with strong ethical guardrails within these tools.

This survey study evaluates the percentage of US adolescents and young adults who used artificial intelligence (AI) chatbots for mental health advice as of 2025 and to what extent they told others.

This qualitative study evaluates the associations between use of an ambient artificial intelligence (AI) scribe system and clinician productivity, efficiency, and documentation burden.

This post hoc secondary analysis of a cluster randomized clinical trial assesses whether implementation of a clinical decision support system is associated with increased antihypertensive treatment intensification and improved blood pressure (BP) control in primary care practices.

This Viewpoint discusses the pros and cons of artificial intelligence (AI) in physician learning and offers ways in which AI systems should be used to support rather than replace clinical judgment.

This Viewpoint explores whether the utility artificial intelligence (AI) tools for non-native English researchers may compromise the epistemic accuracy of scientific writing.

This qualitative study aimed to evaluate the usability, perceived effectiveness, and acceptability of a voice-based generative artificial intelligence assistant for educating patients about intravitreal therapy for wet age-related macular degeneration and supporting treatment understanding and adherence.

This quality improvement study evaluates the physician-rated safety and use of artificial intelligence (AI)–generated hospital course summaries and their association with physician burnout levels.

This cluster randomized clinical trial of patients with chronic kidney disease assesses the effectiveness of a clinical decision support system in improving process measures and clinical outcomes in primary care.

This Viewpoint discusses how overreliance on artificial intelligence (AI) can lead to deskilling and mis-skilling among clinicians still in training and the importance of thoughtful design and implementation into the clinical learning environment.

In this episode of JAMA+ AI Conversations, Associate Editor Yulin Hswen and JAMA Health Forum Editor Sandro Galea discuss the issues surrounding AI’s move from the laboratory into health policy.

Nature Machine Intelligence, Published online: 28 May 2026; doi:10.1038/s42256-026-01248-2

Human–AI interactions reshape the self and our social networks

Nature Machine Intelligence, Published online: 27 May 2026; doi:10.1038/s42256-026-01243-7

Han et al. introduce UniAIR, a unified AI framework that predicts mutation effects across diverse immune recognition settings. The approach enables more generalizable modelling of antibody, antigen and T cell receptor interactions.

Nature Machine Intelligence, Published online: 25 May 2026; doi:10.1038/s42256-026-01234-8

pUniFind is a large-scale deep learning model for proteomics that unifies peptide–spectrum scoring and open de novo sequencing. Trained on over 100 million spectra, it substantially improves peptide identification and modification discovery.

Nature Machine Intelligence, Published online: 21 May 2026; doi:10.1038/s42256-026-01238-4

Free boundary problems, such as modelling glacier melt, are difficult to capture with neural operators. A new framework addresses this challenge by leveraging the mathematical principle of topological conjugacy.

Nature Machine Intelligence, Published online: 21 May 2026; doi:10.1038/s42256-026-01233-9

Long et al. introduce a neural operator method to solve free boundary problems with high precision. The framework shows promise for real-time predictions in clinical applications, particularly in simulating tumour growth.

Nature Machine Intelligence, Published online: 18 May 2026; doi:10.1038/s42256-026-01247-3

Generative artificial intelligence (GenAI) tools are challenging our understanding of plagiarism. How should we deal with plagiarism of ideas if this misbehaviour is increasingly common, and it is extremely difficult to prove when GenAI is involved? Definitions of research misconduct that specifically address the use of GenAI tools are needed.

Nature Machine Intelligence, Published online: 18 May 2026; doi:10.1038/s42256-026-01253-5

Companies, tech workers and researchers are in a frenzy to embed agentic AI into their workflows, locked in a self-imposed race not to fall behind. There must be a better way to make use of AI technology.

Nature Machine Intelligence, Published online: 18 May 2026; doi:10.1038/s42256-026-01246-4

SpecGP enhances fragment ion coverage to enable the prediction of N-glycopeptide structural spectra across diverse collision energies, thereby improving isomer discrimination and boosting identification confidence through rescoring.

npj Digital Medicine, Published online: 11 June 2026; doi:10.1038/s41746-026-02890-1

FIRST-ICU: forecasting interventions and risk stratification in the ICU using graph neural network autoencoders

npj Digital Medicine, Published online: 11 June 2026; doi:10.1038/s41746-026-02878-x

