Bastien Le Guellec, Cyril Bruge, Najib Chalhoub, Victor Chaton, Edouard De Sousa, Yann Gaillandre, Riyad Hanafi, Matthieu Masy, Quentin Vannod-Michel, Aghiles Hamroun, Grégory Kuchcinski
{"title":"Comparison between multimodal foundation models and radiologists for the diagnosis of challenging neuroradiology cases with text and images.","authors":"Bastien Le Guellec, Cyril Bruge, Najib Chalhoub, Victor Chaton, Edouard De Sousa, Yann Gaillandre, Riyad Hanafi, Matthieu Masy, Quentin Vannod-Michel, Aghiles Hamroun, Grégory Kuchcinski","doi":"10.1016/j.diii.2025.04.006","DOIUrl":"https://doi.org/10.1016/j.diii.2025.04.006","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to compare the ability of two multimodal models (GPT-4o and Gemini 1.5 Pro) with that of radiologists to generate differential diagnoses from textual context alone, key images alone, or a combination of both using complex neuroradiology cases.</p><p><strong>Materials and methods: </strong>This retrospective study included neuroradiology cases from the \"Diagnosis Please\" series published in the Radiology journal between January 2008 and September 2024. The two multimodal models were asked to provide three differential diagnoses from textual context alone, key images alone, or the complete case. Six board-certified neuroradiologists solved the cases in the same setting, randomly assigned to two groups: context alone first and images alone first. Three radiologists solved the cases without, and then with the assistance of Gemini 1.5 Pro. An independent radiologist evaluated the quality of the image descriptions provided by GPT-4o and Gemini for each case. Differences in correct answers between multimodal models and radiologists were analyzed using McNemar test.</p><p><strong>Results: </strong>GPT-4o and Gemini 1.5 Pro outperformed radiologists using clinical context alone (mean accuracy, 34.0 % [18/53] and 44.7 % [23.7/53] vs. 16.4 % [8.7/53]; both P < 0.01). Radiologists outperformed GPT-4o and Gemini 1.5 Pro using images alone (mean accuracy, 42.0 % [22.3/53] vs. 3.8 % [2/53], and 7.5 % [4/53]; both P < 0.01) and the complete cases (48.0 % [25.6/53] vs. 34.0 % [18/53], and 38.7 % [20.3/53]; both P < 0.001). While radiologists improved their accuracy when combining multimodal information (from 42.1 % [22.3/53] for images alone to 50.3 % [26.7/53] for complete cases; P < 0.01), GPT-4o and Gemini 1.5 Pro did not benefit from the multimodal context (from 34.0 % [18/53] for text alone to 35.2 % [18.7/53] for complete cases for GPT-4o; P = 0.48, and from 44.7 % [23.7/53] to 42.8 % [22.7/53] for Gemini 1.5 Pro; P = 0.54). Radiologists benefited significantly from the suggestion of Gemini 1.5 Pro, increasing their accuracy from 47.2 % [25/53] to 56.0 % [27/53] (P < 0.01). Both GPT-4o and Gemini 1.5 Pro correctly identified the imaging modality in 53/53 (100 %) and 51/53 (96.2 %) cases, respectively, but frequently failed to identify key imaging findings (43/53 cases [81.1 %] with incorrect identification of key imaging findings for GPT-4o and 50/53 [94.3 %] for Gemini 1.5).</p><p><strong>Conclusion: </strong>Radiologists show a specific ability to benefit from the integration of textual and visual information, whereas multimodal models mostly rely on the clinical context to suggest diagnoses.</p>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":4.9,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144057816","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}
Gael Dournes, Hugues Bégueret, Xavier Demant, Jean Delmas, Michael Fayon, Nathalie Aladjidi
{"title":"CT features of genetic mutation-related pulmonary alveolar proteinosis (CCR2 and GATA2 deficiency.","authors":"Gael Dournes, Hugues Bégueret, Xavier Demant, Jean Delmas, Michael Fayon, Nathalie Aladjidi","doi":"10.1016/j.diii.2025.04.007","DOIUrl":"https://doi.org/10.1016/j.diii.2025.04.007","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":" ","pages":""},"PeriodicalIF":4.9,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144032856","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}
