BJR artificial intelligence最新文献

{"title":"Aligning brain tumor imaging: generating synthetic 3D FA maps from T1-weighted MRI using CycleGAN models.","authors":"Xin Du, Francesca M Cozzi, Stephen J Price, Rajesh Jena","doi":"10.1093/bjrai/ubag019","DOIUrl":"10.1093/bjrai/ubag019","url":null,"abstract":"<p><strong>Objectives: </strong>This study addresses the issue of spatial misalignment between fractional anisotropy (FA) maps and tractography atlases in neuroimaging. We propose a CycleGAN-based method to generate FA and directionally encoded color (DEC) maps directly from T1-weighted MRI scans, applicable to both healthy and tumor-affected cases.</p><p><strong>Methods: </strong>A CycleGAN model was developed and trained using unpaired data to convert T1-weighted MRI images into FA and DEC maps. The quality of the generated maps was assessed using Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) metrics. Special emphasis was placed on evaluating performance in tumor regions. Radiological assessments were also conducted to determine the clinical applicability of the generated maps.</p><p><strong>Results: </strong>The CycleGAN-based model effectively generated high-fidelity FA and DEC maps, with robust SSIM and PSNR values, particularly in tumor regions. Radiological evaluations highlighted the potential of this approach to enhance clinical workflows, offering a reliable AI-driven alternative to traditional image processing methods.</p><p><strong>Conclusions: </strong>This CycleGAN-based approach successfully mitigates the problem of spatial misalignment by generating accurate FA and DEC maps from T1-weighted MRI scans. The method offers a promising pathway for integrating assessments of white matter integrity into predictive models without requiring additional imaging.</p><p><strong>Advances in knowledge: </strong>This study introduces the first use of CycleGAN for generating FA and DEC maps from T1-weighted images for tumor-affected cases, presenting a method that could enhance neuroimaging procedures by reducing the need for additional scans and improving efficiency in clinical settings.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag019"},"PeriodicalIF":0.0,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13648209/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149140113","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":"Casting wider than U-Nets: evaluating the role of novel machine learning applications in radiation therapy.","authors":"Osama Omrani, Sayan Biswas, Rajesh Jena","doi":"10.1093/bjrai/ubag018","DOIUrl":"10.1093/bjrai/ubag018","url":null,"abstract":"<p><p>Radiation oncology has proven an early adopter of machine learning (ML) and deep learning (DL) owing to its image-centered workflow and data richness. DL auto-segmentation of normal structures is already guideline-endorsed, with self-configuring nnU-Net delivering near-state-of-the-art accuracy and widely adopted. In this review, we explore advances in ML algorithms in processing and interpreting imaging-based data beyond normal tissue auto-segmentation with applications upstream and downstream of this task, highlighting training data volume and best-in-class architectures. Applications discussed range from diagnostics with \"virtual biopsies\" and automated staging to radiotherapy planning with gross tumor volume and clinical target volume (CTV) prediction. We illustrate the developments of cutting-edge transformer-based designs and foundation models, but also the important role of lightweight, task-specific classical ML models. Data scarcity may be eased by developments in few-shot learning (FSL) and transfer learning strategies. We also consider how end-to-end automated CTV delineation may require an agentic approach to mimic the reasoning of a radiation oncologist, capable of processing multi-modal data with clinical context. Together, these advancements point toward a future where ML will become increasingly central to radiation oncology practice. However, implementation of these tools beyond normal tissue auto-segmentation remains limited and will require careful assessment and validation in the clinic.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag018"},"PeriodicalIF":0.0,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13648204/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149140080","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":"Federated artificial intelligence monitoring service (FAMOS): an in silico feasibility study.","authors":"Aysha Luis, Andrew Scarsbrook, Mariusz Grzeda, Jesus Perdomo Lampignano, Matt Clark, Bob Wheller, Jack Baldwin, James Cairns, Simran Dhesi, Mark Hall, David J Lowe, Haris Shuaib","doi":"10.1093/bjrai/ubag016","DOIUrl":"https://doi.org/10.1093/bjrai/ubag016","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate feasibility of a federated AI monitoring service (FAMOS) for post-deployment surveillance of third-party AI applications used in chest X-ray (CXR) interpretation.</p><p><strong>Methods: </strong>FAMOS was deployed at 2 NHS Trusts using a federated architecture enabling local data processing while maintaining data governance compliance. De-identified CXRs from patients aged >18 years were retrospectively identified, along with relevant patient attributes (age, sex, inpatient status, image orientation, season, artefact). Chest X-rays were processed by 2 AI applications to simulate real-world deployment. FAMOS analyzed input data, AI inference values, and longitudinal human-AI agreement as proxy indicators of data, prediction, and behavioral drift. Input monitoring used image feature embeddings analyzed with principal component analysis and Hotelling's <i>T</i>² statistics, while risk-adjusted cumulative sum charts were applied to sequentially monitor AI inference values. human-AI agreement was evaluated at 10 time points over 3 months.