Insights into Imaging最新文献

{"title":"Impaired right atrial function preceding right ventricular systolic dysfunction: clinical utility and long-term prognostic value in pulmonary hypertension.","authors":"Fan Yang, Yan Yan, Wang Jiang, Zhouming Wang, Caixin Wu, Qian Wu, Yuanlin Deng, Yamin Du, Zhenwen Yang, Zhang Zhang, Dong Li","doi":"10.1186/s13244-025-01996-6","DOIUrl":"10.1186/s13244-025-01996-6","url":null,"abstract":"<p><strong>Objectives: </strong>Pulmonary hypertension (PH) in patients with right ventricular systolic dysfunction (RVSD) is associated with a poor prognosis. This study assessed the characteristics of right atrial (RA) function using cardiac magnetic resonance feature tracking (CMR-FT) before RVSD onset and evaluated the long-term prognostic significance of these characteristics.</p><p><strong>Materials and methods: </strong>A total of 96 PH patients, including 36 without RVSD (PH-nonRVSD) and 60 with RVSD (PH-RVSD), were compared to 20 healthy controls (HCs). The RA reservoir, conduit, booster pump functions, and the right ventricular global longitudinal strain (RVGLS) were evaluated. Ventricular morphological and functional parameters of the RA and right ventricle (RV) were also acquired.</p><p><strong>Results: </strong>Compared with HCs, both RA reservoir and conduit functions were significantly reduced (p_s < 0.05) in the PH-nonRVSD, without significant morphological changes in either the RA or RV (p_s > 0.05). The RA reservoir and conduit function were significantly correlated with the right ventricular ejection fraction (RVEF), RVGLS, pulmonary vascular resistance, brain natriuretic peptide, cardiac index, and 6-min walk distance. Receiver operating characteristic analysis demonstrated that RA conduit function outperformed RVGLS and RVEF in differentiating PH-nonRVSD and HCs. However, a reduction in RA booster pump function was observed only in the PH-RVSD group (p < 0.001). During a median follow-up period of 97 (80-106) months, 45% of the included patients died. RA reservoir function was an independent predictor of all-cause mortality (HR = 0.963, 95% CI: 0.935-0.992, p = 0.014).</p><p><strong>Conclusions: </strong>RA function can detect right heart dysfunction prior to RVSD and monitor disease progression in patients with PH. Moreover, RA reservoir function independently predicts long-term prognosis.</p><p><strong>Critical relevance statement: </strong>Impairment of right atrial (RA) function, assessed by cardiac magnetic resonance feature tracking (CMR-FT), in pulmonary hypertension (PH) patients is sensitive in detecting right-sided heart dysfunction before right ventricular systolic dysfunction and can be utilized to monitor disease progression and long-term prognosis.</p><p><strong>Key points: </strong>RA function is sensitive in detecting early right heart dysfunction in PH patients. The disease progression of PH can be monitored by assessing RA function. RA function can serve as a tool for predicting long-term prognosis.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"115"},"PeriodicalIF":4.1,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12137862/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144215729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trends in CT use in an emergency department in Western Australia: 2015-2022.","authors":"Fouziah Almouqati, Thi Ninh Ha, Sharmani Barnard, Ashu Gupta, Elizabeth Thomas, Tracey Bhar, Colleen Taylor, Delia Hendrie","doi":"10.1186/s13244-025-01993-9","DOIUrl":"10.1186/s13244-025-01993-9","url":null,"abstract":"<p><strong>Objectives: </strong>We examined trends in CT use within the emergency department (ED) and their association with trends in subsequent hospital admission.</p><p><strong>Methods: </strong>This retrospective study analyzed administrative data on episodes of adults aged 18+ years who presented to the ED of a tertiary hospital in Western Australia (WA) from March 2015 to December 2022. Adjusted annual rates of CT use and hospital admission, stratified by CT status, were estimated using multivariable regression models.</p><p><strong>Results: </strong>Between 2015 and 2022, while the number of ED episodes increased by 8%, the number of CT scans rose by 90%. The crude rate of scans per 1000 ED episodes rose from 111 [95% CI: 108, 113] to 195 [95% CI: 192, 199]. After adjusting for variations in patients' characteristics, the rate increased from 118 [95% CI: 115, 121] to 173 [95% CI: 169, 176]. Admission rates were consistently higher for patients with CT but declined over time in both groups: from 47.6% [95% CI: 46.46, 48.75] to 42.01% [95% CI: 41.12, 42.9] for those with CT, and from 27.25% [95% CI: 26.86, 27.64] to 23.83% [95% CI: 23.47, 24.2] for those without. Compared to those without CT, the admission rate in those who underwent CT decreased by 2.17% [95% CI: 3.68, 0.66] over the period.