Pedro Augusto Gondim Teixeira , Hippolyte Kessler , Lieve Morbée , Nicolas Douis , Fatma Boubaker , Romain Gillet , Alain Blum
{"title":"Mineralized tissue visualization with MRI: Practical insights and recommendations for optimized clinical applications","authors":"Pedro Augusto Gondim Teixeira , Hippolyte Kessler , Lieve Morbée , Nicolas Douis , Fatma Boubaker , Romain Gillet , Alain Blum","doi":"10.1016/j.diii.2024.11.001","DOIUrl":"10.1016/j.diii.2024.11.001","url":null,"abstract":"<div><div>Magnetic resonance imaging (MRI) techniques that enhance the visualization of mineralized tissues (hereafter referred to as MT-MRI) are increasingly being incorporated into clinical practice, particularly in musculoskeletal imaging. These techniques aim to mimic the contrast provided by computed tomography (CT), while taking advantage of MRI's superior soft tissue contrast and lack of ionizing radiation. However, the variety of MT-MRI techniques, including three-dimensional gradient-echo, ultra-short and zero-echo time, susceptibility-weighted imaging, and artificial intelligence-generated synthetic CT, each offer different technical characteristics, advantages, and limitations. Understanding these differences is critical to optimizing clinical application. This review provides a comprehensive overview of the most commonly used MT-MRI techniques, categorizing them based on their technical principles and clinical utility. The advantages and disadvantages of each approach, including their performance in bone morphology assessment, fracture detection, arthropathy-related findings, and soft tissue calcification evaluation are discussed. Additionally, technical limitations and artifacts that may affect image quality and diagnostic accuracy, such as susceptibility effects, signal-to-noise ratio issues, and motion artifacts are addressed. Despite promising developments, MT-MRI remains inferior to conventional CT for evaluating subtle bone abnormalities and soft tissue calcification due to spatial resolution limitations. However, advances in deep learning and hardware innovations, such as artificial intelligence-generated synthetic CT and ultrahigh-field MRI, may bridge this gap in the future.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 5","pages":"Pages 147-156"},"PeriodicalIF":4.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142819726","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":"Cinematic rendering of transcatheter aortic valve replacement-associated infective endocarditis","authors":"Taha M. Ahmed, Elliot K. Fishman","doi":"10.1016/j.diii.2025.03.005","DOIUrl":"10.1016/j.diii.2025.03.005","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 5","pages":"Pages 196-197"},"PeriodicalIF":4.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765472","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}
Clément Marcelin , Amandine Crombé , Eva Jambon , Grégoire Robert , Franck Bladou , Pierre Bour , Thibaut Faller , Valéry Ozenne , Nicolas Grenier , Bruno Quesson
{"title":"Real-time multislice MR-thermometry of the prostate: Assessment of feasibility, accuracy and sources of biases in patients","authors":"Clément Marcelin , Amandine Crombé , Eva Jambon , Grégoire Robert , Franck Bladou , Pierre Bour , Thibaut Faller , Valéry Ozenne , Nicolas Grenier , Bruno Quesson","doi":"10.1016/j.diii.2024.11.006","DOIUrl":"10.1016/j.diii.2024.11.006","url":null,"abstract":"<div><h3>Purpose</h3><div>The primary purpose of this study was to evaluate the accuracy of an MR-thermometry sequence for monitoring prostate temperature. The secondary purposes were to analyze clinical and technical factors that may affect accuracy and testing the method in a realistic setting, with MR-guided Laser ablation on an <em>ex vivo</em> muscle sample.