Pub Date : 2026-01-23DOI: 10.1016/j.ejrad.2026.112692
Margaux Roques , Kevin Pimentel , Aurore Siegfried-Vergnon , Elizabeth Moyal , Caroline Zerbib , Amaury de Barros , Magali Raveneau , Delphine Dghayem , Fabrice Bonneville
Objective
IDH-wildtype diffuse gliomas with molecular features of glioblastoma (mGBM) were integrated into the GBM category in the 2021 WHO classification, yet their MRI characteristics remain poorly described. This study aimed to detail morphological and advanced MRI features of mGBM to improve diagnostic accuracy and management.
Methods
MRI scans (1.5 T or 3 T) of 72 patients with histomolecularly confirmed mGBM were retrospectively reviewed. Two neuroradiologists analyzed morphological features (necrosis, contrast enhancement, FLAIR pattern, multilobar involvement) and advanced imaging findings (diffusion, perfusion).
Results
Mean patient age was 63 years. mGBMs showed a broad spectrum of MRI appearances, from grade 2-like (39%) to grade 4-like (26%). Infiltrative FLAIR hyperintensity was nearly constant, frequently with multilobar involvement (65%). Contrast enhancement was absent in 39% or faint/limited when present, often mimicking lower-grade gliomas. Gyriform cortical infiltration sparing white matter was seen in 15% of cases, less than previously reported. Advanced imaging showed diffusion restriction in 64% and elevated rCBV (>1.75) in 88% of cases with perfusion data, leading to reclassification of 22% of morphologically grade 2-like lesions as grade 3-like.
Conclusion
mGBMs often mimic low-grade gliomas, exposing patients to underdiagnosis and treatment delays. However, infiltrative FLAIR abnormalities, multilobar involvement, diffusion restriction, or increased perfusion should raise suspicion, particularly in older patients. This cohort describing both morphological and advanced MRI features of mGBM provides practical imaging criteria to enhance early recognition in routine practice.
{"title":"MRI features of molecular glioblastoma: morphological and advanced imaging insights","authors":"Margaux Roques , Kevin Pimentel , Aurore Siegfried-Vergnon , Elizabeth Moyal , Caroline Zerbib , Amaury de Barros , Magali Raveneau , Delphine Dghayem , Fabrice Bonneville","doi":"10.1016/j.ejrad.2026.112692","DOIUrl":"10.1016/j.ejrad.2026.112692","url":null,"abstract":"<div><h3>Objective</h3><div>IDH-wildtype diffuse gliomas with molecular features of glioblastoma (mGBM) were integrated into the GBM category in the 2021 WHO classification, yet their MRI characteristics remain poorly described. This study aimed to detail morphological and advanced MRI features of mGBM to improve diagnostic accuracy and management.</div></div><div><h3>Methods</h3><div>MRI scans (1.5 T or 3 T) of 72 patients with histomolecularly confirmed mGBM were retrospectively reviewed. Two neuroradiologists analyzed morphological features (necrosis, contrast enhancement, FLAIR pattern, multilobar involvement) and advanced imaging findings (diffusion, perfusion).</div></div><div><h3>Results</h3><div>Mean patient age was 63 years. mGBMs showed a broad spectrum of MRI appearances, from grade 2-like (39%) to grade 4-like (26%). Infiltrative FLAIR hyperintensity was nearly constant, frequently with multilobar involvement (65%). Contrast enhancement was absent in 39% or faint/limited when present, often mimicking lower-grade gliomas. Gyriform cortical infiltration sparing white matter was seen in 15% of cases, less than previously reported. Advanced imaging showed diffusion restriction in 64% and elevated rCBV (>1.75) in 88% of cases with perfusion data, leading to reclassification of 22% of morphologically grade 2-like lesions as grade 3-like.</div></div><div><h3>Conclusion</h3><div>mGBMs often mimic low-grade gliomas, exposing patients to underdiagnosis and treatment delays. However, infiltrative FLAIR abnormalities, multilobar involvement, diffusion restriction, or increased perfusion should raise suspicion, particularly in older patients. This cohort describing both morphological and advanced MRI features of mGBM provides practical imaging criteria to enhance early recognition in routine practice.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112692"},"PeriodicalIF":3.3,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-22DOI: 10.1016/j.ejrad.2026.112696
Yujie Chen , Yan Sun , Yu Song , Yi Liao , Xuesheng Li , Xijian Chen , Gang Ning
Background
Three-dimensional ultrashort echo time (3D-UTE) MRI enables proton-density assessment of lung parenchyma without radiation. We aimed to evaluate the feasibility of 3D-UTE for quantifying lung density of preterm infants and characterize gestational-age (GA)-dependent developmental patterns.
Methods
101 infants (1 day-24 months) were enrolled as extremely-to-very preterm (EVP, <32 weeks, n = 33), moderate-to-late preterm (MLP, 32–<37 weeks, n = 34), and full-term (FT, 37–42 weeks, n = 34). Lung protocol including 3D-UTE, 3D-GRE (gradient-echo) and T2-FSE (fast spin-echo) sequences were used. Image quality was assessed qualitatively and quantitatively. Lung density was quantified using UTE-derived lung-to-muscle ratios (LMRs), and group differences and age-related patterns were evaluated.
Results
UTE-MRI provided superior visualization of lung structure with significantly higher signal-to-noise and contrast-to-noise ratios. Lung-to-muscle ratios demonstrated a consistent anterior–posterior gradient (R2 = 0.582, p < 0.001) and decreased with lower gestational age (LMR-total: FT 50.8 ± 9.7; MLP 48.7 ± 7.6; EVP 45.1 ± 7.6), with EVP significantly lower than FT (p < 0.05). Within the first year of life, age-related analyses revealed distinct developmental patterns across gestational age groups.
Conclusions
UTE-MRI enables radiation-free quantification of lung density. UTE-MRI-derived lung-to-muscle ratios provide a radiation-free biomarker of preterm lung structural deficits and support risk-adapted follow-up.
