Diagnostic and Interventional Imaging最新文献

{"title":"Artificial intelligence in emergency musculoskeletal imaging: A critical review of current applications","authors":"Brian Tsang,&nbsp;Bo Gong,&nbsp;Linda Probyn,&nbsp;Michael N. Patlas","doi":"10.1016/j.diii.2026.02.003","DOIUrl":"10.1016/j.diii.2026.02.003","url":null,"abstract":"<div><div>Artificial intelligence (AI) is increasingly shaping emergency musculoskeletal imaging, where rapid and accurate diagnosis is often challenged by high imaging volumes and time pressure. These constraints increase the risk of missed injuries and underscore the need for tools that support faster and reliable assessments. AI systems show promise in improving workflow efficiency by prioritizing urgent studies, guiding modality selection, and reducing reporting delays. Deep learning models can enhance abnormality detection by identifying fractures, soft tissue injuries, and infectious processes, and can provide structured classifications that support clinical decision making. Pediatric-focused AI systems address age-specific developmental considerations and offer valuable support for clinicians with varying levels of pediatric musculoskeletal expertise. Large language models further expand the role of AI by improving report clarity, generating structured impressions, and facilitating communication with clinicians, patients, and families. Despite these advances, challenges remain, including limited external validation, dataset bias, and medicolegal considerations. This review summarizes current AI applications across these domains and highlights key strengths, limitations, and future directions for safe and effective integration into emergency musculoskeletal imaging.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 7","pages":"Pages 247-255"},"PeriodicalIF":11.1,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147311644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved visualization of the Adamkiewicz artery with photon-counting CT","authors":"Yu-Cheng Huang,&nbsp;Salim Si-Mohamed,&nbsp;Angèle Houmeau,&nbsp;Antoine Millon,&nbsp;Philippe Douek,&nbsp;Sara Boccalini","doi":"10.1016/j.diii.2026.01.004","DOIUrl":"10.1016/j.diii.2026.01.004","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 7","pages":"Pages 276-278"},"PeriodicalIF":11.1,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146047298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Training for the unknown: Artificial intelligence-driven early detection of pancreatic cancer","authors":"Felipe Lopez-Ramirez,&nbsp;Theodore Aouad,&nbsp;Elliot K. Fishman","doi":"10.1016/j.diii.2026.02.006","DOIUrl":"10.1016/j.diii.2026.02.006","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 7","pages":"Pages 245-246"},"PeriodicalIF":11.1,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147285723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Precision imaging and minimally invasive therapy in osteoid osteoma.","authors":"Mickael Tordjman, Valerie Bousson","doi":"10.1016/j.diii.2026.06.008","DOIUrl":"https://doi.org/10.1016/j.diii.2026.06.008","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":11.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148363251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interstitial lung disease pattern recognition on full high resolution computed tomography volume: Development and evaluation of a decision-support tool for less-experimented radiologists.","authors":"Valentin Ong, Rafael Marini, Raphael Borie, Constance De Margerie-Mellon, Mathieu Lederlin, Samia Boussouar, Nisrine Chalhoub, Sarra Sahraoui, Denis Habip Gatenyo, Nicolas Billet, Penelope Gaillot, Sara Benchara, Ghita Miyara, Camille-Albane Pincet, Francesco Dellavalle, Jean-Baptiste Safa, Luc Mouthon, Bruno Crestani, Isabelle Honore, Abdellatif Tazi, Gwenaël Lorillon, Marie-Pierre Debray, Guillaume Chassagnon","doi":"10.1016/j.diii.2026.06.005","DOIUrl":"https://doi.org/10.1016/j.diii.2026.06.005","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to develop an artificial intelligence (AI) tool to assist recognition of three major interstitial lung disease (ILD) patterns on high-resolution computed tomography (HRCT) and to evaluate its added value in supporting decision-making for non-specialist radiologists.</p><p><strong>Material and methods: </strong>This retrospective, multicenter study included 1097 HRCT examinations. Of these, 989 (90.15%) were used for development and 108 (9.85%) for external testing. A two-stage architecture inspired by domain-specific pretraining was employed. The encoder of a three-dimensional ILD segmentation model was kept to extract 7168 disease-specific features per HRCT, which were combined with age and sex in a deep learning model to predict three radiological patterns (usual interstitial pneumonia, non-specific interstitial pneumonia and fibrotic bronchiolocentric interstitial pneumonia) as diagnosed in multidisciplinary discussions (MDD). The external test dataset was interpreted by seven thoracic radiologists to establish a second reference (majority's vote) and by eight radiology residents with and without AI assistance. Accuracy, sensitivity and specificity were calculated for each pattern.