BJR artificial intelligence最新文献

{"title":"Autonomous reporting of 'normal' chest X-rays by artificial intelligence in the United Kingdom; can we take the human out of the loop?","authors":"Katrina Nash, James Vaz, Ahmed Maiter, Christopher S Johns, Nicholas Woznita, Aditya U Kale, Abdala T Espinosa Morgado, Rhidian Bramley, Mark Hall, David Lowe, Alex Novak, Sarim Ather","doi":"10.1093/bjrai/ubag008","DOIUrl":"10.1093/bjrai/ubag008","url":null,"abstract":"<p><p>Chest X-rays (CXRs) are the most commonly performed imaging investigation. In the UK, many centers experience reporting delays due to radiologist workforce shortages. Artificial intelligence (AI) tools capable of distinguishing \"normal\" from \"abnormal\" CXRs have emerged as a potential solution. If \"normal\" CXRs could be safely identified and reported without human input, a substantial portion of radiology workload could be reduced. This article examines the feasibility and implications of autonomous AI reporting of \"normal\" CXRs, using the United Kingdom as an example setting. Key issues include defining \"normal,\" ensuring generalizability across populations, and managing the sensitivity-specificity trade-off. It also addresses legal and regulatory challenges, such as compliance with IR(ME)R and GDPR, and the lack of accountability frameworks for errors. Further considerations include the impact on radiologists practice, the need for robust post-market surveillance, and incorporation of patient perspectives. While the benefits are clear, adoption must be cautious, with strong governance, legal clarity, and rigorous clinical validation to ensure safe and sustainable use.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag008"},"PeriodicalIF":0.0,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13353222/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148428067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and evaluation of artificial intelligence tools to estimate volumetric breast density from processed 2D mammograms.","authors":"Sam Ellis, Sandra Gomes, Mark D Halling-Brown, Kenneth C Young, Lucy M Warren","doi":"10.1093/bjrai/ubag009","DOIUrl":"10.1093/bjrai/ubag009","url":null,"abstract":"<p><strong>Objectives: </strong>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).</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>Patient-level AI predictions for volumetric breast density demonstrated strong correlation with ground-truth values derived from unprocessed image counterparts (<i>r</i> = 0.954-0.976). Models trained on less prevalent manufacturers performed worse (<i>r</i> = 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.</p><p><strong>Conclusions: </strong>The presented models demonstrated good performance overall and were generally consistent across screening sites.</p><p><strong>Advances in knowledge: </strong>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.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag009"},"PeriodicalIF":0.0,"publicationDate":"2026-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13187629/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147990670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cost-effectiveness of radiologist reading of chest CT scans assisted by software with artificial intelligence-derived algorithms for the detection and analysis of lung nodules.","authors":"Peter Auguste, Hesam Ghiasvand, Julia Geppert, Asra Asgharzadeh, Anna Brown, Mubarak Patel, Daniel Gallacher, Emma Helm, Sian Taylor-Phillips, Yen-Fu Chen, Jason Madan","doi":"10.1093/bjrai/ubag004","DOIUrl":"https://doi.org/10.1093/bjrai/ubag004","url":null,"abstract":"<p><strong>Objective: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusion: </strong>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.</p><p><strong>Advances in knowledge: </strong>This paper shows whether adding AI-derived software to radiologists' reading of CT scans to identify lung nodules offers good value for money.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag004"},"PeriodicalIF":0.0,"publicationDate":"2026-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045519/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic prioritisation of AI-detected chest X-ray abnormalities for optimised lung cancer detection.","authors":"Rhidian R Bramley, Anna C Sharman, Rebecca Duerden, Sarah Lyon, Melissa Ryan, Elodie Weber, Louise Brown, Matthew Evison","doi":"10.1093/bjrai/ubag007","DOIUrl":"10.1093/bjrai/ubag007","url":null,"abstract":"<p><p>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 (<i>n</i> = 1,282) with confirmed lung cancer and visible CXR abnormalities, and a prospective cohort (<i>n</i> = 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.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag007"},"PeriodicalIF":0.0,"publicationDate":"2026-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13070793/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reconfiguring work: artificial intelligence, agentic AI, and the future of the radiology profession.","authors":"Angela Aristidou","doi":"10.1093/bjrai/ubag006","DOIUrl":"10.1093/bjrai/ubag006","url":null,"abstract":"<p><p>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: <b>reconfiguration</b>. 