{"title":"Developments in MRI radiomics research for vascular cognitive impairment.","authors":"Xuezhi Chen, Xianting Luo, Liang Chen, Hao Liu, Xiaoping Yin, Zhiying Chen","doi":"10.1186/s13244-025-02026-1","DOIUrl":"https://doi.org/10.1186/s13244-025-02026-1","url":null,"abstract":"<p><p>Vascular cognitive impairment (VCI) is an umbrella term for diseases associated with cognitive decline induced by substantive brain damage following pathological changes in the cerebrovascular system. The primary clinical manifestations include behavioral abnormalities and diminished learning and memory cognitive functions. If the location and extent of brain injury are not identified early and therapeutic interventions are not promptly administered, it may lead to irreversible cognitive impairment. Therefore, the early diagnosis of VCI is crucial for its prevention and treatment. Prior to the onset of cognitive impairment in VCI, magnetic resonance imaging (MRI) radiomics can be utilized for early assessment and diagnosis, thereby guiding clinicians in providing precise treatment for patients, which holds significant potential for development. This article reviews the classification of VCI, the concept of radiomics, the application of MRI radiomics in VCI, and the limitations of radiomics in the context of advancements in its application within the central nervous system. CRITICAL RELEVANCE STATEMENT: This article explores how MRI radiomics can be used to detect VCI early, enhancing clinical radiology practice by offering a reliable method for prediction, diagnosis, and identification, which also promotes standardization in research and integration of disciplines. KEY POINTS: MRI radiomics can predict VCI early. MRI radiomics can diagnose VCI. MRI radiomics distinguishes VCI from Alzheimer's disease.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"146"},"PeriodicalIF":4.1,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144540076","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":"Predictive value of subacromial motion metrics for the effectiveness of ultrasound-guided dual-target injection: a longitudinal follow-up cohort trial.","authors":"Wei-Ting Wu, Che-Yu Lin, Yi-Chung Shu, Lan-Rong Chen, Levent Özçakar, Ke-Vin Chang","doi":"10.1186/s13244-025-01989-5","DOIUrl":"https://doi.org/10.1186/s13244-025-01989-5","url":null,"abstract":"<p><strong>Objective: </strong>Subacromial impingement syndrome (SIS) frequently causes shoulder pain. This study aimed to (1) assess the predictive utility of quantitative dynamic subacromial ultrasound for ultrasound-guided dual-target injections and (2) compare the long-term efficacy of dual-target injections with standard subdeltoid-subacromial injections in SIS patients.</p><p><strong>Methods: </strong>Patients with SIS received 40 mg of triamcinolone acetonide via ultrasound-guided dual-target injections (subdeltoid-subacromial bursa and long head of the biceps brachii tendon). Clinical assessments and static/dynamic ultrasound were performed at baseline and 4 weeks post-procedure. Minimal vertical acromiohumeral distance (mVAHD) was measured by tracing the humeral greater tuberosity against the acromion. A historical cohort receiving standard subdeltoid-subacromial corticosteroid injections was used for comparison.</p><p><strong>Results: </strong>Of 90 patients receiving dual-target injections, 70 (77.7%) achieved early treatment success. An enlarged minimal mVAHD was associated with success, except during the abduction phase in the full-can posture. Among these 70 patients, 25 (35.7%) had shoulder pain recurrence requiring repeat injections, linked to a decreased mVAHD across all phases and postures. Compared to 90 patients in a historical cohort receiving standard subdeltoid-subacromial injections, the dual-target group had a significantly longer mean time to pain recurrence (309.1 ± 130.1 days vs. 267.5 ± 184.2 days, p = 0.03).</p><p><strong>Conclusion: </strong>Dynamic ultrasound metrics, including mVAHD, predict early success and pain recurrence following dual-target injections in SIS. Dual-target injections offer a longer duration of effectiveness compared to standard subdeltoid-subacromial injections. Future research should explore the predictive value of mVAHD with deep learning algorithms and evaluate the approach in adhesive capsulitis.