</p><p><strong>Conclusions: </strong>CT use in the ED has continued to increase since 2015, coinciding with a greater decrease in admissions among patients who underwent CT. The appropriateness of this increase remains undetermined, warranting further investigation.</p><p><strong>Critical relevance statement: </strong>Given the ongoing efforts to optimize CT scan use, this study evaluates its current utilization in the emergency department and its usefulness in patient management, particularly in hospital admission.</p><p><strong>Key points: </strong>Examining CT use and usefulness is vital given ongoing optimization efforts. CT rates rose significantly, with a clear upward shift from 2020. This coincided with a greater drop in admission for CT patients than non-CT.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"116"},"PeriodicalIF":4.1,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12137846/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144215730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of sarcopenia on the progression of chronic non-bacterial osteomyelitis.","authors":"Daniel Vogele, Janine Akbulut, Franziska Müller-Reichart, Aleš Janda, Henner Morbach, Hermann J Girschick, Matthias C Schaal, Meinrad Beer, Clemens Benoit","doi":"10.1186/s13244-025-02001-w","DOIUrl":"10.1186/s13244-025-02001-w","url":null,"abstract":"<p><strong>Objectives: </strong>Chronic non-bacterial osteomyelitis (CNO) is the most common autoinflammatory bone disease in children and adolescents. This study investigated the progression of CNO lesions during therapy and the potential impact of sarcopenia on disease progression, utilizing routine MRI.</p><p><strong>Methods: </strong>A retrospective analysis of MRI examinations was conducted on 29 children and adolescents with CNO. CNO lesions were segmented. Sarcopenia was assessed using the total psoas muscle index (PMI) at lumbar vertebral levels L3/4 and L4/5. Measurements were taken at four time points during the disease course (T1: baseline, T2-T4: follow-up). Based on the PMI, patients were classified as sarcopenic or non-sarcopenic, and the progression of CNO lesions and the impact of sarcopenia were analyzed.</p><p><strong>Results: </strong>A total of 29 patients, aged 1-16 years, were included in the study, with 13 males and 16 females. Patients with sarcopenia had a significantly larger mean lesion area (868.95 mm², SD = 684.49) compared to those without sarcopenia (636.11 mm², SD = 832.41); p = 0.042, d = 0.4). The comparison between the two patient groups revealed a consistently lower percentage reduction in lesion size for the sarcopenic patients at all time points. Notably, the difference between T1 and T3 was statistically significant (p = 0.045, d = 0.82).</p><p><strong>Conclusion: </strong>The present study indicates that sarcopenia may serve as a negative prognostic factor in the treatment of CNO. Incorporating sarcopenia assessment as an additional parameter in routine whole-body MRI examinations could enhance the evaluation process.</p><p><strong>Critical relevance statement: </strong>Sarcopenia can be assessed using routine whole-body MRI in patients with CNO and may serve as a negative prognostic factor, potentially enhancing the evaluation process.</p><p><strong>Key points: </strong>Whole-body MRI is crucial for diagnosing and monitoring CNO. Routine whole-body MRI in CNO patients can also be used to assess sarcopenia as an additional parameter. Sarcopenia may act as a negative prognostic factor in CNO treatment, potentially improving the evaluation process.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"117"},"PeriodicalIF":4.1,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12137865/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144225349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Added value of 3D fast-field-echo (FRACTURE) sequences for cervical spondylosis diagnosis: a prospective multi-reader non-inferiority study.","authors":"Qizheng Wang, Xiaoying Xing, Zixian Zhang, Xiaoxi Ji, Shipei He, Yuxin Yang, Jiajia Xu, Qiang Zhao, Ning Lang","doi":"10.1186/s13244-025-01997-5","DOIUrl":"10.1186/s13244-025-01997-5","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the potential of fast field echo resembling a CT using restricted echo-spacing (FRACTURE) sequence to enhance conventional MRI in detecting bone abnormalities of cervical spondylosis.</p><p><strong>Materials and methods: </strong>137 consecutive patients with cervical spondylosis who underwent clinically indicated paired CT and MRI within 2 weeks between January and June 2024. After routine MRI, the 3D-FRACTURE sequences were performed. Three radiologists independently evaluated the data during three sessions: (1) CT with consensus, (2) routine MRI, and (3) FRACTURE, with a 4-week interval between sessions. Assessments included osteophytes, bony foraminal stenosis, posterior longitudinal ligament ossification (OPLL), their anatomical location, and diagnostic confidence, using CT as the reference standard. Inter- and intra-reader reproducibility was assessed using multi-rater Fleiss κ and the intraclass correlation coefficient (ICC), respectively. The non-inferiority assessment compared routine MRI/FRACTURE and CT diagnoses using a relative reduction margin of 0.5.