{"title":"Quantitative assessment of lung density and developmental patterns in preterm infants using three-dimensional ultrashort echo time MRI (UTE-MRI)","authors":"Yujie Chen , Yan Sun , Yu Song , Yi Liao , Xuesheng Li , Xijian Chen , Gang Ning","doi":"10.1016/j.ejrad.2026.112696","DOIUrl":"10.1016/j.ejrad.2026.112696","url":null,"abstract":"<div><h3>Background</h3><div>Three-dimensional ultrashort echo time (3D-UTE) MRI enables proton-density assessment of lung parenchyma without radiation. We aimed to evaluate the feasibility of 3D-UTE for quantifying lung density of preterm infants and characterize gestational-age (GA)-dependent developmental patterns.</div></div><div><h3>Methods</h3><div>101 infants (1 day-24 months) were enrolled as extremely-to-very preterm (EVP, <32 weeks, n = 33), moderate-to-late preterm (MLP, 32–<37 weeks, n = 34), and full-term (FT, 37–42 weeks, n = 34). Lung protocol including 3D-UTE, 3D-GRE (gradient-echo) and T2-FSE (fast spin-echo) sequences were used. Image quality was assessed qualitatively and quantitatively. Lung density was quantified using UTE-derived lung-to-muscle ratios (LMRs), and group differences and age-related patterns were evaluated.</div></div><div><h3>Results</h3><div>UTE-MRI provided superior visualization of lung structure with significantly higher signal-to-noise and contrast-to-noise ratios. Lung-to-muscle ratios demonstrated a consistent anterior–posterior gradient (R<sup>2</sup> = 0.582, <em>p</em> < 0.001) and decreased with lower gestational age (LMR-total: FT 50.8 ± 9.7; MLP 48.7 ± 7.6; EVP 45.1 ± 7.6), with EVP significantly lower than FT (<em>p</em> < 0.05). Within the first year of life, age-related analyses revealed distinct developmental patterns across gestational age groups.</div></div><div><h3>Conclusions</h3><div>UTE-MRI enables radiation-free quantification of lung density. UTE-MRI-derived lung-to-muscle ratios provide a radiation-free biomarker of preterm lung structural deficits and support risk-adapted follow-up.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112696"},"PeriodicalIF":3.3,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146060911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-22DOI: 10.1016/j.ejrad.2026.112693
Max Masthoff , Emily Hoffmann , Markus Kimmann , Jörn Arne Meier , Philipp Schindler , Gesa Pöhler , Jonel Trebicka , Michael Praktiknjo , Michael Köhler
Objective
To evaluate the technical feasibility, efficacy, and safety of endovascular rotational thrombectomy (ERT) for treating portomesenteric thrombosis (PMVT) and Transjugular Intrahepatic Portosystemic Shunt thrombosis (TIPS-T) in a real-world clinical setting.
Materials and Methods
In this retrospective single-center study, 23 consecutive patients (n; 16 women; median age 60 years, range 27–80) underwent ERT for PMVT and/or TIPS-T between May 2024 and December 2025. Procedural data, technical outcomes, complications, and follow-up were analyzed.
Results
A total of 26 procedures (N) were performed. ERT was performed as first-line (N = 18, 69.2%) or second-line (N = 8, 30.8%) endovascular approach. Adjunctive thrombectomy techniques were required in 55.6% of procedures. Here, complete recanalization was achieved in 55.6%, partial in 44.4%, yielding a 100% technical success rate. The portosystemic pressure gradient significantly decreased post-procedure (median 17.0 mmHg (IQR 15.0–25.0) to median 7.0 mmHg (IQR 6.0–10.0), p < 0.0001). No device-related adverse events occurred. One hemolysis event (N = 1/26, 6.25%) was likely related to adjunctive hydrodynamic thrombectomy. The 30-day mortality rate was 0.0% (n = 0); overall all-cause mortality during follow-up (median: 137 days; IQR: 83.5–270 days) was 21.7% (n = 5), mainly in patients with Yerdel class 4 thrombosis or advanced liver cirrhosis.
Conclusion
Endovascular rotational thrombectomy demonstrated high technical performance and a favorable safety profile for PMVT and TIPS-T. Effective both as a primary and rescue tool, it may represent a valuable addition to the existing mechanical and pharmacomechanical strategies.
{"title":"Rotational thrombectomy for endovascular treatment of portomesenteric vein and TIPS thrombosis: Initial single-center experience","authors":"Max Masthoff , Emily Hoffmann , Markus Kimmann , Jörn Arne Meier , Philipp Schindler , Gesa Pöhler , Jonel Trebicka , Michael Praktiknjo , Michael Köhler","doi":"10.1016/j.ejrad.2026.112693","DOIUrl":"10.1016/j.ejrad.2026.112693","url":null,"abstract":"<div><h3>Objective</h3><div>To evaluate the technical feasibility, efficacy, and safety of endovascular rotational thrombectomy (ERT) for treating portomesenteric thrombosis (PMVT) and Transjugular Intrahepatic Portosystemic Shunt thrombosis (TIPS-T) in a real-world clinical setting.</div></div><div><h3>Materials and Methods</h3><div>In this retrospective single-center study, 23 consecutive patients (n; 16 women; median age 60 years, range 27–80) underwent ERT for PMVT and/or TIPS-T between May 2024 and December 2025. Procedural data, technical outcomes, complications, and follow-up were analyzed.</div></div><div><h3>Results</h3><div>A total of 26 procedures (N) were performed. ERT was performed as first-line (N = 18, 69.2%) or second-line (N = 8, 30.8%) endovascular approach. Adjunctive thrombectomy techniques were required in 55.6% of procedures. Here, complete recanalization was achieved in 55.6%, partial in 44.4%, yielding a 100% technical success rate. The portosystemic pressure gradient significantly decreased post-procedure (median 17.0 mmHg (IQR 15.0–25.0) to median 7.0 mmHg (IQR 6.0–10.0), p < 0.0001). No device-related adverse events occurred. One hemolysis event (N = 1/26, 6.25%) was likely related to adjunctive hydrodynamic thrombectomy. The 30-day mortality rate was 0.0% (n = 0); overall all-cause mortality during follow-up (median: 137 days; IQR: 83.5–270 days) was 21.7% (n = 5), mainly in patients with Yerdel class 4 thrombosis or advanced liver cirrhosis.</div></div><div><h3>Conclusion</h3><div>Endovascular rotational thrombectomy demonstrated high technical performance and a favorable safety profile for PMVT and TIPS-T. Effective both as a primary and rescue tool, it may represent a valuable addition to the existing mechanical and pharmacomechanical strategies.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112693"},"PeriodicalIF":3.3,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-21DOI: 10.1016/j.ejrad.2026.112673
Guangwen Cheng , Xueqi Li , Jing Liang , Iwaki Akiyama , Xiaohui Qiao , Liyun Xue , Hong Ding
Background
Quantitative ultrasound techniques enable noninvasive assessment of hepatic steatosis, fibrosis, and inflammation in metabolic dysfunction-associated steatotic liver disease (MASLD). This study performed a head-to-head comparison of dual-elastography and 2D shear wave elastography (2D-SWE) for comprehensive histologic evaluation.