</div></div><div><h3>Materials and methods</h3><div>An <em>ex vivo</em> muscle sample was subjected to Laser ablation while using a two-dimensional multislice segmented echo planar imaging sequence for MR thermometry. The MR thermometry measurements were compared with invasive sensor temperature readings to assess accuracy. Subsequently, 56 men with a median age of 70 years (age range: 53–84 years) who underwent prostate MRI examinations at 1.5- (<em>n</em> = 27) or 3 T (<em>n</em> = 24) were prospectively included. For each patient, the proportion of 'noisy voxels' (i.e., those with a temporal standard deviation of temperature [SD(T)] > 2 °C) in the prostate was calculated. The impact of clinical and technical factors on the proportion of noisy voxels was also examined.</div></div><div><h3>Results</h3><div>MR-thermometry showed excellent correlation with invasive sensors during MR-guided Laser ablation on the <em>ex vivo</em> muscle sample. The median proportion of noisy voxels per patient in the entire cohort was 1 % (Q1, 0.2; Q3, 4.9; range: 0–90.4). No significant differences in median proportion of noisy voxels were observed between examinations performed at 1.5 T and those at 3 T (<em>P</em> = 0.89 before and after adjustment). No clinical or technical factors significantly influenced the proportion of noisy voxels.</div></div><div><h3>Conclusion</h3><div>Two-dimensional real time multislice MR-thermometry is feasible and accurate for monitoring prostate temperature in patients.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 5","pages":"Pages 183-191"},"PeriodicalIF":4.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873071","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":"Improved myocardial scar visualization using free-breathing motion-corrected wideband black-blood late gadolinium enhancement imaging in patients with implantable cardiac devices","authors":"Pauline Gut , Hubert Cochet , Panagiotis Antiochos , Guido Caluori , Baptiste Durand , Marion Constantin , Konstantinos Vlachos , Kalvin Narceau , Ambra Masi , Jürg Schwitter , Frederic Sacher , Pierre Jaïs , Matthias Stuber , Aurélien Bustin","doi":"10.1016/j.diii.2024.12.001","DOIUrl":"10.1016/j.diii.2024.12.001","url":null,"abstract":"<div><h3>Purpose</h3><div>The purpose of this study was to introduce and evaluate a novel 2D wideband black-blood (BB) LGE sequence, incorporating wideband inversion recovery, wideband T2 preparation, and non-rigid motion correction (MOCO) reconstruction, to improve myocardial scar detection and address artifacts associated with implantable cardioverter defibrillators (ICDs).</div></div><div><h3>Materials and methods</h3><div>The wideband MOCO free-breathing BB-LGE sequence was tested on a sheep with ischemic scar and in 22 patients with cardiac disease, including 15 with cardiac implants, at 1.5T. Wideband MOCO free-breathing BB-LGE sequence was compared with conventional and wideband breath-held PSIR-LGE and conventional and wideband breath-held BB-LGE techniques. Image sharpness, entropy, and scar-to-blood, scar-to-myocardium, and blood-to-myocardium contrast were analyzed and reconstruction times were measured. Two expert readers assessed the image quality, ICD artifact severity, and the diagnostic confidence with scar extent. Finally, for the animal study, a histology of the heart was performed to confirm the presence and localization of scar tissue.</div></div><div><h3>Results</h3><div>In the animal, wideband MOCO free-breathing BB-LGE were reconstructed in 0.6 s and demonstrated a 200 % improvement in scar-to-blood contrast compared to wideband breath-held PSIR-LGE, with significant improvement in image sharpness and reduction in entropy. It also effectively minimized ICD artifacts and accurately detected scars. In patients, wideband MOCO free-breathing BB-LGE were reconstructed in 1.5 ± 0.4 (standard deviation) s per slice. Seventeen patients (17/22; 77%) with myocardial scars were confidently diagnosed with wideband MOCO free-breathing BB-LGE, compared to 11 (11/22; 50 %) with wideband breath-held PSIR-LGE (<em>P</em> < 0.01).</div></div><div><h3>Conclusion</h3><div>Free-breathing wideband T2-prepared black-blood LGE imaging, combined with motion-corrected reconstruction, offers a promising diagnostic approach for the evaluation of myocardial lesions in patients with ICDs.