Diagnostic and Interventional Imaging最新文献

{"title":"Understanding the challenges to implementing AI solutions in radiology departments and how to overcome them: A comprehensive review endorsed by the French College of Radiologists (CERF) and the French Society of Radiology (SFR)","authors":"Amandine Crombé ,&nbsp;Camille Bourillon ,&nbsp;Stéphane Chaillou ,&nbsp;Clara Bechet ,&nbsp;Jules Dupont ,&nbsp;Alexandre Bône ,&nbsp;Fanny Louvet-de Verchère ,&nbsp;Alain Luciani ,&nbsp;Marie-France Bellin ,&nbsp;Christophe Aubé ,&nbsp;Nathalie Lassau","doi":"10.1016/j.diii.2025.12.002","DOIUrl":"10.1016/j.diii.2025.12.002","url":null,"abstract":"<div><div>Despite the exponential growth of artificial intelligence (AI) solutions designed to assist radiologists in clinical practice, their actual impact on radiology departments remains below initial expectations. Daily workflows have not been profoundly transformed. The actual clinical benefit of these tools is often limited to single, modality-specific \"narrow AI\" tasks, and their return on investment is unclear. The purpose of this article was to analyze: (<em>i</em>), the human and perceptual challenges that shape attitudes toward AI among radiologists, referring clinicians, and patients; (<em>ii</em>), the technical and clinical limitations of current AI models, including the mismatches between target tasks and real-world needs, and between published versus real-life performances; (<em>iii</em>), the lack of objective return on investment quantification and the paucity of medicoeconomic studies in a context of constrained hospital budgets; (<em>iv</em>), the limitations of the current \"assistive models\" of human-AI interaction in radiology; (<em>v</em>), the technical and organizational difficulties that information and technology departments face in integrating, maintaining, and securing a growing number of AI applications across specialties within complex hospital information systems; (<em>vi</em>), the ethical and patient safety concerns related to bias, transparency, data protection, and regulatory compliance with respect to data protection officers and the European General Data Protection Regulation; and (<em>vii</em>), the underexplored environmental and energy implications of large-scale AI deployment. Finally, potential solutions relating to AI governance, national data infrastructures, user education, and the design of randomized clinical trials and cost-effectiveness studies, are discussed to promote the responsible, evidence-based integration of AI into radiology practice.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 4","pages":"Pages 133-142"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145821631","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":"Deep learning-based image reconstruction significantly improves image quality of MRI examinations of the orbit at 3 Tesla","authors":"Aurore Sajust de Bergues de Escalup ,&nbsp;Augustin Lecler ,&nbsp;Émilie Poirion ,&nbsp;Caroline Papeix ,&nbsp;Romain Deschamps ,&nbsp;Dan Milea ,&nbsp;Julien Savatovsky ,&nbsp;Loïc Duron ,&nbsp;Emma O’Shaughnessy","doi":"10.1016/j.diii.2025.11.003","DOIUrl":"10.1016/j.diii.2025.11.003","url":null,"abstract":"<div><h3>Purpose</h3><div>The purpose of this study was to assess the benefit of a deep learning-based image reconstruction (DLBIR) for improving image quality in orbital magnetic resonance imaging (MRI) at 3 Tesla (T).</div></div><div><h3>Materials and methods</h3><div>Seventy-one patients (48 women and 23 men) with a mean age of 52 ± 19.5 (standard deviation [SD]) years (age range: 7–90 years) who underwent MRI examination of the orbit at 3 T between January and June of 2024, were included in the study. Coronal T2-weighted MR images obtained in 70 patients and post-contrast fat-saturated (FS) coronal T1-weighted MR images obtained in 25 patients, were reconstructed with and without DLBIR, resulting in four imaging sets. Two radiologists independently and blindly measured the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the optic nerves on the four imaging sets. Image quality and orbital abnormalities were assessed using a standardized 5-point Likert scale. Comparisons between MR images obtained with and without DLBIR were performed using Wilcoxon test for ordinal and quantitative variables and McNemar test for paired binary data.