A systematic review of explainable artificial intelligence and cardiac electrophysiological models addressing sports-related sudden cardiac death and arrest in adolescents and young adults

npj Digital Medicine, Published online: 10 June 2026; doi:10.1038/s41746-026-02893-y

AI-assisted improvement of endoscopic diagnosis of ampullary lesions

npj Digital Medicine, Published online: 10 June 2026; doi:10.1038/s41746-026-02866-1

Federated generative prompt learning with vision foundation models: universal efficient multi-center medical image analysis

npj Digital Medicine, Published online: 10 June 2026; doi:10.1038/s41746-026-02680-9

Deployable real-time spinal endoscopic instance segmentation with lightweight multi-scale attention mechanism

npj Digital Medicine, Published online: 10 June 2026; doi:10.1038/s41746-026-02877-y

Development and application of an intelligent assessment system for medical clinical skill training

npj Digital Medicine, Published online: 10 June 2026; doi:10.1038/s41746-026-02884-z

Noninvasive PPROM risk stratification with explainable AI using routine antenatal CRP and albumin

npj Digital Medicine, Published online: 10 June 2026; doi:10.1038/s41746-026-02816-x

Benchmarking deep learning architectures for MALDI-TOF mass spectrometry in infectious disease diagnostics and vector-borne disease surveillance

This Review Article examines how large language models could reshape informed consent in clinical research by making it clearer, more accessible, and more responsive to participants’ needs through plain-language revision, translation, and comprehension support. It also highlights the accuracy, bias, and oversight safeguards required for responsible use.

This Policy Corner clarifies key concepts and differences across various applications of AI in health care to help clinicians, patients, managers and policy-makers better understand, apply, manage and govern these technologies in practice.

This Editorial traces the evolution of medical knowledge delivery from print and search-based systems to artificial intelligence–driven synthesis powered by large language models. It argues that while LLMs improve efficiency, they introduce new risks to reliability and evidence, requiring clinicians and journals to adapt their roles to preserve critical appraisal and accountability.

This Review examines the Medical Event Data Standard (MEDS), an open-source data framework designed to address gaps in reproducibility and interoperability for artificial intelligence models applied to electronic health record data. It argues that MEDS, by prioritizing algorithm transportability, minimal data harmonization, and scalable computation, enables more efficient and reproducible health AI development, with early evidence showing promising adoption and gains in computational performance and code efficiency.

This Policy Corner argues that predictive artificial intelligence can act as a multiplier on the clinical and economic value of therapies by improving how treatments are allocated across heterogeneous patient populations through risk-based and response-based targeting. Using case studies in remote physiological monitoring and Alzheimer’s disease, it explores how more precise targeting can lower effective numbers needed to treat, improve outcomes, and materially change the economic value of therapies, while highlighting the data, incentive, and regulatory conditions required to realize these gains.

This Perspective examines the emerging legal risks of ambient artificial intelligence documentation tools in clinical care, with a focus on consent, data transmission, and state-level recording laws. It highlights gaps in current regulatory frameworks and outlines operational and policy strategies to mitigate liability and ensure ethical, transparent implementation.

This Policy Corner examines the emerging privacy risks related to artificial intelligence scribes, outlining data flows and key privacy considerations, and offers best practice recommendations for health systems implementing or considering their use.

This Letter responds to the ongoing debate on the terminology for large language model errors by arguing that “hallucination” mislocates the error in the perceptual domain and that “confabulation” is a better-calibrated conceptual borrowing. It further proposes a functional typology distinguishing ordinary from delusional confabulation, with practical implications for clinical settings.

A Letter in response to the article “AI-Standardized Clinical Examination Training on OSCE Performance.” This perspective supports the randomized trial evaluating artificial intelligence–standardized clinical examination training while highlighting limitations in perceived authenticity and domain-specific effectiveness.

Author response to a Letter about “AI-Standardized Clinical Examination Training on OSCE Performance.”

This Letter responds to Uscher-Pines et al. and argues that chatbot errors in behavioral health should be weighted by clinical severity, that unmonitored chatbot use outside clinical workflows creates gaps in physician awareness, and that English-only evaluation likely overstates chatbot performance.

The authors respond to a Letter about “Assessing Generative AI Chatbots for Alcohol Misuse Support: A Longitudinal Simulation Study.”