</p><p><strong>Trial registration: </strong>ClinicalTrials.gov (NCT04219527). Registered on 27 December 2019, https://clinicaltrials.gov/study/NCT04219527 .</p><p><strong>Critical relevance statement: </strong>Dynamic ultrasound metrics predict early success and pain recurrence following dual-target injections in SIS, offering a longer duration of effectiveness compared to standard subdeltoid-subacromial injections.</p><p><strong>Key points: </strong>Dynamic ultrasound metrics predict injection success and pain recurrence in impingement. Dual-target injections offer a longer duration of effectiveness than standard injections. Future research should assess deep learning's predictive value in adhesive capsulitis.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"145"},"PeriodicalIF":4.1,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144540077","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":"Thin-slice T<sub>2</sub>-weighted images and deep-learning-based super-resolution reconstruction: improved preoperative assessment of vascular invasion for pancreatic ductal adenocarcinoma.","authors":"Xiaoqi Zhou, Yuxin Wu, Yanjin Qin, Chenyu Song, Meng Wang, Huasong Cai, Qiaochu Zhao, Jiawei Liu, Jifei Wang, Zhi Dong, Yanji Luo, Zhenpeng Peng, Shi-Ting Feng","doi":"10.1186/s13244-025-02022-5","DOIUrl":"https://doi.org/10.1186/s13244-025-02022-5","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the efficacy of thin-slice T<sub>2</sub>-weighted imaging (T<sub>2</sub>WI) and super-resolution reconstruction (SRR) for preoperative assessment of vascular invasion in pancreatic ductal adenocarcinoma (PDAC).</p><p><strong>Methods: </strong>Ninety-five PDACs with preoperative MRI were retrospectively enrolled as a training set, with non-reconstructed T<sub>2</sub>WI (NRT<sub>2</sub>) in different slice thicknesses (NRT<sub>2</sub>-3, 3 mm; NRT<sub>2</sub>-5, ≥ 5 mm). A prospective test set was collected with NRT<sub>2</sub>-5 (n = 125) only. A deep-learning network was employed to generate reconstructed super-resolution T<sub>2</sub>WI (SRT<sub>2</sub>) in different slice thicknesses (SRT<sub>2</sub>-3, 3 mm; SRT<sub>2</sub>-5, ≥ 5 mm). Image quality was assessed, including the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and signal-intensity ratio (SIR<sub>t/p</sub>, tumor/pancreas; SIR<sub>t/b</sub>, tumor/background). Diagnostic efficacy for vascular invasion was evaluated using the area under the curve (AUC) and compared across different slice thicknesses before and after reconstruction.</p><p><strong>Results: </strong>SRT<sub>2</sub>-5 demonstrated higher SNR and SIR<sub>t/p</sub> compared to NRT<sub>2</sub>-5 (74.18 vs 72.46; 1.42 vs 1.30; p < 0.05). SRT<sub>2</sub>-3 showed increased SIR<sub>t/p</sub> and SIR<sub>t/b</sub> over NRT<sub>2</sub>-3 (1.35 vs 1.31; 2.73 vs 2.58; p < 0.05). SRT<sub>2</sub>-5 showed higher CNR, SIR<sub>t/p</sub> and SIR<sub>t/b</sub> than NRT<sub>2</sub>-3 (p < 0.05). NRT<sub>2</sub>-3 outperformed NRT<sub>2</sub>-5 in evaluating venous invasion (AUC: 0.732 vs 0.597, p = 0.021). SRR improved venous assessment (AUC: NRT<sub>2</sub>-3, 0.927 vs 0.732; NRT<sub>2</sub>-5, 0.823 vs 0.597; p < 0.05), and SRT<sub>2</sub>-5 exhibits comparable efficacy to NRT<sub>2</sub>-3 in venous assessment (AUC: 0.823 vs 0.732, p = 0.162).</p><p><strong>Conclusion: </strong>Thin-slice T<sub>2</sub>WI and SRR effectively improve the image quality and diagnostic efficacy for assessing venous invasion in PDAC. Thick-slice T<sub>2</sub>WI with SRR is a potential alternative to thin-slice T<sub>2</sub>WI.</p><p><strong>Critical relevance statement: </strong>Both thin-slice T<sub>2</sub>-WI and SRR effectively improve image quality and diagnostic performance, providing valuable options for optimizing preoperative vascular assessment in PDAC. Non-invasive and accurate assessment of vascular invasion supports treatment planning and avoids futile surgery.</p><p><strong>Key points: </strong>Vascular invasion evaluation is critical for the surgical eligibility of PDAC. SRR improved image quality and vascular assessment in T<sub>2</sub>WI. Utilizing thin-slice T<sub>2</sub>WI and SRR aids in clinical decision making for PDAC.