</p><p><strong>Results: </strong>The AI system achieved 77.8% accuracy on the external test dataset using MMD as a reference standard, within the range of thoracic experts (median, 75.6%; range: 61.1-81.5). AI assistance improved residents' median accuracy (+14.8% of absolute increase) and reduced reading time by 20.7% (P < 0.001). Six out of eight residents assisted by AI (75%) performed worse than AI alone.</p><p><strong>Conclusion: </strong>AI can accurately classify major ILD patterns and help less-experienced readers improve their performance. However, the level of improvement was inconsistent, and non-specialists rarely equaled the performance of AI alone.</p>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":11.1,"publicationDate":"2026-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148340755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Breast cryoablation: What does the current evidence allow us to say?","authors":"Maxime Barat, Anthony Dohan","doi":"10.1016/j.diii.2026.06.007","DOIUrl":"https://doi.org/10.1016/j.diii.2026.06.007","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":11.1,"publicationDate":"2026-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148340712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simultaneous pulmonary ventilation and perfusion imaging using spectral photon counting CT with xenon and gadolinium-based agents in combination with color K-edge imaging.","authors":"Antoine Robert, Sofia Poletto, Klaus Erhard, Maria Nicole Antonuccio, Christian A Hernandez, Agnieszka Gutwinska, Ramata Seydou Coulibaly, Florian Davaux, Jean-Baptiste Langlois, Loic Boussel, Philippe Douek, Vincent Cottin, Simon Rit, Raffaele L Dellacà, Sam Bayat, Salim A Si-Mohamed","doi":"10.1016/j.diii.2026.06.003","DOIUrl":"https://doi.org/10.1016/j.diii.2026.06.003","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to assess the feasibility of color K-edge imaging enabled by spectral photon-counting CT (SPCCT) for simultaneous ventilation-perfusion evaluation using xenon and a gadolinium-based agent within healthy rabbit lungs.</p><p><strong>Materials and methods: </strong>In this animal study, a clinical SPCCT prototype was used to perform lung imaging in five New Zealand white rabbits. A phantom study was performed to assess gadolinium quantification accuracy and cross-contamination. Animals underwent controlled mechanical ventilation with xenon gas wash-in and received an intravenous injection of a gadolinium-based ultrasmall rigid platform (USRP) (dose, 2.3 mL·kg^-1; injection rate, 3 mL·s^-1; concentration, 0.29 mmol Gd.mL^-1). Material decomposition yielded specific xenon and gadolinium K-edge images. Xenon maps were validated against dynamic specific ventilation maps using Pearson correlation test and linear regression analysis. Regional lung distribution was analyzed using Kruskal-Wallis test.</p><p><strong>Results: </strong>Five rabbits (mean weight, 2.9 ± 0.06 [standard deviation] kg) were evaluated. In phantoms, measured gadolinium concentrations showed a perfect linear correlation with prepared concentrations (R² = 1). In vivo, normalized steady-state xenon maps demonstrated a strong correlation with specific ventilation maps, with a pooled Pearson correlation coefficient of 0.88 and a pooled R² of 0.78. Simultaneous imaging revealed a homogeneous xenon distribution with a median value across rabbits of 60.2% (first quartile [Q1], 59.3%; third quartile [Q3], 67.9%), with no significant regional differences. The median gadolinium perfusion across rabbits was 6.1% (Q1, 3.0%; Q3, 7.1%), with a significant dorsal-ventral gradient (P < 0.05) where the median value increased from 0.2% (Q1, -0.2%; Q3, 1.3%) in ventral regions to 6.9% (Q1, 3.8%; Q3, 10.6%) in dorsal regions.</p><p><strong>Conclusion: </strong>Color K-edge xenon/gadolinium-enhanced lung imaging using SPCCT is feasible in healthy animals, enabling the simultaneous specific and quantitative imaging of lung gas and blood volume.</p>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":11.1,"publicationDate":"2026-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148320012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Occupational radiation exposure and radiation protection practices in interventional radiology and cardiology: A multicenter study in France.","authors":"Cyril Duverger, Djamel Dabli, Jean-Paul Beregi, Guillaume Cayla, Julien Frandon, Joël Greffier","doi":"10.1016/j.diii.2026.06.006","DOIUrl":"https://doi.org/10.1016/j.diii.2026.06.006","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to assess occupational radiation exposure and radiation protection practices among physicians performing interventional radiology and cardiology procedures in France.</p><p><strong>Materials and methods: </strong>This retrospective multicenter study included 138 radiologists and 106 cardiologists from 17 French centers between 2019 and 2021. Data regarding passive dosimetry monitoring, radiation protection training, and availability and use of collective and personal protective equipment were collected. Whole-body, extremity, and eye lens dosimetry results were analyzed according to specialty and activity. Only physicians reporting systematic or frequent dosimeter use were included in the quantitative dosimetry analysis.