Methods
A total of 186 biopsy proven MASLD patients were enrolled. Dual-elastography provided attenuation imaging (ATI), fibrosis (F-index), and inflammatory activity (A-index), while 2D-SWE offered attenuation coefficient (ATT), shear wave elasticity (SWE), and shear wave dispersion (SWD). Histologic grades of steatosis (S0–S3), fibrosis (F0–F3), and inflammation (A0–A3) served as the reference standard. Diagnostic performance was assessed using receiver operating characteristic (ROC) analysis.
Results
ATI outperformed ATT for detecting ≥S1 steatosis (AUROC 0.90 vs. 0.81, P = 0.036), while their performance for ≥S2 and ≥S3 was comparable. For significant fibrosis (≥F2), the F-index showed higher accuracy than SWE (AUROC 0.87 vs. 0.80, P = 0.046) with greater sensitivity (73.7%) and balanced specificity (85.3%). SWD demonstrated moderate diagnostic ability for inflammatory activity (AUROC 0.75 for ≥A2; 0.84 for ≥A3), and the A-index achieved AUROC 0.73 for detecting lobular inflammation grade ≥2.
Conclusions
ATI and ATT are reliable for assessing steatosis, the F-index provides superior accuracy for significant fibrosis, and SWD and A-index reflect overall and lobular inflammation, respectively. These multiparametric ultrasound techniques enable comprehensive, noninvasive evaluation of key histologic features in MASLD.
背景：定量超声技术可以无创地评估代谢功能障碍相关脂肪性肝病（MASLD）的肝脂肪变性、纤维化和炎症。本研究对双弹性成像和二维剪切波弹性成像（2D- swe）进行了全面的组织学评估。方法共纳入186例活检证实的MASLD患者。双弹性成像提供了衰减成像（ATI）、纤维化（f指数）和炎症活动性（a指数），而2D-SWE提供了衰减系数（ATT）、剪切波弹性（SWE）和剪切波弥散（SWD）。脂肪变性（S0-S3）、纤维化（F0-F3）和炎症（A0-A3）的组织学分级作为参考标准。采用受试者工作特征（ROC）分析评估诊断表现。结果sati在检测≥S1脂肪变性方面优于ATT (AUROC为0.90 vs. 0.81, P = 0.036)，在检测≥S2和≥S3脂肪变性方面具有可比性。对于显著纤维化（≥F2）， f指数的准确性高于SWE (AUROC 0.87 vs. 0.80, P = 0.046)，具有更高的敏感性（73.7%）和平衡的特异性（85.3%）。SWD对炎症活动性的诊断能力中等（≥A2的AUROC为0.75，≥A3的AUROC为0.84），检测小叶炎症等级≥2的a指数达到AUROC 0.73。结论sati和ATT是评估脂肪变性的可靠指标，f指数对显著纤维化具有较高的准确性，SWD和a指数分别反映整体和小叶炎症。这些多参数超声技术能够对MASLD的关键组织学特征进行全面、无创的评估。
{"title":"Head-to-head comparison of dual-elastography and 2D shear wave elastography for assessing steatosis, fibrosis, and inflammation in MASLD","authors":"Guangwen Cheng , Xueqi Li , Jing Liang , Iwaki Akiyama , Xiaohui Qiao , Liyun Xue , Hong Ding","doi":"10.1016/j.ejrad.2026.112673","DOIUrl":"10.1016/j.ejrad.2026.112673","url":null,"abstract":"<div><h3>Background</h3><div>Quantitative ultrasound techniques enable noninvasive assessment of hepatic steatosis, fibrosis, and inflammation in metabolic dysfunction-associated steatotic liver disease (MASLD). This study performed a head-to-head comparison of dual-elastography and 2D shear wave elastography (2D-SWE) for comprehensive histologic evaluation.</div></div><div><h3>Methods</h3><div>A total of 186 biopsy proven MASLD patients were enrolled. Dual-elastography provided attenuation imaging (ATI), fibrosis (F-index), and inflammatory activity (A-index), while 2D-SWE offered attenuation coefficient (ATT), shear wave elasticity (SWE), and shear wave dispersion (SWD). Histologic grades of steatosis (S0–S3), fibrosis (F0–F3), and inflammation (A0–A3) served as the reference standard. Diagnostic performance was assessed using receiver operating characteristic (ROC) analysis.</div></div><div><h3>Results</h3><div>ATI outperformed ATT for detecting ≥S1 steatosis (AUROC 0.90 vs. 0.81, P = 0.036), while their performance for ≥S2 and ≥S3 was comparable. For significant fibrosis (≥F2), the F-index showed higher accuracy than SWE (AUROC 0.87 vs. 0.80, P = 0.046) with greater sensitivity (73.7%) and balanced specificity (85.3%). SWD demonstrated moderate diagnostic ability for inflammatory activity (AUROC 0.75 for ≥A2; 0.84 for ≥A3), and the A-index achieved AUROC 0.73 for detecting lobular inflammation grade ≥2.</div></div><div><h3>Conclusions</h3><div>ATI and ATT are reliable for assessing steatosis, the F-index provides superior accuracy for significant fibrosis, and SWD and A-index reflect overall and lobular inflammation, respectively. These multiparametric ultrasound techniques enable comprehensive, noninvasive evaluation of key histologic features in MASLD.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112673"},"PeriodicalIF":3.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146035335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-21DOI: 10.1016/j.ejrad.2026.112695
Jiwoo Park , Kyunghwa Han , Ji Seon Oh , Hee Dong Chae , Ahram Kim , Si Young Park , Hye Jin Yoo , Young Han Lee
Objectives
To evaluate the diagnostic interchangeability of DL-enhanced accelerated lumbar (L)-spine magnetic resonance imaging (MRI) with conventional imaging and to assess the diagnostic agreement and feasibility of vision-language-model (VLM)-based automated reporting.