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"144"},"PeriodicalIF":4.1,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144527814","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":"Advantages of BioMatrix respiratory gating in free-breathing three-dimensional magnetic resonance cholangiopancreatography: a prospective comparative study.","authors":"Qing Yang, Xueyi Ding, Qiuyang Guo, Yifan Tang, Jianyu Lin, Yantu Huang, Mengxiao Liu, Junqiang Lei","doi":"10.1186/s13244-025-02023-4","DOIUrl":"10.1186/s13244-025-02023-4","url":null,"abstract":"<p><strong>Objectives: </strong>To compare the image acquisition time, total examination time, image quality, and technical reliability of three free-breathing MRCP techniques: BioMatrix-triggered (BM-MRCP), respiratory-gating triggered using respiratory bellows (RG-MRCP), and navigator-triggered (NT-MRCP).</p><p><strong>Methods: </strong>A prospective intra-individual comparison was performed in 47 patients undergoing 3.0-T MRCP for suspected pancreatic and biliary diseases. Two patients with technique adaptability limitations were included in the reliability analysis as \"technical failures.\" For primary analyses, data from 45 patients completing all three techniques were used. Image quality was evaluated by three blinded radiologists (experience: 5, 10, 16 years). Statistical analysis included Friedman tests with Bonferroni correction (p < 0.0167).</p><p><strong>Results: </strong>Median total examination times were significantly shorter for BM-MRCP (218 [48] seconds) compared to RG-MRCP (228 [56] seconds) and NT-MRCP (259 [53] seconds) (p < 0.05). BM-MRCP and RG-MRCP had comparable image acquisition times, both significantly faster than NT-MRCP (p < 0.05). BM-MRCP provided superior image quality for key anatomical structures (p < 0.05), higher SNR, and CNR compared to RG-MRCP and NT-MRCP (p < 0.05). Image contrast showed no significant differences (p > 0.05). Two patients experienced failures with RG-MRCP or NT-MRCP due to breathing issues, while BM-MRCP had no failures.</p><p><strong>Conclusion: </strong>BM-MRCP significantly reduces examination times while achieving superior image quality and technical reliability. Its integration into clinical workflows enhances efficiency, reduces technician workload, and improves patient-centered imaging.</p><p><strong>Critical relevance statement: </strong>BioMatrix-gating 3D-MRCP enhances imaging efficiency and diagnostic accuracy for the biliary and pancreatic duct systems. By reducing scan times and improving workflow, it supports patient comfort and compliance. Its simplicity and reliability also make it ideal for high-throughput clinical settings.</p><p><strong>Key points: </strong>BioMatrix-triggered (BM)-MRCP shortens examination time, aiding patients with compliance or limitations. BM-MRCP offers superior image quality with reduced motion artifacts and higher clarity. BM respiratory sensors streamline workflows, boost reliability, and enhance patient comfort.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"137"},"PeriodicalIF":4.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205134/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511886","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}
Silvia Bottazzi, Roberta V Ninkova, Luca Russo, Andrea Ponsiglione, Benedetta Gui, Daniela Demundo, Massimo Imbriaco, Aradhana M Venkatesan, Evis Sala, Stephanie Nougaret, Lucia Manganaro, Stefania Rizzo
{"title":"Incidental findings in female pelvis MRI performed for gynaecological malignancies.","authors":"Silvia Bottazzi, Roberta V Ninkova, Luca Russo, Andrea Ponsiglione, Benedetta Gui, Daniela Demundo, Massimo Imbriaco, Aradhana M Venkatesan, Evis Sala, Stephanie Nougaret, Lucia Manganaro, Stefania Rizzo","doi":"10.1186/s13244-025-02006-5","DOIUrl":"10.1186/s13244-025-02006-5","url":null,"abstract":"<p><p>Incidental findings on female pelvic MRI present diagnostic challenges and may have significant clinical implications. Defined as abnormalities unrelated to the primary imaging indication, these findings have become increasingly prevalent with the expanded use of MRI in gynaecological practice. Standard gynaecological MRI protocols, incorporating T1- and T2-weighted sequences, diffusion-weighted imaging, and contrast-enhanced sequences, facilitate the characterisation of numerous extra-gynaecological abnormalities, ranging from