</p><p><strong>Results: </strong>Input monitoring identified a small proportion of outlier examinations, predominantly associated with modifiable image quality issues. Artificial intelligence inference values remained stable across most findings for both vendors, with limited drift events detected. Human-AI agreement patterns differed between sites, remaining stable at 1 site while increasing over time at another, suggesting evolving automation bias.</p><p><strong>Conclusions: </strong>Real-time, federated monitoring of deployed radiology AI systems is technically and operationally feasible within clinical environments. Multi-domain platform-based monitoring provides scalable, independent oversight and may function as an early-warning system supporting identification of emerging risks following deployment.</p><p><strong>Advances in knowledge: </strong>This study introduces a federated, multi-domain monitoring framework integrating sociotechnical indicators for continuous post-deployment surveillance of clinical radiology AI tools.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag016"},"PeriodicalIF":0.0,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13623527/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149121865","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":"Analysis of leg bone lengths from whole-body dual-energy X-ray absorptiometry in the UK biobank.","authors":"Faten Alomar, Junkai Wang, Timothy F Cootes","doi":"10.1093/bjrai/ubag014","DOIUrl":"https://doi.org/10.1093/bjrai/ubag014","url":null,"abstract":"<p><strong>Objectives: </strong>To calculate the distributions of leg bone lengths (as measured from dual-energy X-ray absorptiometry [DXA] images) and their relationship with height. Estimating human height from long bone measurements is widely used in forensic and biological anthropology.</p><p><strong>Methods: </strong>An automated system was developed to find the outlines of the femur and tibia in DXA images from the UK Biobank. These were used to measure the length of the bones. Images with implants, severe abnormalities, or missing data were excluded. Relationships between lengths and with height were estimated using linear regression.</p><p><strong>Results: </strong>Of the 73 405 available DXA images, we successfully measured both femurs and tibia in 66 730 cases (91%). The lengths of femurs and tibias for males and females each show normal distributions, with left and right being very similar. The mean absolute difference between measurements at 2 time points was below 1.8 mm (femur), 2.3 mm (tibia), showing the system is repeatable. Linear regression gives the relationships between individual bone lengths and between them and height.</p><p><strong>Conclusions: </strong>The developed software system and the resulting analysis provide promising insights into bone geometry using DXA imaging, enabling large-scale, precise bone measurements. These models are relevant for predicting height, a subject of interest in archaeology and forensic science.</p><p><strong>Advances in knowledge: </strong>This is the largest study of the distributions of leg bone lengths and their relationship to height that we are aware of.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag014"},"PeriodicalIF":0.0,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13623526/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149121839","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":"Artificial intelligence in ultrasound: divergent pathways, shared challenges.","authors":"Viksit Kumar, Michael Blaivas","doi":"10.1093/bjrai/ubag015","DOIUrl":"https://doi.org/10.1093/bjrai/ubag015","url":null,"abstract":"<p><p>Artificial intelligence (AI) in ultrasound is often reviewed as a unified field, though in practice it spans 3 distinct deployment environments: clinical radiology (traditional imaging) ultrasound, point-of-care users, and ultrasound education. The 3 environments share the same underlying AI methods but differ in image quality, operator skill, time allotted to scan, regulatory exposure, and acceptable failure modes. In clinical radiology ultrasound, FDA-cleared decision support is routine for breast and thyroid lesion characterization, obstetric biometry, and cardiac quantification, and emerging in liver, vascular, and interventional imaging. In point-of-care ultrasound, AI enables bedside clinicians to acquire diagnostic images under real-time guidance and to document examinations that would otherwise go unrecorded. In education, AI reshapes competency assessment and scales instruction. This article offers the practicing radiologist and imaging specialist a framework for matching AI to deployment context, names the mature applications in each pathway, and addresses cross-cutting challenges (data, validation, regulation, bias, liability, reimbursement, environmental cost) that every deployment must navigate. The recurring message: treating \"ultrasound AI\" as a monolith is a repeated error, and honest attention to deployment context matters most.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag015"},"PeriodicalIF":0.0,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13649578/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149168778","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":"A 7-criteria evaluation approach for the responsible use of synthetic medical data.","authors":"Ghada Zamzmi, Adarsh Subbaswamy, Rucha Deshpande, Diksha Sharma, Jana G Delfino, Aldo Badano","doi":"10.1093/bjrai/ubag005","DOIUrl":"https://doi.org/10.1093/bjrai/ubag005","url":null,"abstract":"<p><strong>Purpose: </strong>To develop an approach for evaluating and reporting the quality of synthetic medical data (SMDs).