Methods
The Institutional Review Boards oftwo participating institutions approved this prospective study. Seventy patients were enrolled from these two institutions. All the participants underwent both conventional and accelerated L-spine MRI during the same session, resulting in 140 MRI scans. Quantitative analyses included signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), whereas qualitative image quality assessments were conducted by four radiologists blinded to the scan type and patient information. The interchangeability between conventional and accelerated MRI with DL-based enhancement protocols was evaluated for five key pathologic findings. Automated structured reports were generated using a commercially available VLM-based spine interpretation software and compared with radiologist consensus reports. Statistical analyses were performed, with p < 0.05 considered statistically significant.
Results
Accelerated L-spine MRI with DL-based enhancement reduced the acquisition time by approximately 80–86% when compared with conventional MRI, while maintaining diagnostic interchangeability. Quantitative analyses revealed superior SNRs and CNRs, and qualitative evaluations supported comparable image quality. Automated reporting demonstrated substantial to almost perfect agreement across key pathologies.
Conclusions
DL-enhanced accelerated MRI produced high-quality diagnostic images within 2 min, and VLM-based automated reporting demonstrated strong agreement with the radiologists. These findings provide prospective evidence supporting the clinical feasibility of integrating AI into both the acquisition and interpretation workflows in L-spine MRI, with the potential to enhance the efficiency, consistency, and scalability of musculoskeletal imaging.
{"title":"Prospective evaluation of artificial intelligence (AI) in lumbar spine magnetic resonance imaging (MRI) workflow: from deep learning (DL)-enhanced accelerated acquisition to simultaneous vision-language model (VLM)-based automated report generation","authors":"Jiwoo Park , Kyunghwa Han , Ji Seon Oh , Hee Dong Chae , Ahram Kim , Si Young Park , Hye Jin Yoo , Young Han Lee","doi":"10.1016/j.ejrad.2026.112695","DOIUrl":"10.1016/j.ejrad.2026.112695","url":null,"abstract":"<div><h3>Objectives</h3><div>To evaluate the diagnostic interchangeability of DL-enhanced accelerated lumbar (L)-spine magnetic resonance imaging (MRI) with conventional imaging and to assess the diagnostic agreement and feasibility of vision-language-model (VLM)-based automated reporting.</div></div><div><h3>Methods</h3><div>The Institutional Review Boards oftwo participating institutions approved this prospective study. Seventy patients were enrolled from these two institutions. All the participants underwent both conventional and accelerated L-spine MRI during the same session, resulting in 140 MRI scans. Quantitative analyses included signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), whereas qualitative image quality assessments were conducted by four radiologists blinded to the scan type and patient information. The interchangeability between conventional and accelerated MRI with DL-based enhancement protocols was evaluated for five key pathologic findings. Automated structured reports were generated using a commercially available VLM-based spine interpretation software and compared with radiologist consensus reports. Statistical analyses were performed, with <em>p</em> < 0.05 considered statistically significant.</div></div><div><h3>Results</h3><div>Accelerated L-spine MRI with DL-based enhancement reduced the acquisition time by approximately 80–86% when compared with conventional MRI, while maintaining diagnostic interchangeability. Quantitative analyses revealed superior SNRs and CNRs, and qualitative evaluations supported comparable image quality. Automated reporting demonstrated substantial to almost perfect agreement across key pathologies.</div></div><div><h3>Conclusions</h3><div>DL-enhanced accelerated MRI produced high-quality diagnostic images within 2 min, and VLM-based automated reporting demonstrated strong agreement with the radiologists. These findings provide prospective evidence supporting the clinical feasibility of integrating AI into both the acquisition and interpretation workflows in L-spine MRI, with the potential to enhance the efficiency, consistency, and scalability of musculoskeletal imaging.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112695"},"PeriodicalIF":3.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146035638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To evaluate the feasibility of correlation-weighted averaging factor (CWAF) in liver diffusion-weighted imaging (DWI).
Materials and methods
This prospective study included 103 participants who underwent liver MRI. DWI were reconstructed using both original data (DWIOriginal) and CWAF-corrected data (DWICWAF). Two radiologists independently assessed high-b DWI images for overall image quality, image noise, hepatic edge sharpness, and lesion conspicuity in the right and left lobes using five-point scales. Signal intensity ratio (SIR) and apparent diffusion coefficient (ADC) values were measured in four hepatic segments and in liver lesions, with lesion measurements analyzed separately for each lobe. These parameters were compared between the two image sets.
Results
The scores for overall image quality (P < 0.001), image noise (P < 0.001), and hepatic edge sharpness in the right lobe (P = 0.001) were higher in DWIOriginal compared with DWICWAF. In contrast, hepatic edge sharpness (P < 0.001) and lesion conspicuity (P < 0.001) in the left lobe were superior in DWICWAF. Liver and lesion SIRs were higher in DWICWAF across all segments than in DWIOriginal (P < 0.007). Liver ADC values were lower in DWICWAF than in DWIOriginal in all segments (P < 0.001). Lesion ADC values were also lower in DWICWAF than in DWIOriginal in the right lobe (P < 0.001) but were not different in the left lobe (P = 0.48).
Conclusion
CWAF improved hepatic edge sharpness and lesion conspicuity in the left lobe, although overall image quality was slightly reduced. ADC values were generally lower in DWICWAF than in DWIOriginal.