benign to critical lesions. This review proposes a compartment-based approach for identifying extra-gynaecological findings, discussing their imaging characteristics and differential diagnoses. This approach may help radiologists systematically assess incidental findings, potentially improving the recognition of clinically relevant abnormalities and supporting timely clinical decision-making. CRITICAL RELEVANCE STATEMENT: Incidental extra-gynaecological findings on pelvic MRI can present significant diagnostic challenges. Systematic evaluation of incidental extra-gynaecological findings on pelvic MRI can improve radiologists' awareness of clinically relevant abnormalities. KEY POINTS: Extra-gynaecological incidental findings on pelvic MRI are common and range from benign to malignant conditions. A compartment-based classification-dividing the female pelvis into anterior, lateral, posterior, musculoskeletal, and miscellaneous compartments-provides a systematic framework for interpretation. Thorough assessment of all MRI sequences, including large field-of-view images, may help identify clinically relevant incidental findings.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"143"},"PeriodicalIF":4.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12204973/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511889","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":"Development and psychometric evaluation of the fear of medical imaging radiation scale (FOMIRS): insights from multimethod analysis.","authors":"Lin-Sen Feng, Si-Rong She, Yuan-Yuan Zhang, Jia-Qi Xie, Zheng-Jiao Dong, Ai Tang, Yin-Zhu Li, Xiao-Qian Wu, Qing Yang, Hao-Yu Wang, San-Bin Wang","doi":"10.1186/s13244-025-02018-1","DOIUrl":"10.1186/s13244-025-02018-1","url":null,"abstract":"<p><strong>Objective: </strong>Fear of medical imaging radiation (FOMIR) may influence disease screening willingness; however, no validated tool currently exists to assess FOMIR. This study aimed to develop and validate the Fear of Medical Imaging Radiation Scale (FOMIRS) and explore its psychological mechanisms.</p><p><strong>Methods: </strong>Based on classical test theory, the FOMIRS was developed through semi-structured interviews, grounded theory, and Delphi consultation. A cross-sectional survey with 1509 participants was conducted in Yunnan Province from September to December 2024. Psychometric properties were evaluated using construct validity, convergent validity, discriminant validity, criterion-related validity, content validity, and internal consistency. ROC curve analysis was used to determine the critical thresholds. Logistic regression analysis, network analysis, and structural equation modeling were employed to examine the relationships between the FOMIRS and related variables.</p><p><strong>Results: </strong>The FOMIRS consisted of 18 items organized into a two-dimensional structure. It demonstrated good model fit (Goodness-of-fit index = 0.909, Comparative fit index = 0.949), convergent validity (AVE > 0.45, CR > 0.80), discriminant validity (HTMT = 0.574), criterion-related validity (γ = 0.441), and content validity (S-CVI = 0.889). The FOMIRS also showed excellent internal consistency (Cronbach's α = 0.926 and McDonald's ω = 0.935). Cost-induced refusal of imaging examinations, cancer screening willingness, online learning, imaging radiation cognition, and fear of cancer were identified as influencing factors of FOMIR (p < 0.05). FOMIR serves as a core node in the network, and imaging radiation cognition may affect cancer screening willingness through this mechanism (p < 0.05).</p><p><strong>Conclusion: </strong>FOMIRS accurately measures individual FOMIR levels. It captures the psychological characteristics and behavioral tendencies associated with FOMIR and indicates potential mechanisms.</p><p><strong>Critical relevance statement: </strong>We developed the Fear of Medical Imaging Radiation Scale (FOMIRS), a psychometric tool measuring individuals' fear of medical imaging radiation (FOMIR), demonstrating good reliability, validity, and practical application potential.