For as long as modern medicine has existed, one of the biggest hurdles to delivering widespread and affordable care hasn’t been a lack of clinical knowledge or human empathy, it has been a fundamental scarcity of labor. Healthcare is one of the few remaining major industries bound entirely to the physical limits of human time. ...;

Living in an Era of Endless Health Information  Clinical knowledge is expanding at an unprecedented pace and scale. New research, updated guidelines and emerging treatment options are published at a speed that makes it increasingly difficult for clinicians to stay current while managing heavy workloads and growing patient complexity. For many, the challenge is no longer a lack of information, ...;

Healthcare AI is entering a new phase. The conversation is moving beyond documentation, triage, and workflow automation toward systems that claim to be more context aware, more personalized, and more responsive to human need. Dementia will be the real test of whether that promise is serious. The World Alzheimer Report 2025 makes clear how underbuilt ...;

Healthcare leaders are tired of AI theater. The industry has endured years of buzzwords, polished demos, and ambitious promises that rarely survive contact with operational reality. AI is going to revolutionize drug discovery. It’s going to transform diagnostics. It’s going to reinvent the patient experience. Some of that may eventually prove true, but for most ...;

If you want to understand just how broken legacy enterprise workflows can be, look no further than the clinical trial industry. Before a life-saving drug ever reaches a pharmacy shelf, it gets bogged down in a multi-billion-dollar administrative swamp.  The biggest culprit? Study site selection and kickoff, a process still largely dependent on manual spreadsheets, ...;

Real-time diagnostic accuracy can mean the difference between immediate treatment and dangerous delay. AI-powered ultrasound systems are changing what clinicians can see, measure, and decide within seconds of placing the probe on a patient.  From emergency departments to maternity units, intelligent imaging tools are helping professionals make faster and more confident calls. Reducing Measurement Variability  ...;

Artificial intelligence now plays a central role in drug discovery. In antibody research especially, models support sequence design, paratope prediction, affinity maturation, and developability screening. Yet as these systems move from benchmark tasks to real discovery programs, a familiar pattern is emerging: models often perform well within known training space, then weaken when asked to ...;

ISTANBUL, Turkey — Modern breast augmentation is evolving as patients increasingly move away from exaggerated cosmetic trends and seek more natural-looking, personalized results. According to Dr. Leyla Arvas, MD, an Istanbul-based plastic surgeon internationally recognized for her work in aesthetic surgery and body contouring, modern breast aesthetics is no longer defined simply by implant size or ...;

Elon Musk recently brought back one of his long-standing ideas during the OpenAI trial: that as artificial intelligence becomes more powerful, humans may need a closer, more direct connection to machines. He calls this future “human–AI symbiosis.” The phrase sounds ambitious, but the underlying idea is straightforward. If AI begins to outpace human cognition in ...;

We’re sharing an update on our mental health work, including some new changes to better connect people with the right information.

Here are Google’s latest AI updates from March 2026

The winners of the MedGemma Impact Challenge demonstrated the potential of Google’s open medical models for solving diverse healthcare challenges.

Google and DocMorris have announced a partnership to create a more intuitive and supportive digital health experience.

<p data-block-key="1tp3e">At Google’s annual health event, The Check Up, we shared how our products, research and partnerships are making the most of AI to help everyone live healthier lives.</p>

At The Check Up, Google announced a $10M investment in clinician AI training and how AI is upgrading Search and Fitbit for better health data.

An overview of how Google Earth AI is supporting the global health community’s work to predict outbreaks and deliver proactive care.

A new Google AI initiative aims to improve heart health outcomes for people living in remote Australian communities.

New research shows how Google AI helps radiologists detect breast cancer earlier and more accurately, while giving radiologists more time for patient care.

Objectives;Artificial intelligence (AI) has shown promise for estimating volumetric breast density values from processed, “for presentation,” mammograms. However, previous evaluations have typically used small datasets or focused on a single vendor. In this study, we aimed to improve volumetric breast density estimation from processed mammograms for the three main UK vendors with a combination of improved training methods and the utilization of up-to-date data from the large OPTIMAM Mammography Image Database (OMI-DB).Methods;Paired processed/unprocessed mammograms were obtained from OMI-DB. Ground-truth, image-level density values were calculated by passing unprocessed images through a commercial density estimation tool. AI tools, comprising feed-forward convolution neural networks, were then trained to reproduce these values from the corresponding processed mammograms.Results;Patient-level AI predictions for volumetric breast density demonstrated strong correlation with ground-truth values derived from unprocessed image counterparts (<span style="font-style:italic;">r; = 0.954-0.976). Models trained on less prevalent manufacturers performed worse (<span style="font-style:italic;">r; = 0.954 compared to 0.976 for the most prevalent manufacturer), highlighting the importance of collecting larger training datasets in future. Error levels were higher in patients with dense breasts. Model performance was generally consistent across screening sites but correlated with patient age, possibly due to the correlation of age and breast density.Conclusions;The presented models demonstrated good performance overall and were generally consistent across screening sites.Advances in knowledge;The presented AI tools provide a means of estimating breast density from processed mammograms, enabling further research into breast cancer epidemiology and risk where only processed mammograms are available.;