{"title":"Enhancing liver diffusion-weighted imaging quality with correlation-weighted averaging: notable benefits in the left hepatic lobe","authors":"Tetsuro Kaga , Yoshifumi Noda , Masashi Asano , Nobuyuki Kawai , Shingo Omata , Yukiko Takai , Satoshi Ido , Kimihiro Kajita , Abdelazim Elsayed Elhelaly , Hirohiko Imai , Hiroki Kato , Masayuki Matsuo","doi":"10.1016/j.ejrad.2026.112680","DOIUrl":"10.1016/j.ejrad.2026.112680","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the feasibility of correlation-weighted averaging factor (CWAF) in liver diffusion-weighted imaging (DWI).</div></div><div><h3>Materials and methods</h3><div>This prospective study included 103 participants who underwent liver MRI. DWI were reconstructed using both original data (DWI<sub>Original</sub>) and CWAF-corrected data (DWI<sub>CWAF</sub>). Two radiologists independently assessed high-<em>b</em> DWI images for overall image quality, image noise, hepatic edge sharpness, and lesion conspicuity in the right and left lobes using five-point scales. Signal intensity ratio (SIR) and apparent diffusion coefficient (ADC) values were measured in four hepatic segments and in liver lesions, with lesion measurements analyzed separately for each lobe. These parameters were compared between the two image sets.</div></div><div><h3>Results</h3><div>The scores for overall image quality (<em>P</em> < 0.001), image noise (<em>P</em> < 0.001), and hepatic edge sharpness in the right lobe (<em>P</em> = 0.001) were higher in DWI<sub>Original</sub> compared with DWI<sub>CWAF</sub>. In contrast, hepatic edge sharpness (<em>P</em> < 0.001) and lesion conspicuity (<em>P</em> < 0.001) in the left lobe were superior in DWI<sub>CWAF</sub>. Liver and lesion SIRs were higher in DWI<sub>CWAF</sub> across all segments than in DWI<sub>Original</sub> (<em>P</em> < 0.007). Liver ADC values were lower in DWI<sub>CWAF</sub> than in DWI<sub>Original</sub> in all segments (<em>P</em> < 0.001). Lesion ADC values were also lower in DWI<sub>CWAF</sub> than in DWI<sub>Original</sub> in the right lobe (<em>P</em> < 0.001) but were not different in the left lobe (<em>P</em> = 0.48).</div></div><div><h3>Conclusion</h3><div>CWAF improved hepatic edge sharpness and lesion conspicuity in the left lobe, although overall image quality was slightly reduced. ADC values were generally lower in DWI<sub>CWAF</sub> than in DWI<sub>Original</sub>.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112680"},"PeriodicalIF":3.3,"publicationDate":"2026-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-17DOI: 10.1016/j.ejrad.2026.112688
Joanna F Dipnall, Thomas O'Donnell, Richard S Page, Raphael Hau, Richard de Steiger, Andrew Bucknill, Andrew Oppy, Elton Edwards, Dinesh Varma, Ronan A Lyons, Peter Cameron, William Veitch, Emily Doole, Berwout Wiltschut, Leah Sleaby, Adil Zia, Robin Lee, Belinda J Gabbe
Purpose: This study used different metrics to assess the reliability of radiology text and images in Distal Radial Fractures (DRF) classifications using classifiers with varying levels of experience.
Methods: A random sample of 534 patients (16 + years) admitted to two major trauma centres for > 24 h for DRF management with 1,269 radiology images and radiology text reports were reviewed. Eight classifiers, with varying levels of experience, were randomly assigned patients, with overlap, to classify four different DRF classifications, nine radiological features and one treatment type: (two interns (802 text/images), three registrars (1,079 text/images), three orthopaedic trauma specialists (740 text/images)). The agreement measures utilised were: Percentage agreement (PA), Brennan/ Prediger coefficient, Cohen/Conger Kappa, Fleiss kappa, Gwet's AC, Krippendorff's alpha coefficient; all with 95% confidence intervals.
Results: For DRF classifications, the ulnar fracture (81%, 77%-86%) then AO Level 1 (67%, 60%-74%) had the highest PA; AO Level 3 had the lowest (29%, 23%-34%). For radiological features: highest PA was the presence/absence of tear drop/volar rim fragment (97%, 96%-98%) and severe dorsal comminution (97%, 96%-98%); lowest was ulnar variance (70%, 57%-83%). Treatment had high PA (96%, 87%-100%). Differences across classifier experience were not significant.
Conclusions: Even with descriptive texts from the radiology reports and x-ray images, DRF classification is complex and classifier experience not affecting classification. Generally, above fair agreement and interrater reliability was achieved, but the type and complexity of the classification task and the choice of agreement coefficient were important considerations in the reporting of agreement and reliability of the data.