</p><p><strong>Key points: </strong>Evaluating individuals' FOMIR improves compliance with imaging exams and reduces related cognitive biases. FOMIRS is a reliable and valid tool for measuring FOMIR levels, capturing psychological and behavioral traits, and revealing interactions with external features. FOMIR is a complex phenomenon involving psychological traits, behavioral tendencies, and cognitive biases that affect people's willingness to undergo cancer screening.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"140"},"PeriodicalIF":4.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205105/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511887","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":"Explainable multi-modal radiomics for early prediction of liver metastasis in rectal cancer: a multicentric study.","authors":"Yaru Feng, Jing Gong, Yanyan Wang, Yanfen Cui, Tong Tong","doi":"10.1186/s13244-025-02010-9","DOIUrl":"10.1186/s13244-025-02010-9","url":null,"abstract":"<p><strong>Objectives: </strong>To enhance liver metastasis (LM) risk prediction for rectal cancer (RC) patients using a multi-modal, explainable radiomics model based on rectal MRI and whole-liver CT, and to assess its prognostic value for survival.</p><p><strong>Methods: </strong>This retrospective study enrolled patients with pathologically confirmed RC from two medical centers. Radiomics features were extracted from rectal MRI as well as pre-metastatic liver CT. Feature selection was performed using ANOVA F-value and recursive feature elimination. The SHAP method elucidated the model's functionality by highlighting key feature contributions. Finally, Kaplan-Meier survival analysis and Cox regression assessed the prognostic utility of the model's prediction score.</p><p><strong>Results: </strong>A total of 431 patients were enrolled from two centers in our study. The radiomics model developed from baseline whole-liver CT features alone could predict LM development in all cohorts. A fusion model integrating liver CT with primary tumor MRI features provided synergetic effect and was more efficient in predicting LM, displaying an area under the receiver operating curve (AUC) of 0.85 (95% CI: 0.80-0.90) in the training cohort, and AUC values of 0.75 (95% CI: 0.64-0.86) and 0.73 (95% CI: 0.61-0.85) in the internal and external validation cohorts, respectively. SHAP summary plots illustrated how feature values influenced their impact on the model. The risk score generated by our model demonstrated significant prognostic value for LM-free survival (LMFS).</p><p><strong>Conclusions: </strong>The multi-modal, explainable radiomics model integrating primary tumor and pre-metastatic liver radiomics enhances the prediction of LM development and provides prognostic value in RC patients.</p><p><strong>Critical relevance statement: </strong>This study demonstrates that integrating radiomics features from pre-metastatic liver and primary tumors enhances the predictive performance for liver metastasis development in rectal cancer patients, highlighting its potential for personalized treatment planning and follow-up strategies for rectal cancer patients.</p><p><strong>Key points: </strong>Pre-metastatic liver CT radiomics features could predict the liver metastasis development of rectal cancer. Integrating primary tumor and pre-metastatic liver radiomics improved liver metastasis prediction accuracy. The model demonstrated favorable interpretability through SHAP method.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"142"},"PeriodicalIF":4.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205110/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511888","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}
Liwen Zhu, Ben Zhao, Tianyi Xia, Di Chang, Cong Xia, Mengqiu Liu, Ridong Li, Buyue Cao, Yue Qiu, Yaoyao Yu, Shuwei Zhou, Huayu Chen, Wu Cai, Zhimin Ding, Chunqiang Lu, Tianyu Tang, Yang Song, Yuancheng Wang, Jing Ye, Ying Liu, Shenghong Ju