<span class="paragraphSection">Abstract;This paper presents a reproducible, data-driven approach for prioritisation of AI-detected chest X-ray (CXR) findings to support faster lung cancer diagnosis in the NHS. The Annalise Enterprise CXR system was deployed in shadow mode across seven acute trusts in Greater Manchester. Two cohorts were used: a retrospective cancer cohort (<span style="font-style:italic;">n; = 1,282) with confirmed lung cancer and visible CXR abnormalities, and a prospective cohort (<span style="font-style:italic;">n; = 13,802) comprising consecutively acquired GP-referred CXRs. Prevalence ratios were calculated for 124 AI-detected abnormalities across both cohorts, and three prioritisation strategies were developed. Strategy 3, which combined prevalence analysis with expert clinical review, achieved optimal performance with a sensitivity of 95.87% and estimated specificity of 79.11%, while maintaining a negative predictive value of 99.95%, for identification of lung cancer. Findings most associated with cancer included solitary lung mass, mediastinal mass, and hilar lymphadenopathy. An Excel-based tool was developed to support rapid configuration and evaluation of categorisation. Application of this approach enabled safe deployment of AI using shadow mode to inform configuration prior to live use. This work provides a scalable model for AI implementation in radiology workflows that aligns with the National Optimal Lung Cancer Pathway and addresses real-world challenges of diagnostic capacity, safety, and reproducibility.;

Objective;To assess the cost-effectiveness of using artificial intelligence (AI)–derived software to assist reading CT scans of the chest to identify and analyse lung nodules compared to unaided reading in symptomatic, incidental and screening populations.Methods;Decision tree structures were developed in TreeAge Pro 2021. Structures were informed by British Thoracic Society clinical guidelines and clinical opinion. Results were presented as incremental cost-effectiveness ratios (ICERs) expressed as cost per quality-adjusted life-year (QALY) over a lifetime from the UK National Health Service and Personal Social Services perspective.Results;For the symptomatic population, the unaided radiologist reading strategy dominated the AI-assisted reading strategy. In the incidental population, unaided radiologist reading was cost-effective with an ICER of approximately £1000 per QALY. Conversely, in the screening population, AI-assisted radiologist reading dominated unaided reading. The cause of AI assistance being cost-effective depended on the number of people who had undergone CT surveillance because of non-cancerous findings. Given the limitations in the quality and quantity of evidence to inform inputs, these results should be interpreted with caution.Conclusion;Current analyses based on limited evidence suggested that, in the symptomatic and incidental populations, unaided radiologist reading may be the more cost-effective strategy, while in the screening population, AI-assisted radiologist reading appeared to be the dominant strategy. Better quality evidence is required to have a definitive answer about their cost-effectiveness.Advances in knowledge;This paper shows whether adding AI-derived software to radiologists' reading of CT scans to identify lung nodules offers good value for money.;

<span class="paragraphSection">Abstract;Radiology is undergoing a major shift with the growing use of artificial intelligence (AI), and more change is expected with the emergence of agentic AI—systems that can initiate, manage, and coordinate tasks. So far, most discussions about AI’s impact on radiology follow 2 main approaches. The first, the “displacement” approach, tries to predict which jobs are most at risk of being replaced by AI. This narrative often warns that radiologists may be displaced. The second, the automation-versus-augmentation approach, looks within jobs to identify which tasks are likely to be fully automated (automation) and which will be improved by AI working alongside humans (augmentation). This paper introduces a third approach: <strong>reconfiguration</strong>. Instead of focusing on job loss or task replacement, the reconfiguration model looks at how AI changes the way tasks connect, how responsibilities shift, and how professional roles evolve. Drawing on recent research and developments in AI, this paper advances the reconfiguration approach and articulates why it offers a clearer way to understand—and help shape—the future of work in radiology. This paper offers a forward-looking reflection on the shifting nature of radiological work—clinically, educationally, and organizationally—as AI systems become increasingly integrated into practice.;