{"title":"Inter-rater reliability of a classification systems for distal radius fractures using radiology text and x-rays: what really matters?","authors":"Joanna F Dipnall, Thomas O'Donnell, Richard S Page, Raphael Hau, Richard de Steiger, Andrew Bucknill, Andrew Oppy, Elton Edwards, Dinesh Varma, Ronan A Lyons, Peter Cameron, William Veitch, Emily Doole, Berwout Wiltschut, Leah Sleaby, Adil Zia, Robin Lee, Belinda J Gabbe","doi":"10.1016/j.ejrad.2026.112688","DOIUrl":"https://doi.org/10.1016/j.ejrad.2026.112688","url":null,"abstract":"<p><strong>Purpose: </strong>This study used different metrics to assess the reliability of radiology text and images in Distal Radial Fractures (DRF) classifications using classifiers with varying levels of experience.</p><p><strong>Methods: </strong>A random sample of 534 patients (16 + years) admitted to two major trauma centres for > 24 h for DRF management with 1,269 radiology images and radiology text reports were reviewed. Eight classifiers, with varying levels of experience, were randomly assigned patients, with overlap, to classify four different DRF classifications, nine radiological features and one treatment type: (two interns (802 text/images), three registrars (1,079 text/images), three orthopaedic trauma specialists (740 text/images)). The agreement measures utilised were: Percentage agreement (PA), Brennan/ Prediger coefficient, Cohen/Conger Kappa, Fleiss kappa, Gwet's AC, Krippendorff's alpha coefficient; all with 95% confidence intervals.</p><p><strong>Results: </strong>For DRF classifications, the ulnar fracture (81%, 77%-86%) then AO Level 1 (67%, 60%-74%) had the highest PA; AO Level 3 had the lowest (29%, 23%-34%). For radiological features: highest PA was the presence/absence of tear drop/volar rim fragment (97%, 96%-98%) and severe dorsal comminution (97%, 96%-98%); lowest was ulnar variance (70%, 57%-83%). Treatment had high PA (96%, 87%-100%). Differences across classifier experience were not significant.</p><p><strong>Conclusions: </strong>Even with descriptive texts from the radiology reports and x-ray images, DRF classification is complex and classifier experience not affecting classification. Generally, above fair agreement and interrater reliability was achieved, but the type and complexity of the classification task and the choice of agreement coefficient were important considerations in the reporting of agreement and reliability of the data.</p>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"112688"},"PeriodicalIF":3.3,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146124464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-17DOI: 10.1016/j.ejrad.2026.112666
Haotian Yuan , Lin Yuan , Jiapeng Chen , Naixu Shi , Detong Lin , Xinyu Wang , Chenfei Kong , Xiaofeng Wang
Head and neck squamous cell carcinoma (HNSCC) is a highly heterogeneous malignancy characterized by altered lactate metabolism, where traditional prognostic indicators are insufficient for precision medicine. This study aimed to construct an enhanced CT radiomics model integrated with lactate metabolism gene-related (LMGR) genomic signatures for HNSCC prognosis using TCGA and TCIA databases. A cohort of 399 HNSCC patients was analyzed. Analysis of 204 lactate-related genes identified 24 differentially expressed LMGR genes (DELMGR). Univariate Cox regression revealed that among these, PKLR, IL19, and CXCL9 exhibited protective effects (HR = 0.932, 0.885, and 0.931, respectively). A lactate classification score (LCS) was derived from the analysis of these three genes, demonstrating a significant correlation with overall survival (OS) in both univariate (HR = 1.807, 95 % CI: 1.346–2.424, P < 0.001) and multivariate assessments (HR = 1.772, 95 % CI: 1.296–2.424, P < 0.001). From enhanced CT images, 2060 radiomic features were extracted. Subsequently, after feature selection using mRMR and RFE algorithms, a support vector machine (SVM) model was built to predict LCS, which generated a radiomics score (RS). The model demonstrated AUC values of 0.773 and 0.760 in the training and validation datasets, respectively. The RS distribution significantly differed between lactate subtypes in the training cohort (P < 0.001), with specifically higher RS in the high-risk LCS group. High RS was associated with poor OS (HR = 3.582, 95 % CI: 1.240–10.348, P = 0.018) and was correlated with clinical features such as the perineural invasion and the margin status. Mechanistic analysis indicated that the high RS group was enriched in an immunosuppressive microenvironment and was associated with fatty acid metabolism pathways. This enhanced CT-based radiomics model effectively predicts lactate-based stratification, demonstrating potential prognostic value in HNSCC and providing novel biomarkers as well as a non-invasive predictive tool for prognostic assessment.
头颈部鳞状细胞癌（HNSCC）是一种高度异质性的恶性肿瘤，其特征是乳酸代谢改变，传统的预后指标不足以用于精准医学。本研究旨在利用TCGA和TCIA数据库，构建结合乳酸代谢基因相关（LMGR）基因组特征的HNSCC预后增强CT放射组学模型。对399例HNSCC患者进行队列分析。对204个乳酸相关基因进行分析，鉴定出24个差异表达LMGR基因（DELMGR）。单因素Cox回归结果显示，其中PKLR、IL19和CXCL9具有保护作用（HR分别为0.932、0.885和0.931）。通过对这三个基因的分析得出乳酸盐分类评分（LCS），显示单因素（HR = 1.807, 95% CI: 1.346-2.424, P < 0.001）和多因素评估（HR = 1.772, 95% CI: 1.296-2.424, P < 0.001）与总生存率（OS）有显著相关性。从增强CT图像中提取2060个放射学特征。随后，在使用mRMR和RFE算法进行特征选择后，建立支持向量机（SVM）模型来预测LCS，并生成放射组学评分（RS）。该模型在训练集和验证集上的AUC分别为0.773和0.760。训练队列中不同乳酸亚型的RS分布差异显著（P < 0.001），其中高危LCS组RS更高。RS高与OS差相关（HR = 3.582, 95% CI: 1.240 ~ 10.348, P = 0.018），并与神经周围侵袭、切缘状况等临床特征相关。机制分析表明，高RS组在免疫抑制微环境中富集，与脂肪酸代谢途径有关。这种增强的基于ct的放射组学模型有效地预测了基于乳酸盐的分层，显示了HNSCC的潜在预后价值，并提供了新的生物标志物以及用于预后评估的非侵入性预测工具。
{"title":"Development and validation of a radiomics model for lactate metabolism genes-based stratification and prognostic prediction in head and neck squamous cell carcinoma","authors":"Haotian Yuan , Lin Yuan , Jiapeng Chen , Naixu Shi , Detong Lin , Xinyu Wang , Chenfei Kong , Xiaofeng Wang","doi":"10.1016/j.ejrad.2026.112666","DOIUrl":"10.1016/j.ejrad.2026.112666","url":null,"abstract":"<div><div>Head and neck squamous cell carcinoma (HNSCC) is a highly heterogeneous malignancy characterized by altered lactate metabolism, where traditional prognostic indicators are insufficient for precision medicine. This study aimed to construct an enhanced CT radiomics model integrated with lactate metabolism gene-related (LMGR) genomic signatures for HNSCC prognosis using TCGA and TCIA databases. A cohort of 399 HNSCC patients was analyzed. Analysis of 204 lactate-related genes identified 24 differentially expressed LMGR genes (DELMGR). Univariate Cox regression revealed that among these, PKLR, IL19, and CXCL9 exhibited protective effects (HR = 0.932, 0.885, and 0.931, respectively). A lactate classification score (LCS) was derived from the analysis of these three genes, demonstrating a significant correlation with overall survival (OS) in both univariate (HR = 1.807, 95 % CI: 1.346–2.424, P < 0.001) and multivariate assessments (HR = 1.772, 95 % CI: 1.296–2.424, P < 0.001). From enhanced CT images, 2060 radiomic features were extracted. Subsequently, after feature selection using mRMR and RFE algorithms, a support vector machine (SVM) model was built to predict LCS, which generated a radiomics score (RS). The model demonstrated AUC values of 0.773 and 0.760 in the training and validation datasets, respectively. The RS distribution significantly differed between lactate subtypes in the training cohort (P < 0.001), with specifically higher RS in the high-risk LCS group. High RS was associated with poor OS (HR = 3.582, 95 % CI: 1.240–10.348, P = 0.018) and was correlated with clinical features such as the perineural invasion and the margin status. Mechanistic analysis indicated that the high RS group was enriched in an immunosuppressive microenvironment and was associated with fatty acid metabolism pathways. This enhanced CT-based radiomics model effectively predicts lactate-based stratification, demonstrating potential prognostic value in HNSCC and providing novel biomarkers as well as a non-invasive predictive tool for prognostic assessment.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112666"},"PeriodicalIF":3.3,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146035334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-17DOI: 10.1016/j.ejrad.2026.112687
Lei Cai , Xiaoyu Tong , Jingyi Ju , Zhaoyang Li , Deying Wen , Shuang Liu , Huilou Liang , Yufang Wang , Jiayu Sun
Rationale and Objectives
To investigate the diagnostic value of the enhancement slope in an 18-second ultrafast dynamic contrast-enhanced MRI (DCE-MRI) using differential subsampling with Cartesian ordering (DISCO) in quantifying Crohn’s Disease (CD) activity.