{"title":"A radiomics-based model for predicting lymph nodes metastasis of pancreatic ductal adenocarcinoma: a multicenter study.","authors":"Liwen Zhu, Ben Zhao, Tianyi Xia, Di Chang, Cong Xia, Mengqiu Liu, Ridong Li, Buyue Cao, Yue Qiu, Yaoyao Yu, Shuwei Zhou, Huayu Chen, Wu Cai, Zhimin Ding, Chunqiang Lu, Tianyu Tang, Yang Song, Yuancheng Wang, Jing Ye, Ying Liu, Shenghong Ju","doi":"10.1186/s13244-025-02025-2","DOIUrl":"10.1186/s13244-025-02025-2","url":null,"abstract":"<p><strong>Purpose: </strong>To develop a radiomics model to predict lymph nodes metastasis (LNM) in patients with pancreatic ductal adenocarcinoma (PDAC) and assess its value for clinical management.</p><p><strong>Methods: </strong>Patients with pathologically confirmed PDAC from four centers were retrospectively enrolled and split into four cohorts: training (n = 192), validation (n = 82), testing (n = 100), and clinical utilization (n = 163). A radiomics model was constructed based on contrast-enhanced CT (CECT) to predict LNM, and its performance was evaluated using the areas under the curve (AUC). Kaplan-Meier analysis was used to assess the prognostic and therapeutic decision-assisting value of the radiomics model.</p><p><strong>Results: </strong>A total of 437 patients (mean age: 63.1 years ± 9.2 standard deviation; 253 men) were included. The radiomics model outperformed other models with AUCs of 0.84, 0.82, and 0.78 in the training, validation, and testing cohorts (all p < 0.05), respectively. LNM predicted by the radiomics model was significantly associated with overall survival (p < 0.001). Kaplan-Meier analysis revealed that patients with a higher risk of LNM also had worse outcomes (all p < 0.05). Additionally, among the high-risk subgroup identified by the radiomics model in the clinical utilization cohort, patients who underwent dissection of ≥ 15 lymph nodes exhibited better overall survival compared to those with fewer lymph nodes dissected (p = 0.002).</p><p><strong>Conclusion: </strong>The radiomics model we constructed demonstrated impressive performance in predicting LNM and prognosis, suggesting its potential for optimizing the clinical management of PDAC.</p><p><strong>Critical relevance statement: </strong>This radiomics model can predict the risk of lymph nodes metastasis and prognosis of patients in pancreatic ductal adenocarcinoma and has potential value in selecting patients who can benefit from different extents of lymph nodes dissection.</p><p><strong>Key points: </strong>Thorough lymph node dissection is important for achieving the best prognosis in pancreatic ductal adenocarcinoma (PDAC). The radiomics model can accurately predict lymph node status and stratify patients' prognosis. This radiomics model enhances the clinical management of PDAC.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"141"},"PeriodicalIF":4.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12204970/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511884","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}
Jingxuan Wang, Xiaowen Zhang, Wei Tang, Marcel van Tuinen, Rozemarijn Vliegenthart, Peter van Ooijen
{"title":"A multi-view CNN model to predict resolving of new lung nodules on follow-up low-dose chest CT.","authors":"Jingxuan Wang, Xiaowen Zhang, Wei Tang, Marcel van Tuinen, Rozemarijn Vliegenthart, Peter van Ooijen","doi":"10.1186/s13244-025-02000-x","DOIUrl":"10.1186/s13244-025-02000-x","url":null,"abstract":"<p><strong>Objective: </strong>New, intermediate-sized nodules in lung cancer screening undergo follow-up CT, but some of these will resolve. We evaluated the performance of a multi-view convolutional neural network (CNN) in distinguishing resolving and non-resolving new, intermediate-sized lung nodules.</p><p><strong>Materials and methods: </strong>This retrospective study utilized data on 344 intermediate-sized nodules (50-500 mm<sup>3</sup>) in 250 participants from the NELSON (Dutch-Belgian Randomized Lung Cancer Screening) trial. We implemented four-fold cross-validation for model training and testing. A multi-view CNN model was developed by combining three two-dimensional (2D) CNN models and one three-dimensional (3D) CNN model. We used 2D, 2.5D, and 3D models for comparison. The models' performance was evaluated using sensitivity, specificity, and area under the ROC curve (AUC). Specificity, indicating what percentage of non-resolving nodules requiring follow-up can be correctly predicted, was maximized.</p><p><strong>Results: </strong>Among all nodules, 18.3% (63) were resolving. The multi-view CNN model achieved an AUC of 0.81, with a mean sensitivity of 0.63 (SD, 0.15) and a mean specificity of 0.93 (SD, 0.02). The model significantly improved performance compared to 2D, 2.5D, or 3D models (p < 0.05). Under the premise of specificity greater than 90% (meaning < 10% of non-resolving nodules are incorrectly identified as resolving), follow-up CT in 14% of individuals could be prevented.