Objectives;Deep learning neural network (DLNN)-based tools can automate body composition analysis for cancer cachexia research. We aimed to evaluate a DLNN tool trained on a European population of Chinese cancer patients.Methods;Computed tomography (CT) images at the 3rd lumbar vertebral (L3) level of Chinese gastric cancer patients were retrospectively collected. An externally validated DLNN tool (Mosamatic) was used to segment skeletal muscle, visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT). Manual segmentation was performed using SliceOmatic software (TomoVision, version 5.0). Geometric similarity between automated and manual segmentation, and the reliability was assessed.Results;The cohort comprised 203 patients with a median body mass index (BMI) of 22.2 kg/m², and 604 CT images at L3 were collected. The median Dice Similarity Coefficient (IQR) of skeletal muscle, VAT and SAT were 0.973 (0.961-0.980), 0.980 (0.964-0.989), and 0.967 (0.945-0.977), respectively. The median Lin’s Concordance Correlation Coefficient for skeletal muscle area (0.983), VAT area (1.000), SAT area (0.998), skeletal muscle radiation attenuation (0.995), VAT radiation attenuation (0.994), and SAT radiation attenuation (0.997) demonstrated excellent reliability. Low BMI (<18.5 kg/m²) and ascites impaired the agreement between the 2 methods. The automated method showed high diagnostic concordance with manual segmentation for sarcopenia (<span style="font-style:italic;">κ ;= 0.843, <span style="font-style:italic;">P ;< .001) and myosteatosis (<span style="font-style:italic;">κ ;= 0.946, <span style="font-style:italic;">P ;< .001).Conclusions;The Mosamatic tool displays excellent generalizability to analyse body compositions in Chinese gastric cancer patients and can facilitate cachexia research.Advances in knowledge;The Mosamatic tool displayed excellent generalizability without recalibration to analyse body composition on the 3rd lumbar vertebral CT images in Chinese gastric cancer patients.;

<span class="paragraphSection">Abstract;Recent advances in artificial intelligence (AI) offer significant potential to address the growing bottleneck in radiology caused by an increasing volume of imaging studies amidst a global shortage of radiology professionals. This study presents a comprehensive review of the latest developments in AI, particularly in vision-language models for radiology report generation, providing radiologists with a current reference. We conducted a focused literature search for studies published from 2020 to 2024 and included 14 studies in our review specifically on chest X-ray datasets with limited coverage of 3D modalities, reflecting the early stage of research and ongoing methodological advances in report generation for volumetric imaging. We analysed the model architectures, report generation capabilities, training datasets, evaluation metrics, and performance of these models. Our review highlights the evolution of AI in radiology report generation and underscores the critical need for diverse datasets and standardized evaluation metrics. Despite rapid progress, current AI models are not yet capable of consistently producing high-quality reports and require further improvements in data diversity, model training, and evaluation metrics to achieve a level comparable to human experts.;

Objectives;There is a growing need to develop user-friendly, bladder-specific image analysis tools that can produce reliable artificial intelligence (AI)-quantitative imaging biomarkers (QIBs) derived from multiparametric (mp)MRI data for clinical applications. To address it, we developed an AI-powered BLADdEr multiparametric MRI Analysis for Clinical Application (AI-BLADE, current release v1.0) toolbox designed for extracting mpMRI-derived quantitative metrics.Methods;AI-BLADE is an advanced tool for bladder-specific mpMRI data analysis with 2 core functionalities: (1) Deep Feature Analysis (MRI-DFA toolkit) and (2) Data-Driven Model-Based Analysis (MRI-MBA toolkit). AI-BLADE offers customizable options and serves as a one-stop shop solution for bladder cancer (BCa) clinical applications. The models within DFA and MBA were tested separately on 2 patient cohorts. DFA was used to classify BCa histology subtypes (<span style="font-style:italic;">n; = 104) with T2-weighted images, while MBA was used to interrogate tumour physiology by deriving mpMRI QIBs, including apparent diffusion coefficient (ADC), and volume transfer constant (K^trans) obtained from 34 BCa patients.Results;Out of the 17 AI models tested, the VGG19 model with a decision tree classifier and no feature selection for the fully connected layer 7 achieved the highest area under the curve of the receiver operating characteristic of 0.79 in classifying BCa histology subtypes, demonstrating the strongest performance. The mean ADC and K^trans values were 1.22 × 10⁻³ (mm²/s) and 0.27 (min⁻¹), respectively, reflecting underlying tumour physiology.Conclusion;The AI-BLADE (v1.0), a flexible and user-friendly software toolbox for analysing mpMRI data, shows strong potential for application in BCa oncology, offering capabilities that can enhance diagnostic accuracy and support improved patient outcomes.Advances in knowledge;This is the first study to design, develop, and implement a novel bladder-specific AI toolbox for analysing mpMRI data. AI-BLADE enables an advanced image analysis workflow, facilitating AI-QIB-based clinical decision-making for patients with BCa.;