Materials and Methods
In a prospective cohort, 41CD patients (141 diseased segments) underwent endoscopy and 3.0 T magnetic resonance enterography (MRE). The DISCO sequence was employed for ultrafast DCE scanning. Using endoscopic results as the gold standard, the slope of the dynamic enhancement curve (K) and the magnetic resonance index of activity (MaRIA) were calculated. The correlations between the K value, MaRIA, relative contrast enhancement (RCE), and simple endoscopic activity score for Crohn’s disease (SES-CD) were analyzed. Diagnostic performance for categorizing CD activity (remission, mild, moderate–severe) was assessed by receiver operating characteristic (ROC) curve. To optimize the MaRIA for CD activity assessment, a modified MaRIA index was constructed by substituting the RCE in the original MaRIA with the K value. The diagnostic efficacy of this modified MaRIA was further validated, and its performance was compared with the original MaRIA to verify its clinical utility in distinguishing different CD activity states.
Results
The K showed positive correlation with the SES-CD score (r = 0.77, P < 0.001) and the MaRIA score (r = 0.70, P < 0.001), while the correlation between RCE and the SES-CD score was relatively weak (r = 0.54, P < 0.001). For diagnosing moderate-to-severe CD, the K showed an AUC of 0.916 (95% CI: 0.869, 0.950); when using the clinically relevant cutoff of 22.64, it yielded a sensitivity of 87.56% and a specificity of 83.44%. Notably, there was no significant difference in diagnostic performance between K and MaRIA. However, the AUC for diagnosing remission and mild was 0.609 (95% CI: 0.512, 0.701) and 0.889 (95% CI: 0.829, 0.934), respectively, slightly lower than that of MaRIA. The modified-MaRIA score demonstrated high diagnostic efficacy in differentiating remission-phase, mild, and moderate-to-severe CD, with AUC values of 0.947 (95% CI: 0.902, 0.970), 0.964 (95% CI: 0.922, 0.987), and 0.981 (95% CI: 0.936, 0.998), respectively. Additionally, its sensitivity and specificity both exceed 85%.
Conclusion
The 18-second ultrafast DCE-MRI enhancement slope streamlines workflow while serving as a robust noninvasive biomarker for CD activity. This methodology exhibits strong diagnostic efficacy in distinguishing mild and moderate-to-severe Crohn’s disease. Furthermore, incorporating K into MaRIA enhances the detection of remission-phase CD.
{"title":"Enhancement slope of ultrafast dynamic contrast-enhanced MRI: a promising biomarker for assessing Crohn’s disease activity","authors":"Lei Cai , Xiaoyu Tong , Jingyi Ju , Zhaoyang Li , Deying Wen , Shuang Liu , Huilou Liang , Yufang Wang , Jiayu Sun","doi":"10.1016/j.ejrad.2026.112687","DOIUrl":"10.1016/j.ejrad.2026.112687","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To investigate the diagnostic value of the enhancement slope in an 18-second ultrafast dynamic contrast-enhanced MRI (DCE-MRI) using differential subsampling with Cartesian ordering (DISCO) in quantifying Crohn’s Disease (CD) activity.</div></div><div><h3>Materials and Methods</h3><div>In a prospective cohort, 41CD patients (141 diseased segments) underwent endoscopy and 3.0 T magnetic resonance enterography (MRE). The DISCO sequence was employed for ultrafast DCE scanning. Using endoscopic results as the gold standard, the slope of the dynamic enhancement curve (K) and the magnetic resonance index of activity (MaRIA) were calculated. The correlations between the K value, MaRIA, relative contrast enhancement (RCE), and simple endoscopic activity score for Crohn’s disease (SES-CD) were analyzed. Diagnostic performance for categorizing CD activity (remission, mild, moderate–severe) was assessed by receiver operating characteristic (ROC) curve. To optimize the MaRIA for CD activity assessment, a modified MaRIA index was constructed by substituting the RCE in the original MaRIA with the K value. The diagnostic efficacy of this modified MaRIA was further validated, and its performance was compared with the original MaRIA to verify its clinical utility in distinguishing different CD activity states.</div></div><div><h3>Results</h3><div>The K showed positive correlation with the SES-CD score (r = 0.77, P < 0.001) and the MaRIA score (r = 0.70, P < 0.001), while the correlation between RCE and the SES-CD score was relatively weak (r = 0.54, P < 0.001). For diagnosing moderate-to-severe CD, the K showed an AUC of 0.916 (95% CI: 0.869, 0.950); when using the clinically relevant cutoff of 22.64, it yielded a sensitivity of 87.56% and a specificity of 83.44%. Notably, there was no significant difference in diagnostic performance between K and MaRIA. However, the AUC for diagnosing remission and mild was 0.609 (95% CI: 0.512, 0.701) and 0.889 (95% CI: 0.829, 0.934), respectively, slightly lower than that of MaRIA. The modified-MaRIA score demonstrated high diagnostic efficacy in differentiating remission-phase, mild, and moderate-to-severe CD, with AUC values of 0.947 (95% CI: 0.902, 0.970), 0.964 (95% CI: 0.922, 0.987), and 0.981 (95% CI: 0.936, 0.998), respectively. Additionally, its sensitivity and specificity both exceed 85%.</div></div><div><h3>Conclusion</h3><div>The 18-second ultrafast DCE-MRI enhancement slope streamlines workflow while serving as a robust noninvasive biomarker for CD activity. This methodology exhibits strong diagnostic efficacy in distinguishing mild and moderate-to-severe Crohn’s disease. Furthermore, incorporating K into MaRIA enhances the detection of remission-phase CD.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112687"},"PeriodicalIF":3.3,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-17DOI: 10.1016/j.ejrad.2026.112689
Jianliang Lu , Keith Wan-Hang Chiu , Chelsea Chan , Ho-Ming Cheng , Jian Zhou , Justin Christopher NG , Fanny Fong Yi Tang , Wai Kuen Kan , Philip Leung Ho Yu , Wai-Kay Seto
Background
This study evaluates the performance of a general-purpose (GPT-4) and a medically fine-tuned (Med-LM) large language model (LLM) in classifying liver lesions from unstructured Computed Tomography (CT) reports.