</div></div><div><h3>Results</h3><div>SNR and CNR of coronal T2-weighted MR images were significantly greater using DLBIR (26.67 ± 9.03 [SD], and 14.87 ± 10.31 [SD], respectively) than without DLBIR (18.91 ± 7.28 [SD], and 9.78 ± 8.47 [SD], respectively) (<em>P</em> &lt; 0.001). There were no differences in SNR and CNR between post-contrast FS T1-weighted images obtained with DLBIR (85.56 ± 63.13 [SD], and 64 ± 41.38 [SD], respectively) and those obtained without DLBIR (91.36 ± 48.49 [SD], and 43.25 ± 20.4 [SD], respectively) (<em>P</em> = 0.35, and <em>P</em> = 0.14, respectively). Qualitatively, good-to-excellent image quality was obtained more frequently with DLBIR than without DLBIR for T2-weighted and post-contrast FS T1-weighted images with respect to optic nerve sharpness (67 % <em>vs</em>. 16 %, and 8 % <em>vs</em>. 0 %, respectively), brain sharpness (90 % <em>vs</em>. 6 %, and 68 % <em>vs</em>. 4 %, respectively), and overall image quality (73 % <em>vs</em>. 1 % and 36 % <em>vs</em>. 0 %, respectively) (all <em>P</em> ≤ 0.001). No significant differences in the detection rates of orbital abnormalities were found between MR images obtained with and without DLBIR, including optic nerve hyperintensity (34 % <em>vs</em>. 31 %, respectively; <em>P</em> = 0.16) and optic nerve atrophy (33 % for both) on T2-weighted images, and optic nerve enhancement on post-contrast FS T1-weighted images (16 % for both).</div></div><div><h3>Conclusion</h3><div>DLBIR significantly improves image quality of MRI examinations of the orbit at 3 T, without losing clinically relevant information.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 4","pages":"Pages 143-150"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145589687","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":"From promise to practice: Implementing artificial intelligence in radiology","authors":"Kate Hanneman ,&nbsp;Michael N. Patlas","doi":"10.1016/j.diii.2026.01.010","DOIUrl":"10.1016/j.diii.2026.01.010","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 4","pages":"Pages 127-128"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146127072","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":"Automatic vessel tracking with MRI-cone-beam CT image fusion for venous embolization in pelvic congestion syndrome","authors":"Eva Fourage-Jambon ,&nbsp;Thomas Linet ,&nbsp;Rim Maaloum ,&nbsp;Yann Le Bras ,&nbsp;Nicolas Pangon ,&nbsp;Clément Marcelin ,&nbsp;Joffrey Perrin ,&nbsp;Rachel Testard ,&nbsp;Julien Loric ,&nbsp;Hugo Leclercq ,&nbsp;Mickael Peigne","doi":"10.1016/j.diii.2025.12.001","DOIUrl":"10.1016/j.diii.2025.12.001","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 4","pages":"Pages 158-160"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145806076","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":"Cone-beam CT-guided osteosynthesis of traumatic pelvic fractures: An analysis of 67 patients","authors":"Hugo Perez ,&nbsp;Bastien Chalamet ,&nbsp;Sylvain Grange ,&nbsp;Anthony Viste ,&nbsp;Joris Lavigne ,&nbsp;Jean-Baptiste Pialat ,&nbsp;Nicolas Stacoffe","doi":"10.1016/j.diii.2025.11.008","DOIUrl":"10.1016/j.diii.2025.11.008","url":null,"abstract":"<div><h3>Purpose</h3><div>The purpose of this study was to assess the technical success, intervention duration, radiation exposure, and safety of cone-beam computed tomography (CBCT)-guided percutaneous screw fixation in treating traumatic pelvic ring and acetabular fractures.</div></div><div><h3>Materials and methods</h3><div>All consecutive patients with unstable pelvic ring (Tile B/C) or acetabular fractures treated by CBCT-guided percutaneous osteosynthesis between March 2023 and September 2025 were included. All interventions were performed using CBCT navigation with bull's eye guidance. Outcomes were technical success (<em>i.e.</em>, fully intraosseous screw trajectory without cortical breach), intervention duration, dose-area product (DAP), and perioperative complications, and their associations or correlations with fracture classification, screw count, and body mass index .