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.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag006"},"PeriodicalIF":0.0,"publicationDate":"2026-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045514/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Independent validation of the Mosamatic deep learning automated skeletal muscle and adipose tissue segmentation tool in an external Chinese cancer patient cohort.","authors":"Chenfei Zhou, Xuekun Zhang, David P J van Dijk, Sander S Rensen, Jun Zhang, Leroy Volmer, Leonard Wee, Steven W M Olde Damink","doi":"10.1093/bjrai/ubaf021","DOIUrl":"10.1093/bjrai/ubaf021","url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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 (<i>κ </i>= 0.843, <i>P </i>< .001) and myosteatosis (<i>κ </i>= 0.946, <i>P </i>< .001).</p><p><strong>Conclusions: </strong>The Mosamatic tool displays excellent generalizability to analyse body compositions in Chinese gastric cancer patients and can facilitate cachexia research.</p><p><strong>Advances in knowledge: </strong>The Mosamatic tool displayed excellent generalizability without recalibration to analyse body composition on the 3rd lumbar vertebral CT images in Chinese gastric cancer patients.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubaf021"},"PeriodicalIF":0.0,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045518/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recent advances in artificial intelligence for radiology report generation: a brief review.","authors":"Caitlyn Tran, Basudha Pal, Thomas Stirrat, Victoria Shi, Muhammad Umair","doi":"10.1093/bjrai/ubag003","DOIUrl":"10.1093/bjrai/ubag003","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag003"},"PeriodicalIF":0.0,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045517/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-BLADE toolbox: AI-powered BLADdEr multiparametric MRI analysis for clinical application.","authors":"Muhammad Awais, Ramesh Paudyal, Oguz Akin, Samuel Gold, Stephanie Chahwan, Josip Nincevic, Lisa Ruby, Bernard H Bochner, Jonathan Rosenberg, David Aggen, Hikmat Al-Ahmadie, Alvin C Goh, Lawrence H Schwartz, Amita Shukla-Dave","doi":"10.1093/bjrai/ubag002","DOIUrl":"10.1093/bjrai/ubag002","url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>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 (<i>n</i> = 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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusion: </strong>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.</p><p><strong>Advances in knowledge: </strong>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.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag002"},"PeriodicalIF":0.0,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045516/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explaining transformer-based classification of radiology reports.","authors":"Megan Courtman, Galaleldin Abdelhalim, Lingfen Sun, Emmanuel Ifeachor, Stephen Mullin, Mark Thurston","doi":"10.1093/bjrai/ubag001","DOIUrl":"10.1093/bjrai/ubag001","url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>Two radiologists categorized 2038 anonymized MRI head free-text radiology reports for abnormality and for small vessel disease presence. Of these reports, 80% (<i>n</i> = 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 (<i>n</i> = 408). SHapley Additive exPlanations (SHAP) were used to explain the results.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>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.</p><p><strong>Advances in knowledge: </strong>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.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag001"},"PeriodicalIF":0.0,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045515/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PRORED: a hybrid transformer framework with progressive refinement decoding for segmenting dynamic speech MRI.","authors":"Ying He, Qianni Zhang, Marc E Miquel","doi":"10.1093/bjrai/ubaf020","DOIUrl":"10.1093/bjrai/ubaf020","url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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 <math><mi>%</mi></math> 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 <math><mi>%</mi></math> dice score.</p><p><strong>Conclusions: </strong>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.</p><p><strong>Advances in knowledge: </strong>First model that utilizes vision transformer and progressive refinement decoder to segment dynamic speech MRI.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubaf020"},"PeriodicalIF":0.0,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13045520/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}