Radiology. Imaging cancer最新文献

{"title":"Robotic Needle Insertion for CT-guided Percutaneous Biopsy of Thoracoabdominal Lesions: A Prospective Multicenter Randomized Trial.","authors":"Haozhe Huang, Chao Chen, Ying Wang, Lichao Xu, Hua Jiang, Hui Zeng, Wentao Li","doi":"10.1148/rycan.260054","DOIUrl":"10.1148/rycan.260054","url":null,"abstract":"<p><p>Purpose To compare safety and feasibility between a novel CT-guided robotic system and the conventional freehand technique for puncture biopsy of thoracoabdominal lesions. Materials and Methods In this prospective multicenter randomized trial, individuals with suspected lesions were enrolled between July 2023 and April 2024 across three university teaching hospitals and randomized to the robot-assisted group (<i>n</i> = 82) or the freehand group (<i>n</i> = 83). Procedure outcomes included the technical success rate, targeting error, number of CT scans and needle adjustments, puncture time, and complications. Descriptive and inferential statistics were calculated. Results A total of 165 participants (mean age, 60 years ± 10 [SD]; 83 male) were included. Compared with the freehand group, the robot-assisted group demonstrated a higher technical success rate (97.56% [80 of 82] vs 62.65% [52 of 83], <i>P</i> < .001), lower targeting error (mean Euclidean deviation: 1.7 mm ± 1.1 vs 4.5 mm ± 3.9, <i>P</i> < .001), and fewer CT scans (mean, 4.3 ± 1.9 vs 5.2 ± 2.3; <i>P</i> = .002) and needle adjustments (mean, 0.7 ± 0.7 vs 1.6 ± 1.6; <i>P</i> = .003). Despite differences in geometric precision, both groups achieved 100% (82 of 82 and 83 of 83) diagnostic yield. The median puncture time was comparable between groups (5.5 minutes ± 4.3 vs 4.8 minutes ± 7.0, <i>P</i> = .50). During lung biopsies, the robot-assisted approach yielded fewer complications compared with the freehand approach (4.88% [four of 82] vs 16.87% [14 of 83], <i>P</i> = .014). Conclusion Compared with the freehand approach, robot-assisted biopsy yielded greater precision and reduced adjustments and complications while demonstrating noninferior diagnostic efficacy and comparable duration. <b>Keywords:</b> Robotic Needle Insertion, Biopsy, Thoracoabdominal Lesions, Robot-assisted Biopsy, CT-guided Intervention, Percutaneous Needle Biopsy, Randomized Controlled Trial, Algorithm Development, CT, Clinical Testing, Interventional-Body, Biopsy/Needle Aspiration, Percutaneous, Thorax, Abdomen/GI, Liver, Lung, Kidney ©RSNA, 2026.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e260054"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620318/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148892429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can Spectral CT Complement Biopsy for MSI/dMMR Assessment in Esophagogastric Junction Adenocarcinoma?","authors":"Ramiro J Méndez, Ángel Nava","doi":"10.1148/rycan.260534","DOIUrl":"10.1148/rycan.260534","url":null,"abstract":"","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e260534"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620321/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149040469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MR Virtual Cytometry for Zone-specific Prostate Cancer Characterization with Histologic and Molecular Validation.","authors":"Jie Lu, Hao Cheng, Haotian Li, Kuiyuan Liu, Haoan Xu, Ruicheng Ba, Ming Liu, Wei Zhang, Hui Zhu, Min Chen, Chunmei Li, Dan Wu","doi":"10.1148/rycan.250662","DOIUrl":"10.1148/rycan.250662","url":null,"abstract":"<p><p>Purpose To evaluate time-dependent diffusion MRI (<i>t_d</i>-dMRI)-based virtual cytometry for characterizing prostatic lesions and assess its zone-specific diagnostic value. Materials and Methods In this prospective study, participants with clinical suspicion of PCa were enrolled between March 2023 and August 2024 for <i>t_d</i>-dMRI. By modeling prostate tissue as intra- and extracellular compartments, microstructural features, including intracellular volume fraction, cell diameter, cellularity, and transmembrane water exchange time, were estimated. Diagnostic performance was analyzed using a generalized linear mixed model to account for multiple lesions per participant. Validation included correlations with whole-slide histologic examination as the reference standard (<i>n</i> = 36) and prostate-specific membrane antigen (PSMA) PET (<i>n</i> = 27). Results A total of 117 male participants (mean age, 70.0 years ± 6.8 [SD]) contributing 199 lesions were analyzed. PCa showed elevated intracellular volume fraction, cellularity, and accelerated transmembrane water exchange compared with benign lesions (adjusted <i>P</i> < .05). Higher Gleason grades were associated with further increases in these parameters (odds ratio, 2.62, 2.43, and 0.62, respectively; <i>P</i> < .05). Zone-specific features included higher intracellular water diffusivity in the peripheral zone and smaller cell size in the transition zone (TZ) (all adjusted <i>P</i> < .05). The <i>t_d</i>-dMRI-derived cellularity index demonstrated the highest performance for discriminating PCa from benign lesions, particularly in the TZ (area under the receiver operating characteristic curve, 0.94), which improved to 0.96 when combined with the Prostate Imaging Reporting and Data System. Validation showed strong correlations with histopathologic examination (cancer only <i>r</i> = 0.81, <i>P</i> < .001) and PSMA PET (<i>r</i> = 0.74, <i>P</i> < .05). Conclusion In this study, <i>t_d</i>-dMRI-based MR virtual cytometry enabled quantitative characterization of cellular microstructure in prostate disease and improved diagnostic performance, particularly in the TZ. <b>Keywords:</b> MR-Diffusion-weighted Imaging, PET, Prostate, Tissue Characterization, Modeling <i>Supplemental material is available for this article.