</div></div><div><h3>Results</h3><div>Sixty-seven patients underwent CBCT-guided fixation. There were 45 men and 22 women, with a mean age of 50.8 ± 18.5 (standard deviation) years (range: 17–91 years) and a median body mass index of 24.8 kg/m² (Q1, 22.3; Q3, 27.2; range: 16.7–42.2 kg/m²). Overall, 102 out of 103 screws (99.0 %) followed the planned intraosseous trajectory. No intraoperative complications were observed. One patient (1/67; 1.5 %) developed immediate postoperative nervous pain requiring screw adjustment with rapid pain relief. Median intervention duration was 43 min (first quartile [Q1], 30; third quartile [Q3], 54.5; range, 19–107 min) with a moderate correlation with the number of screws (ρ = 0.496). Median DAP was 81.6 Gy·cm² (Q1, 59.1; Q3, 101.5; range, 11.8–226.5 Gy·cm²) with a weak correlation with body mass index (ρ = 0.311).</div></div><div><h3>Conclusion</h3><div>CBCT-guided percutaneous pelvic fixation is safe and effective in the management of traumatic pelvic fractures and may represent a minimally invasive alternative to open surgery or conventional fluoroscopy for patients with this condition.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 4","pages":"Pages 151-157"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145641274","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":"Deep learning-based image reconstruction best contributes to image quality enhancement under close expert supervision","authors":"Lotfi Hacein-Bey","doi":"10.1016/j.diii.2025.12.006","DOIUrl":"10.1016/j.diii.2025.12.006","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 4","pages":"Pages 131-132"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145901469","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":"Stress myocardial perfusion imaging with photon-counting CT: Initial validation against reference modalities","authors":"Benjamin Longère ,&nbsp;Hippolyte Caseneuve ,&nbsp;Christos V Gkizas ,&nbsp;Aimée Rodriguez Musso ,&nbsp;Mariia Tregubova ,&nbsp;Cédric Croisille ,&nbsp;Mehdi Haidar ,&nbsp;François Pontana","doi":"10.1016/j.diii.2025.10.005","DOIUrl":"10.1016/j.diii.2025.10.005","url":null,"abstract":"<div><h3>Purpose</h3><div>The purpose of this study was to evaluate the feasibility and diagnostic performance of stress myocardial perfusion imaging (MPI) using a first-generation dual-source photon-counting CT (PCCT) scanner by comparison with reference standards.</div></div><div><h3>Materials and methods</h3><div>Consecutive patients referred for coronary CT angiography (CCTA) with concomitant stress MPI using PCCT scanner and at least one functional reference test within one month were included. Static PCCT-MPI with regadenoson (Rapiscan, GE Healthcare) was acquired 12 s after the intravenous administration of 40 mL of iodinated contrast material and paired with myocardial delayed enhancement imaging. Reference tests for ischemia included stress cardiac magnetic resonance imaging, stress echocardiography, single-photon emission computed tomography, or invasive coronary angiography. Diagnostic performance was evaluated using sensitivity, specificity, accuracy, areas under receiver operating characteristic curve analysis (AUC) as well as Youden index-derived thresholds.</div></div><div><h3>Results</h3><div>Forty-one patients were included. There were 28 men and 13 women with a median age of 62 years (Q1, 57; Q3, 70; range: 18–85 years). Of these, 35 patients (85 %) had obstructive coronary artery disease (CAD) on CCTA. PCCT-MPI identified myocardial hypoperfusion in 18 patients (44 %) with a median dose-length product of 97 mGy.cm (Q1, 76.8; Q3, 155.8). Visual assessment yielded 100 % sensitivity (95 % confidence interval [CI]: 81–100 %) and 96 % specificity (95 % CI: 78–100 %), with an AUC of 0.98 (95 % CI: 0.93–1.00) for the diagnosis of ischemic and infarcted myocardium. An optimal defect-to-remote iodine ratio cutoff of 0.79 showed 98 % accuracy (95 % CI: 87–100 %) and an AUC of 0.99 (95 % CI: 0.98–1.00 %). Integration of PCCT-MPI with CCTA could have obviated additional functional testing or invasive angiography in up to 50 % of patients with obstructive CAD.</div></div><div><h3>Conclusion</h3><div>Stress static PCCT-MPI is feasible and demonstrates excellent diagnostic accuracy for detecting myocardial ischemia. Defect-to-remote iodine ratio from spectral imaging further enhances performance, establishing PCCT as a comprehensive imaging modality that unifies anatomic and functional coronary assessment at a reasonable radiation dose, within a single examination.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 3","pages":"Pages 103-113"},"PeriodicalIF":8.