</p><p><strong>Method: </strong>As SMDs become increasingly common, their responsible utilization benefits from a detailed characterization of their quality and value within the intended usage context. Here, we introduce an approach to assess SMDs across 7 dimensions: Congruence, Coverage, Constraint, Consistency, Comprehension, Compliance, and Completeness. We also describe an approach for reporting the quality of synthetic data to stakeholders.</p><p><strong>Results: </strong>We applied the proposed approach to 7 digital mammography datasets. The analysis underscored the strengths and limitations of each dataset across these dimensions. For example, while datasets generated by generative AI methods show high Congruence, they often fall short in Constraint and Completeness compared to those generated by knowledge-based methods. Additionally, our findings highlighted that the quality of generated data varies across different subgroups (eg, breast density) with certain subgroups (ie, dense and hetero) showing lower quality. This suggests that subgroup-specific fine-tuning of the generative process may have an effect on downstream tasks.</p><p><strong>Conclusions: </strong>The proposed approach provides stakeholders with a tool for assessing data quality, which may be used to better understand and analyse synthetic datasets..</p><p><strong>Advances in knowledge: </strong>This study introduces an approach for assessing SMD quality. The approach offers a practical mechanism for reporting SMD quality, which can enhance the reliability and usefulness of synthetic datasets.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag005"},"PeriodicalIF":0.0,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13476082/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148766206","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":"Predictive deep learning model based on contrast-enhanced mammography for breast cancer diagnosis: a pilot study.","authors":"Roberto Maroncelli, Chiara De Nardo, Veronica Rizzo, Federica Cicciarelli, Marcella Pasculli, Francesca Galati, Federica Pediconi","doi":"10.1093/bjrai/ubag013","DOIUrl":"10.1093/bjrai/ubag013","url":null,"abstract":"<p><strong>Objectives: </strong>The interpretation of contrast-enhanced mammography (CEM) images heavily depends on radiologists' expertise, highlighting the need for automated tools to assist clinical decision-making. This pilot study aimed to develop a deep learning model using CEM images to predict the histological diagnosis of breast cancer.</p><p><strong>Methods: </strong>We retrospectively analyzed patients who underwent CEM followed by histopathological assessment (October 2022-May 2023) across 2 centers. CEM images from center 1 were used for model development, including training and 10-fold cross-validation, while images from center 2 served as an independent external test set. The breast region was manually segmented, and 2 deep learning architectures were implemented as ensemble classifiers, using biopsy results as reference standard. Performance metrics included accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the Receiver Operating Characteristic Curve (ROC) curve (AUC).</p><p><strong>Results: </strong>A total of 106 CEM images were retrospectively analyzed (50 from center 1 and 56 from center 2), obtained using different mammography systems. Histopathology identified 51 lesions (48%) as malignant and 55 (52%) as benign. Cross-validation yielded an ROC-AUC of 75% [58.4-91.6], accuracy of 68.7% [58.3-79], sensitivity of 68.9% [52.2-85.6], specificity of 67.8% [65.4-70.2], PPV of 69.3% [55.5-83.1], and NPV of 73.5% [55.2-91.8] (<i>P</i> < .05). External testing on images from center 2 (27 malignant, 29 benign) achieved an accuracy of 64.3%.</p><p><strong>Conclusions: </strong>The study showed promising performance but requires further development and dataset expansion. The model has the potential to be integrated into clinical practice.</p><p><strong>Advances in knowledge: </strong>A deep learning model based on CEM provides a tool to support physicians in the decision-making process and reduce invasiveness in breast cancer management.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag013"},"PeriodicalIF":0.0,"publicationDate":"2026-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13394488/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148582016","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":"Radiomics-based mammographic abnormality identification via radiologist annotations.","authors":"Ravi Bullock, Yiwen Xu, Rasika Rajapakshe","doi":"10.1093/bjrai/ubag012","DOIUrl":"10.1093/bjrai/ubag012","url":null,"abstract":"<p><strong>Objective: </strong>This study developed a radiomics-based pipeline to identify suspicious findings on 2D screening mammograms by training models to distinguish radiologist-annotated abnormalities from normal breast tissue.</p><p><strong>Methods: </strong>A total of 1604 screening mammograms (<i>n</i> = 1294 participants) were used in this retrospective study. Each mammogram included an original capture image, and a secondary capture image with a single radiologist-drawn annotation indicating a region of interest (ROI) with an abnormality. The annotation on each secondary capture image was used to select an ROI in the original image. An ROI with normal tissue was automatically selected from the remaining breast tissue for comparison. Radiomics features were extracted from the ROIs with abnormalities and normal tissue. Feature selection was performed using the SciKit-Learn SelectKBest method with Chi-squared, analysis of variance (ANOVA) <i>F</i>-, and mutual information score functions. Logistic regression, random forest, XGBoost, bagging, discriminant analysis (DA), and support vector machine classifiers were trained on the selected features. The model performance was evaluated with the area under the receiver operating characteristic curve (AUC) on a holdout test set.