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 5","pages":"Pages 169-182"},"PeriodicalIF":4.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142819643","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":"Robotics and artificial intelligence in the real world of interventional radiology: Innovation or illusion?","authors":"Baptiste Bonnet , Lambros Tselikas","doi":"10.1016/j.diii.2025.01.006","DOIUrl":"10.1016/j.diii.2025.01.006","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 5","pages":"Pages 145-146"},"PeriodicalIF":4.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143123914","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":"Myocardial scar detection in patients with implantable cardiac device: Wideband free-breathing motion-corrected black-blood late gadolinium enhancement could be the answer","authors":"Farah Cadour , Benjamin Longère","doi":"10.1016/j.diii.2025.01.002","DOIUrl":"10.1016/j.diii.2025.01.002","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 5","pages":"Pages 143-144"},"PeriodicalIF":4.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143014593","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}
Francois H. Cornelis , Dimitrios K Filippiadis , Philipp Wiggermann , Stephen B. Solomon , David C. Madoff , Laurent Milot , Sylvain Bodard
{"title":"Evaluation of navigation and robotic systems for percutaneous image-guided interventions: A novel metric for advanced imaging and artificial intelligence integration","authors":"Francois H. Cornelis , Dimitrios K Filippiadis , Philipp Wiggermann , Stephen B. Solomon , David C. Madoff , Laurent Milot , Sylvain Bodard","doi":"10.1016/j.diii.2025.01.004","DOIUrl":"10.1016/j.diii.2025.01.004","url":null,"abstract":"<div><h3>Purpose</h3><div>Navigation and robotic systems aim to improve the accuracy and efficiency of percutaneous image-guided interventions, but the evaluation of their autonomy and integration of advanced imaging and artificial intelligence (AI) is lacking. The purpose of this study was to evaluate the level of automation and integration of advanced imaging and artificial intelligence in navigation and robotic systems for percutaneous image-guided interventions, using established and novel metrics to categorize and compare their capabilities.</div></div><div><h3>Materials and methods</h3><div>Following PRISMA guidelines, a systematic review was conducted to identify studies on clinically validated navigation and robotic systems published between 2000 and May 2024. The PubMed, Embase, Cochrane Library, and Web of Science databases were searched. Data on navigation devices were extracted and analyzed. The levels of autonomy in surgical robotics (LASR) classification system (from 1 to 5) was used to analyze automation. A novel taxonomy, the Levels of Integration of Advanced Imaging and AI (LIAI2) classification system, was created to categorize the integration of imaging technologies and AI (from 1 to 5). These two scores were combined into an aggregate score (from 1 to 10) to reflect the autonomy in percutaneous image-guided intervention.</div></div><div><h3>Results</h3><div>The review included 20 studies assessing two navigation systems and eight robotic devices. The median LASR score was 1 (Q1, Q3: 1, 1), the median LIAI2 score was 2 (Q1, Q3: 2, 3), and the median aggregate score was 3 (Q1, Q3: 3, 4). Only one robotic system (10 % of those reviewed) achieved the highest LASR qualification in the literature, a level 2/5. Four systems (40 %) shared the highest rating for LIAI2, which was a score of 3/5. Four systems (40 %) achieved the highest aggregate scores of 4/10.</div></div><div><h3>Conclusion</h3><div>None of the navigation and robotic systems achieved full autonomy for percutaneous image-guided intervention. The LASR and LIAI2 scales can guide innovation by identifying areas for further development and integration.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 5","pages":"Pages 157-168"},"PeriodicalIF":4.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143068969","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}