</p><p><strong>Results: </strong>The study sample comprised 82 males and 55 females (age 56.9 ± 9.8 years). ICC indicated good to excellent inter-rater reliability for FRACTURE (osteophytes: ICC, 0.83-1.00; OPLL: ICC, 0.73-0.92; bony foraminal stenosis: ICC, 0.76-0.98), which was superior to conventional MRI (most ICC values < 0.7). The diagnostic confidence by FRACTURE sequences was significantly higher than by routine MRI (p < 0.001). Non-inferiority analysis demonstrated that FRACTURE and CT detection were similar for osteophyte, bony foraminal stenosis, and OPLL within a margin of 0.5.</p><p><strong>Conclusion: </strong>The FRACTURE sequence demonstrated comparable performance to CT in bone abnormalities detection in cervical spondylosis, superior to the routine MRI protocol.</p><p><strong>Critical relevance statement: </strong>The FRACTURE sequence addresses the limitations of conventional MRI in evaluating bone abnormalities, potentially minimizing radiation exposure and streamlining the diagnostic process for patients.</p><p><strong>Key points: </strong>MRI has advantages in the evaluation of cervical spondylosis, but is still insufficient in bone abnormalities evaluation. The FRACTURE sequence performed comparably to CT in bone abnormalities detection in cervical spondylosis. MRI with FRACTURE sequences may provide a non-ionizing method for assessing cervical spondylosis in some clinical settings.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"114"},"PeriodicalIF":4.1,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12133650/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144208468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-model quantitative MRI of uterine cancers in precision medicine's era-a narrative review.","authors":"Marco Gennarini, Rossella Canese, Silvia Capuani, Valentina Miceli, Federica Tomao, Innocenza Palaia, Valentina Zecca, Alessandra Maiuro, Ilaria Balba, Carlo Catalano, Stefania Maria Rita Rizzo, Lucia Manganaro","doi":"10.1186/s13244-025-01965-z","DOIUrl":"10.1186/s13244-025-01965-z","url":null,"abstract":"<p><strong>Purpose: </strong>This review aims to summarize the current applications of quantitative MRI biomarkers in the staging, treatment response evaluation, and prognostication of endometrial (EC) and cervical cancer (CC). By focusing on functional imaging techniques, we explore how these biomarkers enhance personalized cancer management beyond traditional morphological assessments.</p><p><strong>Methods: </strong>A structured search of the PubMed database from January to May 2024 was conducted to identify relevant studies on quantitative MRI in uterine cancers. We included studies examining MRI biomarkers like Dynamic Contrast-Enhanced MRI (DCE-MRI), Diffusion-Weighted Imaging (DWI), and Magnetic Resonance Spectroscopy (MRS), emphasizing their roles in assessing tumor physiology, microstructure, and metabolic changes.</p><p><strong>Results: </strong>DCE-MRI provides valuable quantitative biomarkers such as Ktrans and Ve, which reflect microvascular characteristics and tumor aggressiveness, outperforming T2-weighted imaging in detecting critical factors like myometrial and cervical invasion. DWI, including advanced models like Intravoxel Incoherent Motion (IVIM), distinguishes between normal and cancerous tissue and correlates with tumor grade and treatment response. MRS identifies metabolic alterations, such as elevated choline and lipid signals, which serve as prognostic markers in uterine cancers.</p><p><strong>Conclusion: </strong>Quantitative MRI offers a noninvasive method to assess key biomarkers that inform prognosis and guide treatment decisions in uterine cancers. By providing insights into tumor biology, these imaging techniques represent a significant step forward in the precision medicine era, allowing for a more tailored therapeutic approach based on the unique pathological and molecular characteristics of each tumor.</p><p><strong>Critical relevance statement: </strong>Biomarkers obtained from MRI can provide useful quantitative information about the nature of uterine cancers and their prognosis, both at diagnosis and response assessment, allowing better therapeutic strategies to be prepared.</p><p><strong>Key points: </strong>Quantitative MRI improves diagnosis and management of uterine cancers through advanced imaging biomarkers. Quantitative MRI biomarkers enhance staging, prognosis, and treatment response assessment in uterine cancers. Quantitative MRI biomarkers support personalized treatment strategies and improve patient management in uterine cancers.