</p><p><strong>Conclusion: </strong>The multi-view CNN model achieved high specificity in discriminating new intermediate nodules that would need follow-up CT by identifying non-resolving nodules. After further validation and optimization, this model may assist with decision-making when new intermediate nodules are found in lung cancer screening.</p><p><strong>Critical relevance statement: </strong>The multi-view CNN-based model has the potential to reduce unnecessary follow-up scans when new nodules are detected, aiding radiologists in making earlier, more informed decisions.</p><p><strong>Key points: </strong>Predicting the resolution of new intermediate lung nodules in lung cancer screening CT is a challenge. Our multi-view CNN model showed an AUC of 0.81, a specificity of 0.93, and a sensitivity of 0.63 at the nodule level. The multi-view model demonstrated a significant improvement in AUC compared to the three 2D models, one 2.5D model, and one 3D model.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"138"},"PeriodicalIF":4.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205119/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511883","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}
Qianhe Liu, Jiahui Jiang, Kewei Wu, Yan Zhang, Nan Sun, Jiawen Luo, Te Ba, Aiqing Lv, Chuane Liu, Yiyu Yin, Zhenghan Yang, Hui Xu
{"title":"A two-step automatic identification of contrast phases for abdominal CT images based on residual networks.","authors":"Qianhe Liu, Jiahui Jiang, Kewei Wu, Yan Zhang, Nan Sun, Jiawen Luo, Te Ba, Aiqing Lv, Chuane Liu, Yiyu Yin, Zhenghan Yang, Hui Xu","doi":"10.1186/s13244-025-01995-7","DOIUrl":"10.1186/s13244-025-01995-7","url":null,"abstract":"<p><strong>Objectives: </strong>To develop a deep learning model based on Residual Networks (ResNet) for the automated and accurate identification of contrast phases in abdominal CT images.</p><p><strong>Methods: </strong>A dataset of 1175 abdominal contrast-enhanced CT scans was retrospectively collected for the model development, and another independent dataset of 215 scans from five hospitals was collected for external testing. Each contrast phase was independently annotated by two radiologists. A ResNet-based model was developed to automatically classify phases into the early arterial phase (EAP) or late arterial phase (LAP), portal venous phase (PVP), and delayed phase (DP). Strategy A identified EAP or LAP, PVP, and DP in one step. Strategy B used a two-step approach: first classifying images as arterial phase (AP), PVP, and DP, then further classifying AP images into EAP or LAP. Model performance and strategy comparison were evaluated.</p><p><strong>Results: </strong>In the internal test set, the overall accuracy of the two-step strategy was 98.3% (283/288; p < 0.001), significantly higher than that of the one-step strategy (91.7%, 264/288; p < 0.001). In the external test set, the two-step model achieved an overall accuracy of 99.1% (639/645), with sensitivities of 95.1% (EAP), 99.4% (LAP), 99.5% (PVP), and 99.5% (DP).</p><p><strong>Conclusion: </strong>The proposed two-step ResNet-based model provides highly accurate and robust identification of contrast phases in abdominal CT images, outperforming the conventional one-step strategy.</p><p><strong>Critical relevance statement: </strong>Automated and accurate identification of contrast phases in abdominal CT images provides a robust tool for improving image quality control and establishes a strong foundation for AI-driven applications, particularly those leveraging contrast-enhanced abdominal imaging data.</p><p><strong>Key points: </strong>Accurate identification of contrast phases is crucial in abdominal CT imaging. The two-step ResNet-based model achieved superior accuracy across internal and external datasets. Automated phase classification strengthens imaging quality control and supports precision AI applications.</p>","PeriodicalId":13639,"journal":{"name":"Insights into Imaging","volume":"16 1","pages":"139"},"PeriodicalIF":4.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12204963/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511885","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}