Methods
Consecutive CT reports (2014–2020) from five institutions were input into GPT-4 and Med-LM with simple (sp) and optimised (op) prompts. Lesion- and patient-level performance were benchmarked against LI-RADS scores assigned by two radiologists, and report quality was analysed using a 5-point Likert scale.
Results
A total of 296 CT reports (mean age, 64.6 years ± 11.3 [SD]; 193 men; 654 lesions) were included. Lesion- and patient-level accuracies for LI-RADS scoring ranged from 40.8% (Med-LMsp) to 61.3% (Med-LMop) and from 27.7% (Med-LMsp) to 52.4% (Med-LMop), respectively. When dichotomized into malignant and benign lesions, lesion- and patient-level accuracies rose to 56.1% (GPT-4sp) − 82.3% (Med-LMop) and 71.3% (Med-LMsp) – 86.5% (Med-LMop). Med-LMop demonstrated the highest performance in all analyses and was statistically superior to other models (all p < 0.001). Non-classification rates ranged between 12.7% (Med-LMop) and 40.5% (GPT-4sp), particularly for benign lesions. Kappa values were weak to moderate between the two reviewers in different aspects of report quality (0.471–0.766), and Likert scores for lesion information differed significantly between correctly and incorrectly classified lesions (all p ≤ 0.04). Repeatability varied widely from 12.7% (Med-LMop) to 39.0% (GPT-4sp).
Conclusions
Med-LM outperforms GPT-4 in classifying liver lesions from unstructured CT reports with both models better at detecting malignancy than full LI-RADS classification. However, high misclassification rates and inconsistent repeatability hinder their clinical use.
{"title":"Characterising liver lesions from free-text computer tomography reports – A real-world multicentre analysis","authors":"Jianliang Lu , Keith Wan-Hang Chiu , Chelsea Chan , Ho-Ming Cheng , Jian Zhou , Justin Christopher NG , Fanny Fong Yi Tang , Wai Kuen Kan , Philip Leung Ho Yu , Wai-Kay Seto","doi":"10.1016/j.ejrad.2026.112689","DOIUrl":"10.1016/j.ejrad.2026.112689","url":null,"abstract":"<div><h3>Background</h3><div>This study evaluates the performance of a general-purpose (GPT-4) and a medically fine-tuned (Med-LM) large language model (LLM) in classifying liver lesions from unstructured Computed Tomography (CT) reports.</div></div><div><h3>Methods</h3><div>Consecutive CT reports (2014–2020) from five institutions were input into GPT-4 and Med-LM with<!--> <!-->simple (sp)<!--> <!-->and<!--> <!-->optimised (op) prompts. Lesion-<!--> <!-->and<!--> <!-->patient-level performance were benchmarked against LI-RADS scores assigned by two radiologists, and report quality was analysed using a<!--> <!-->5-point Likert scale.</div></div><div><h3>Results</h3><div>A total of 296 CT reports (mean age, 64.6 years ± 11.3 [SD]; 193 men; 654 lesions) were included. Lesion- and patient-level accuracies for LI-RADS scoring ranged from 40.8% (Med-LMsp) to 61.3% (Med-LMop) and from 27.7% (Med-LMsp) to 52.4% (Med-LMop), respectively. When dichotomized into malignant and benign lesions, lesion- and patient-level accuracies rose to 56.1% (GPT-4sp) − 82.3% (Med-LMop) and 71.3% (Med-LMsp) – 86.5% (Med-LMop). Med-LMop demonstrated the highest performance in all analyses and was statistically superior to other models (all <em>p</em> < 0.001). Non-classification rates ranged between 12.7% (Med-LMop) and 40.5% (GPT-4sp), particularly for benign lesions. Kappa values were weak to moderate between the two reviewers in different aspects of report quality (0.471–0.766), and Likert scores for lesion information differed significantly between correctly and incorrectly classified lesions (all <em>p</em> ≤ 0.04). Repeatability varied widely from 12.7% (Med-LMop) to 39.0% (GPT-4sp).</div></div><div><h3>Conclusions</h3><div>Med-LM outperforms GPT-4 in classifying liver lesions from unstructured CT reports with both models better at detecting malignancy than full LI-RADS classification. However, high misclassification rates and inconsistent repeatability hinder their clinical use.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112689"},"PeriodicalIF":3.3,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146035637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号