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"113"},"PeriodicalIF":4.1,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12119420/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144173768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Solitary fibrous tumors from A to Z: a pictorial review with radiologic-pathologic correlation.","authors":"Fatmaelzahraa Abdelfattah Denewar, Mitsuru Takeuchi, Doaa Khedr, Fatma Mohamed Sherif, Farah A Shokeir, Misugi Urano, Ahmed E Eladl","doi":"10.1186/s13244-025-01991-x","DOIUrl":"10.1186/s13244-025-01991-x","url":null,"abstract":"<p><p>Solitary fibrous tumors (SFTs) represent a rare subset of mesenchymal neoplasms, affecting 1-2 per million people, with no gender preference. They demonstrate indolent behavior, frequent asymptomatic presentation, and widespread anatomical involvement. At imaging, SFTs typically appear as well-defined, predominantly hypervascular masses with varying degrees of cystic change and necrosis, though calcification is rare. Avid heterogeneous enhancement is typical following intravenous contrast administration, with multiple blood vessels observed at the periphery. Although findings on CT and MRI alone are generally nonspecific, a frequent feature of SFTs at MRI is the presence of rounded or linear low signal intensity foci on T1- and T2-weighted images, corresponding to the fibrous and collagenous content. Nevertheless, because the imaging features of SFTs overlap with those of many benign and malignant tumors, histologic confirmation is required for the final diagnosis. A comprehensive understanding of SFTs' multifaceted clinical, pathological, and radiological presentations across various organs is crucial for accurate diagnosis and effective management. CRITICAL RELEVANCE STATEMENT: A comprehensive understanding of the classic radiological and pathological features of solitary fibrous tumors across various organs is crucial for accurate diagnosis and effective management. KEY POINTS: Solitary fibrous tumors (SFTs) are rare hypervascular fibrous tumors with indolent behavior. Imaging features of SFTs overlap with many other tumors, necessitating histologic confirmation. Understanding SFTs' radiological presentations is crucial for accurate diagnosis and effective management.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"112"},"PeriodicalIF":4.1,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12120103/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144173769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inter- and intra-observer variability of software quantified bowel motility measurements of small bowel Crohn's disease: findings from the MOTILITY trial.","authors":"Maira Hameed, Andrew A Plumb, Kashfia Chowdhury, Norin Ahmed, Safi Rahman, Gauraang Bhatnagar, Elen Thomson, Maryam Mohsin, Jude Holmes, Steve Halligan, Stuart A Taylor","doi":"10.1186/s13244-025-01978-8","DOIUrl":"https://doi.org/10.1186/s13244-025-01978-8","url":null,"abstract":"<p><strong>Objectives: </strong>Motility magnetic resonance imaging (mMRI) is a potential marker of disease activity of small bowel Crohn's disease (SBCD), but there is limited data on its reproducibility. We assessed inter- and intra-observer agreement of small bowel motility as part of a prospective multicentre trial investigating whether mMRI can predict longer-term response to biologic therapy in active, non-stricturing SB-CD (MOTILITY Trial).</p><p><strong>Methods: </strong>297 segmental small bowel motility scores from 104 SBCD patients (mean age 38.9 years, 43 female) recruited to the MOTILITY trial were measured independently by two radiologists experienced in mMRI, using GIQuant software. Twenty-six datasets were re-read by both radiologists to test intra-observer variability after a washout period of at least 6 weeks. Five gastrointestinal radiologists inexperienced in mMRI derived 66 segmental motility scores from the same 30 randomly selected patients. Agreement was quantified using the intra-class correlation coefficient (ICC).</p><p><strong>Results: </strong>There was moderate agreement for mMRI-derived segmental small bowel motility measurements for both mMRI-experienced and inexperienced radiologists (ICC 0.59 (95% CI: 0.51, 0.66) and 0.70 (95% CI: 0.61, 0.78), respectively). Agreement remained moderate to good, combining the experienced trial MRI reader measurements with those of the five inexperienced radiologists (ICC 0.69 (95% CI: 0.61, 0.78). Intra-observer agreement for the two mMRI experienced radiologists was (0.71 (95% CI: 0.44, 0.86) and 0.70 (95% CI: 0.44, 0.86)).</p><p><strong>Conclusions: </strong>There is moderate to good interobserver agreement for mMRI measurements of segmental small bowel motility for both experienced and inexperienced radiologists.</p><p><strong>Critical relevance statement: </strong>Study findings support the continuing clinical translation of motility MRI as a reproducible biomarker of disease activity and treatment response in Crohn's disease.