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145423227","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":"Photon-counting CT myocardial perfusion imaging: A future candidate in the guidelines for functional assessment of coronary artery disease","authors":"Farah Cadour ,&nbsp;Jean-Nicolas Dacher","doi":"10.1016/j.diii.2025.11.002","DOIUrl":"10.1016/j.diii.2025.11.002","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 3","pages":"Pages 85-86"},"PeriodicalIF":8.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145534624","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":"Dual-energy CT for peritoneal metastases: When the right question meets the right technology","authors":"Paul Calame ,&nbsp;Christine Hoeffel ,&nbsp;Stéphanie Nougaret","doi":"10.1016/j.diii.2025.11.006","DOIUrl":"10.1016/j.diii.2025.11.006","url":null,"abstract":"","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 3","pages":"Pages 87-88"},"PeriodicalIF":8.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145606770","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":"Multiparametric assessment of tumor pathological regression grade of peritoneal metastases from non-mucinous colorectal cancer during neoadjuvant chemotherapy using dual-energy CT","authors":"Rémi Grange ,&nbsp;Nazim Benzerdjeb ,&nbsp;Salim Si-Mohamed ,&nbsp;Marie Gavrel ,&nbsp;Alexandre Galan ,&nbsp;Laurent Villeneuve ,&nbsp;Olivier Glehen ,&nbsp;Vahan Kepenekian ,&nbsp;Pascal Rousset","doi":"10.1016/j.diii.2025.10.007","DOIUrl":"10.1016/j.diii.2025.10.007","url":null,"abstract":"<div><h3>Purpose</h3><div>The purpose of this prospective study was to evaluate the diagnostic performance of dual-energy computed tomography (DECT) using a dual-layer detector scanner in assessing the pathological response of peritoneal metastases (PMs) from non-mucinous colorectal cancer to neoadjuvant chemotherapy (NAC).</div></div><div><h3>Materials and methods</h3><div>Consecutive patients with PMs from non-mucinous colorectal cancer who underwent preoperative DECT using a dual-layer detector scanner before cytoreductive surgery were prospectively included. Virtual monoenergetic images at 40 keV (VMI_40kev), VMIs at 100 keV (VMI_100kev), VMI slope (VMI_slope), iodine concentration (IC), normalized iodine concentration with aorta (nIC_aorta) and liver (nIC_liver), effective Z atomic number (Z_eff), and extracellular volume fraction (ECV<em>f</em>) were evaluated on PMs by two radiologists. Pathological response of PM was classified using the peritoneal regression grading score (PRGS), and classified as either good (complete response or major histological regression - PRGS <strong>½</strong>) or poor (minor or no histological response - PRGS ¾) responses. DECT variables of PMs with good responses were compared to those of PMs with poor responses using independent-sample <em>t</em>-tests. Receiver operating characteristic curves were built to estimate the capabilities of the different DECT variables in differentiating between PMs with good responses (PRGS <strong>½</strong>) and those with poor responses (PRGS ¾). Intra-class correlation coefficients analyses were performed to estimate interobserver variability in DECT variable measurements.</div></div><div><h3>Results</h3><div>Forty-four patients (22 men median age, 62 years; age range: 35–78 years) with 77 PM were included from September 1st 2023 to July 1st 2025. Thirty-nine out of 77 PMs (51 %) exhibited good response (PRGS <strong>½</strong>) and 38 PMs (49 %) exhibited poor response (PRGS ¾). VMI_40kev, VMI_slope, IC, nIC_aorta, nIC_liver, ECV<em>f</em> were significantly greater in PRGS ¾ PMs by comparison with PRGS <strong>½</strong> (<em>P</em> &lt; 0.05). The best AUC values to distinguish between good and poor pathological response of PMs were obtained with nIC_aorta (AUC, 0.74: 95 % confidence interval [CI]: 0.63–0.85) and ECV<em>f</em> (AUC, 0.74; 95 % CI: 0.63–0.84). ICC was &gt; 0.8 for most DECT variables.</div></div><div><h3>Conclusion</h3><div>DECT using a dual-layer detector scanner provides promising biomarkers for predicting pathological response in non-mucinous PM after chemotherapy.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"107 3","pages":"Pages 114-123"},"PeriodicalIF":8.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145423270","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}