</p><p><strong>Results: </strong>Whole-body dosimeters were available for all physicians, whereas extremity and eye lens dosimeters were less often available, particularly in radiology (67% and 27%, respectively). Systematic or frequent dosimeter use was lower for extremity and eye lens monitoring than for whole-body monitoring. Median annual whole-body effective doses remained low in both radiology and cardiology (0.36 and 0.61 mSv/year, respectively), and no physician exceeded the 6 mSv/year threshold corresponding to category B workers. Extremity and eye lens exposures were substantially higher, particularly in vascular radiology and coronary/valvular cardiology. Four out of 244 physicians (1.6%) exceeded the annual eye lens dose limit of 20 mSv/year. Despite broad availability of eye protection equipment, non-use remained frequent among radiologists (35%). Radiation protection training remained heterogeneous across specialties and activities.</p><p><strong>Conclusion: </strong>Occupational radiation exposure remained globally low for whole-body exposure but remained substantial for extremities and especially the eye lens. Persistent shortcomings in dosimeter compliance and eye protection use emphasize the need to reinforce radiation protection practices in high-exposure interventional specialties.</p>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":11.1,"publicationDate":"2026-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148320004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combination of color-Doppler ultrasound and MRI to improve lacrimal gland lesion characterization: A machine learning approach.","authors":"Axelle Riehm, Lucile Senicourt, Emma O'Shaughnessy, Marie Callet, Loïc Duron, Augustin Lecler","doi":"10.1016/j.diii.2026.06.001","DOIUrl":"https://doi.org/10.1016/j.diii.2026.06.001","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to develop a machine learning-based algorithm based on a combination of magnetic resonance imaging (MRI) and color-Doppler ultrasound (CDUS) to characterize lacrimal gland lesions.</p><p><strong>Materials and methods: </strong>All patients with a lacrimal gland lesion who underwent MRI examination and CDUS between 2014 and 2025 were retrospectively included. Thirty-four imaging features were systematically assessed. A machine learning algorithm was trained with repeated nested cross-validation (RNCV) using random forest classifiers. Shapley additive explanations values were used to assess feature contributions. Simplified models using top 5 and top 10 best features were also developed. Diagnostic performance of the models was assessed using area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (PR AUC), balanced accuracy, precision, sensitivity, specificity, Brier score, Matthew's correlation coefficient and F1-score.</p><p><strong>Results: </strong>One hundred patients (mean age, 49.6 years ± 17.8 [standard deviation] years) with 130 lesions (101 non-epithelial (NEL) and 29 epithelial (EL); 45 malignant) were included. The random forest binary machine learning model yielded 75.9% sensitivity (95% confidence interval [CI]: 39-100), 86.0% specificity (95% CI: 62.4-100), and an AUC of 0.883 (95% CI: 0.692-1.0) for differentiating between malignant and benign lesions and 73.2% sensitivity (95% CI: 33.5-100), 92.9% specificity (95% CI: 69.9-100), and an AUC of 0.93 (95% CI: 0.683-1) for differentiating between EL and NEL. In multiclass analysis (benign NEL, benign EL, malignant NEL and malignant EL), the random forest yielded a macro-averaged AUC of 0.857 (95% CI: 0.722-0.972) for the all-features model. A 5-top features signature comprising apparent diffusion coefficient and resistance index values, echogenicity, age and lesion type (infiltrative vs. well-delineated mass), yielded an AUC of 0.785 (95% CI: 0.641-0.941) to distinguish between the four classes.</p><p><strong>Conclusion: </strong>A combination of MRI and CDUS features demonstrated high diagnostic performance for characterizing lacrimal gland lesions. A simplified 5-feature signature showed similar diagnostic performance compared to the all-features model and warrants prospective multicenter validation for clinical application.</p>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":11.1,"publicationDate":"2026-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148284639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"There is no bone damage on MRI examination after joint embolization with an ethiodized oil-based emulsion.","authors":"Fouad Georges Akkari, Tom Boeken, Nicolas Stacoffe, Marc Sapoval","doi":"10.1016/j.diii.2026.06.002","DOIUrl":"https://doi.org/10.1016/j.diii.2026.06.002","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":11.1,"publicationDate":"2026-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148266699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}