</p><p><strong>Results: </strong>While AUC values ranged from 0.69 to 0.73, no significant differences were observed between models (DeLong test, <i>P</i> > .05). The nominally highest performance was achieved via ANOVA <i>F</i>-score feature selection and DA (AUC: 0.73; 95% CI, 0.70-0.77).</p><p><strong>Conclusion: </strong>The radiomics-based pipeline shows promise in distinguishing abnormalities from normal tissue on screening mammograms.</p><p><strong>Advances in knowledge: </strong>Radiomics has the potential to enhance breast cancer detection and is a step towards the integration of advanced machine learning into screening workflows.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag012"},"PeriodicalIF":0.0,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13322293/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371611","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":"Establishing a framework for development, prioritization, and assessment of artificial intelligence technology within the radiology department at a large UK teaching hospital.","authors":"James H R Cairns, Beverley Riley, Hanif Ismail, Bashar Al-Qaisieh, Mohua Siddique, Christopher Herbert, Bob Wheller, Fahmid U H Chowdhury, Andrew Scarsbrook","doi":"10.1093/bjrai/ubag011","DOIUrl":"10.1093/bjrai/ubag011","url":null,"abstract":"<p><p>Artificial intelligence (AI) can revolutionize clinical workflows in radiology but requires organizational change. An institutional strategy to develop and evaluate AI tools is outlined. A multidisciplinary AI board with a patient and public involvement and engagement group was created. A comprehensive framework was formed, comprising workstreams covering information governance; technical rigor, performance, and safety; economic considerations; and ethical and medical-legal aspects. In addition to recurring meetings, a workshop with clinicians, information technology specialists, and patient representatives helped to identify priority use cases. Technical infrastructure was enhanced to support the development, performance assessment, and deployment of AI tools. Primary areas for AI applications included training staff, vetting of image requests, quality assurance, image interpretation, and communicating imaging findings to patients. Potential barriers, gaps in evidence, and subsequent actions for AI implementation were outlined. Avenues for collaboration with industry and market-available solutions were outlined. A virtual Picture Archiving and Communication System server was developed and then connected to a deployment platform for performance evaluation of AI products. Establishing an institutional AI board and imaging AI sandbox has guided safe, effective AI implementation while creating an ideal setting for innovation and industry partnership. Our approach to the integration of imaging AI provides a pragmatic guide for other institutions.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag011"},"PeriodicalIF":0.0,"publicationDate":"2026-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13235739/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148201901","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":"Restoration of missing regions in limited field of view computer tomography using an image- and sinogram-based conditional generative adversarial network model.","authors":"Hideaki Hirashima, Kohei Arimoto, Takao Onishi, Megumi Nakao, Takashi Mizowaki, Mitsuhiro Nakamura","doi":"10.1093/bjrai/ubag010","DOIUrl":"10.1093/bjrai/ubag010","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to restore missing regions from the limited field of view (FOV) using image- and sinogram-based conditional GAN (cGAN) models.</p><p><strong>Methods: </strong>cGANs are deep learning frameworks that generate realistic data via a competitive neural network process. We used planning CT (pCT) datasets from 96 patients: 64 for training, 16 for validation, and 16 for internal testing. Two cGAN models (image-based and sinogram-based) were developed to generate body contour outside the FOV. Next, 23 cone-beam CT (CBCT) datasets were evaluated as an external test group.</p><p><strong>Results: </strong>In pCT internal test datasets, the median values for mean absolute error (MAE), root mean square error (RMSE), and structural similarity index measure (SSIM) for each model were as follows: image-based model-101.73 HU for MAE, 39.26 HU for RMSE, and 0.83 for SSIM; sinogram-based model-16.91 HU for MAE, 23.19 HU for RMSE, and 0.91 for SSIM. In CBCT external test datasets, the sinogram-based model outperformed the image-based model with a median MAE of 73.32 HU versus 180.72 HU, a median RMSE of 37.02 HU versus 43.42 HU, and a median SSIM of 0.75 versus 0.63. The sinogram-based model demonstrated significant improvements in MAE, RMSE, and SSIM (<i>P </i>< .05).</p><p><strong>Conclusions: </strong>The sinogram-based cGAN model exhibits considerable potential for restoring missing regions outside the FOV, outperforming the image-based model in accuracy metrics.</p><p><strong>Advances in knowledge: </strong>This model offers a novel approach to accurately predict missing regions from a limited FOV, enhancing continuity of the body contour while accommodating patient-specific variations.</p>","PeriodicalId":517427,"journal":{"name":"BJR artificial intelligence","volume":"3 1","pages":"ubag010"},"PeriodicalIF":0.0,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13290481/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148335427","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}