</p><p><strong>Key points: </strong>Motility MRI is a novel biomarker of small bowel Crohn's disease activity. Currently, limited data on intra- and inter-observer variability exists. Motility MRI shows moderate to good inter- and intra-observer agreement. Intraclass correlation was 0.59-0.71 for experienced and inexperienced radiologists. Motility MRI is reproducible, supporting its utility as a biomarker of disease activity.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"111"},"PeriodicalIF":4.1,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12116975/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144208469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a deep-learning segmentation model for patients with colorectal cancer liver metastases (COALA) in the radiological workflow.","authors":"Michiel Zeeuw, Jacqueline Bereska, Marius Strampel, Luuk Wagenaar, Boris Janssen, Henk Marquering, Ruby Kemna, Jan Hein van Waesberghe, Janneke van den Bergh, Irene Nota, Shira Moos, Yung Nio, Marnix Kop, Jakob Kist, Femke Struik, Nina Wesdorp, Jules Nelissen, Katinka Rus, Alexandra de Sitter, Jaap Stoker, Joost Huiskens, Inez Verpalen, Geert Kazemier","doi":"10.1186/s13244-025-01984-w","DOIUrl":"10.1186/s13244-025-01984-w","url":null,"abstract":"<p><strong>Objectives: </strong>For patients with colorectal liver metastases (CRLM), total tumor volume (TTV) is prognostic. A deep-learning segmentation model for CRLM to assess TTV called COlorectal cAncer Liver metastases Assessment (COALA) has been developed. This study evaluated COALA's performance and practical utility in the radiological picture archiving and communication system (PACS). A secondary aim was to provide lessons for future researchers on the implementation of artificial intelligence (AI) models.</p><p><strong>Methods: </strong>Patients discussed between January and December 2023 in a multidisciplinary meeting for CRLM were included. In those patients, CRLM was automatically segmented in portal-venous phase CT scans by COALA and integrated with PACS. Eight expert abdominal radiologists completed a questionnaire addressing segmentation accuracy and PACS integration. They were also asked to write down general remarks.</p><p><strong>Results: </strong>In total, 57 patients were evaluated. Of those patients, 112 contrast-enhanced portal-venous phase CT scans were analyzed. Of eight radiologists, six (75%) evaluated the model as user-friendly in their radiological workflow. Areas of improvement of the COALA model were the segmentation of small lesions, heterogeneous lesions, and lesions at the border of the liver with involvement of the diaphragm or heart. Key lessons for implementation were a multidisciplinary approach, a robust method prior to model development and organizing evaluation sessions with end-users early in the development phase.</p><p><strong>Conclusion: </strong>This study demonstrates that the deep-learning segmentation model for patients with CRLM (COALA) is user-friendly in the radiologist's PACS. Future researchers striving for implementation should have a multidisciplinary approach, propose a robust methodology and involve end-users prior to model development.</p><p><strong>Critical relevance statement: </strong>Many segmentation models are being developed, but none of those models are evaluated in the (radiological) workflow or clinically implemented. Our model is implemented in the radiological work system, providing valuable lessons for researchers to achieve clinical implementation.</p><p><strong>Key points: </strong>Developed segmentation models should be implemented in the radiological workflow. Our implemented segmentation model provides valuable lessons for future researchers. If implemented in clinical practice, our model could allow for objective radiological evaluation.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"110"},"PeriodicalIF":4.1,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12102431/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144132314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mammography-based artificial intelligence for breast cancer detection, diagnosis, and BI-RADS categorization using multi-view and multi-level convolutional neural networks.","authors":"Hongna Tan, Qingxia Wu, Yaping Wu, Bingjie Zheng, Bo Wang, Yan Chen, Lijuan Du, Jing Zhou, Fangfang Fu, Huihui Guo, Cong Fu, Lun Ma, Pei Dong, Zhong Xue, Dinggang Shen, Meiyun Wang","doi":"10.1186/s13244-025-01983-x","DOIUrl":"10.1186/s13244-025-01983-x","url":null,"abstract":"<p><strong>Purpose: </strong>We developed an artificial intelligence system (AIS) using multi-view multi-level convolutional neural networks for breast cancer detection, diagnosis, and BI-RADS categorization support in mammography.