Objectives;Deep learning models developed for the classification of radiological reports have lacked explainability. We aimed to validate and explain a pretrained classification model by applying it to the removal of confounding data from a radiological dataset.Methods;Two radiologists categorized 2038 anonymized MRI head free-text radiology reports for abnormality and for small vessel disease presence. Of these reports, 80% (<span style="font-style:italic;">n; = 1630) were used to fine-tune pretrained transformer models to classify scans. Five-fold cross-validation was used in model development. The models were tested on the remaining 20% of the reports (<span style="font-style:italic;">n; = 408). SHapley Additive exPlanations (SHAP) were used to explain the results.Results;The models exhibited excellent classification performance, with a mean receiver operating characteristic (ROC) area under the curve (AUC) of 0.98 for abnormality classification and 0.99 for small vessel disease classification. SHAP highlighted relevant words in both cases.Conclusions;This application validated the use of a pretrained transformer in detecting confounding data in research cohorts, and exhibited explainable results that allow the models’ decisions to be understood. By highlighting the specific report terms that drive each prediction, the explainable model output can be reviewed and critiqued by subject matter experts, supporting trust, error analysis, and iterative refinement of AI tools within clinical workflows.Advances in knowledge;This application demonstrates the feasibility of explainable report classification, and the fine-tuned model could be used in future for automatic removal of confounding data from radiology datasets, while providing transparent, case-level justifications that support audit, governance, and clinician acceptance.;

Objectives;Dynamic MRI of the upper vocal tract is increasingly used to study speech. Image segmentation is often required to analyse the organs of speech; however, manual segmentation is labour intensive and time consuming and automatic methods are being developed. In this paper, a new hybrid transformer network is proposed for such task.Methods;We introduce a deep learning-based decoder model termed “Progressively Refinement Decoding (PRORED).” This model incorporates a directional field (DF) module designed to capture the contour details of features. The acquired contour information is leveraged to refine the boundaries both between and within classes. By integrating the DF module at different stages of the decoder, features are enhanced progressively, ensuring a more detailed and accurate segmentation.Results;Our model is evaluated using a publicly accessible speech MRI dataset and a cardiac dataset. The metrics employed are the Dice coefficient and the Hausdorff distance. Results indicate that our model attains an average Dice coefficient of 97.78% and a Hausdorff distance of 6.84 mm. Additionally, our network was able to identify closure patterns more efficiently than the baseline network and previously published work. In addition, the model was also evaluated on a cardiac dataset, and achieved 91.90% dice score.Conclusions;The proposed model leads to a more accurate segmentation of speech MRI data and in particular allows for a better velopharyngeal closure study. The proposed model was also evaluated on a cardiac dataset and achieved competitive performance, showing its strong generalizability.Advances in knowledge;First model that utilizes vision transformer and progressive refinement decoder to segment dynamic speech MRI.;

<span class="paragraphSection">Abstract;Liver diseases consistently plague people’s daily lives as a result of their high morbidity and mortality rates. Ultrasound (US), favoured by its flexibility, free of radiation, cost-effectiveness, and real-time capabilities, has been commonly employed as one of the first-line imaging tools for hepatic conditions. Artificial intelligence (AI) algorithms are increasingly applied to automatically identify intricate patterns and perform quantitative analyses in US imaging, potentially reducing radiologists’ workload and improving diagnostic efficiency. AI-based US has been of substantial assistance in detecting, diagnosing, screening as well as monitoring of various liver diseases, and has attracted extensive attention among the medical community. In this review, we present a general introduction to AI in medical imaging; we next review its rapidly evolving applications in liver US, covering evaluation of hepatic steatosis severity, assessment of liver fibrosis, identification of focal hepatic lesions, preoperative prediction of high-risk pathological characteristics, assessment of postoperative prognosis, and the analysis of the model of integrated application of multi-omics data; finally, we present an outlook on the clinical applications of AI-based US in the liver diseases.;