</p><p><strong>Methods: </strong>Twenty-four thousand eight hundred sixty-six breasts from 12,433 Asian women between August 2012 and December 2018 were enrolled. The study consisted of three parts: (1) evaluation of AIS performance in malignancy diagnosis; (2) stratified analysis of BI-RADS 3-4 subgroups with AIS; and (3) reassessment of BI-RADS 0 breasts with AIS assistance. We further evaluate AIS by conducting a counterbalance-designed AI-assisted study, where ten radiologists read 1302 cases with/without AIS assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and F1 score were measured.</p><p><strong>Results: </strong>The AIS yielded AUC values of 0.995, 0.933, and 0.947 for malignancy diagnosis in the validation set, testing set 1, and testing set 2, respectively. Within BI-RADS 3-4 subgroups with pathological results, AIS downgraded 83.1% of false-positives into benign groups, and upgraded 54.1% of false-negatives into malignant groups. AIS also successfully assisted radiologists in identifying 7 out of 43 malignancies initially diagnosed with BI-RADS 0, with a specificity of 96.7%. In the counterbalance-designed AI-assisted study, the average AUC across ten readers significantly improved with AIS assistance (p = 0.001).</p><p><strong>Conclusion: </strong>AIS can accurately detect and diagnose breast cancer on mammography and further serve as a supportive tool for BI-RADS categorization.</p><p><strong>Critical relevance statement: </strong>An AI risk assessment tool employing deep learning algorithms was developed and validated for enhancing breast cancer diagnosis from mammograms, to improve risk stratification accuracy, particularly in patients with dense breasts, and serve as a decision support aid for radiologists.</p><p><strong>Key points: </strong>The false positive and negative rates of mammography diagnosis remain high. The AIS can yield a high AUC for malignancy diagnosis. The AIS is important in stratifying BI-RADS categorization.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"109"},"PeriodicalIF":4.1,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12095762/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144110836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images.","authors":"Bangxin Xiao, Yang Lv, Canjie Peng, Zongjie Wei, Qiao Xv, Fajin Lv, Qing Jiang, Huayun Liu, Feng Li, Yingjie Xv, Quanhao He, Mingzhao Xiao","doi":"10.1186/s13244-025-01988-6","DOIUrl":"10.1186/s13244-025-01988-6","url":null,"abstract":"<p><strong>Objectives: </strong>Lymphovascular invasion significantly impacts the prognosis of urothelial carcinoma of the bladder. Traditional lymphovascular invasion detection methods are time-consuming and costly. This study aims to develop a deep learning-based model to preoperatively predict lymphovascular invasion status in urothelial carcinoma of bladder using CT images.</p><p><strong>Methods: </strong>Data and CT images of 577 patients across four medical centers were retrospectively collected. The largest tumor slices from the transverse, coronal, and sagittal planes were selected and used to train CNN models (InceptionV3, DenseNet121, ResNet18, ResNet34, ResNet50, and VGG11). Deep learning features were extracted and visualized using Grad-CAM. Principal Component Analysis reduced features to 64. Using the extracted features, Decision Tree, XGBoost, and LightGBM models were trained with 5-fold cross-validation and ensembled in a stacking model. Clinical risk factors were identified through logistic regression analyses and combined with DL scores to enhance lymphovascular invasion prediction accuracy.</p><p><strong>Results: </strong>The ResNet50-based model achieved an AUC of 0.818 in the validation set and 0.708 in the testing set. The combined model showed an AUC of 0.794 in the validation set and 0.767 in the testing set, demonstrating robust performance across diverse data.</p><p><strong>Conclusion: </strong>We developed a robust radiomics model based on deep learning features from CT images to preoperatively predict lymphovascular invasion status in urothelial carcinoma of the bladder. This model offers a non-invasive, cost-effective tool to assist clinicians in personalized treatment planning.</p><p><strong>Critical relevance statement: </strong>We developed a robust radiomics model based on deep learning features from CT images to preoperatively predict lymphovascular invasion status in urothelial carcinoma of the bladder.</p><p><strong>Key points: </strong>We developed a deep learning feature-based stacking model to predict lymphovascular invasion in urothelial carcinoma of the bladder patients using CT. Max cross sections from three dimensions of the CT image are used to train the CNN model. We made comparisons across six CNN networks, including ResNet50.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"108"},"PeriodicalIF":4.1,"publicationDate":"2025-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12086130/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144093530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}