</i> © RSNA, 2026.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e250662"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620325/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148991224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pixels to Prognosis: Translating Synthetic MRI Radiomics into Clinical Practice for Human Epidermal Growth Factor Receptor 2-Positive Breast Cancer.","authors":"Chunhong Hu","doi":"10.1148/rycan.260448","DOIUrl":"10.1148/rycan.260448","url":null,"abstract":"","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e260448"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620472/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incremental Value of Synthetic MRI Radiomics in Predicting Neoadjuvant Response in Human Epidermal Growth Factor Receptor 2-Positive Breast Cancer.","authors":"Siyi Chen, Yongxin Chen, Chen Jin, Bingjie Zheng, Shishen Ding, Zijin Weng, Wenjie Tang, Weifeng Liu, Yihong Lin, Qingcong Kong, Qianwei Zhou, Yuan Guo","doi":"10.1148/rycan.250758","DOIUrl":"10.1148/rycan.250758","url":null,"abstract":"<p><p>Purpose To evaluate the added value of a synthetic radiomics model (S-Radiomics) that integrates topologic and Hessian-based features with traditional radiomic features for predicting a pathologic complete response (pCR) in human epidermal growth factor receptor 2 (HER2)-positive breast cancer. Materials and Methods Patients with HER2-positive breast cancer from three centers were retrospectively included between January 2018 and January 2024. Patients from centers 1 and 2 (<i>n</i> = 201) were randomly assigned to training (<i>n</i> = 150) and internal testing (<i>n</i> = 51) sets, whereas patients from center 3 (<i>n</i> = 82) constituted external testing set I. An additional genomic set (<i>n</i> = 64, I-SPY 2) and external testing set II (<i>n</i> = 57, I-SPY 1) were used for independent validation. Multivariable logistic regression with all clinical variables was used to identify independent predictors (<i>P</i> < .05) and develop the clinical model, adjusting for potential confounders. Traditional radiomics model (T-Radiomics) and S-Radiomics were constructed. Performance was evaluated using area under the receiver operating characteristic curve (AUC), integrated discrimination improvement, net reclassification index, and survival analysis. Results A total of 404 female patients with HER2-positive breast cancer (mean age ± SD, 50 years ± 9) were included. The S-Radiomics outperformed the T-Radiomics on both the internal (AUC, 0.86 vs 0.78; <i>P</i> = .37) and external test (AUC, 0.84 vs 0.73; <i>P</i> = .11) sets, with improvements in the integrated discrimination improvement (<i>P</i> = .24 and .01) and net reclassification index (<i>P</i> = .21 and .01). Shapley additive explanations analysis revealed topologic features as the most important predictors. For center 1, survival analysis revealed longer disease-free survival in predicted responders (<i>P</i> = .02). Conclusion The S-Radiomics outperformed the T-Radiomics in predicting pathologic complete responses in patients with HER2-positive breast cancer. <b>Keywords:</b> Radiogenomics, MRI, Breast, Human Epidermal Growth Factor Receptor 2, Breast Cancer, Neoadjuvant Chemotherapy, Pathologic Complete Response, Radiomics <i>Supplemental material is available for this article.</i> © RSNA, 2026.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e250758"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620322/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148762362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectral CT-based Nomogram for Noninvasive Assessment and Prognostic Prediction of MSI/dMMR in Esophagogastric Junction Adenocarcinoma.","authors":"Yinchen Wu, Kaihe Lin, Na Lin, Yu Lin, Xinyao Huang, Mi Wang, Dejun She, Dairong Cao","doi":"10.1148/rycan.250654","DOIUrl":"10.1148/rycan.250654","url":null,"abstract":"<p><p>Purpose To establish and evaluate a nomogram based on quantitative spectral CT parameters for predicting microsatellite instability (MSI) and deficient mismatch repair (dMMR) status in patients with esophagogastric junction adenocarcinoma (EGJA). Materials and Methods In this study including retrospective and prospective datasets (enrollment period: May 2021 to January 2026), patients from two centers were divided into training, validation, external test, prospective test, and neoadjuvant chemotherapy cohorts. A nomogram was constructed integrating clinical characteristics with quantitative spectral CT parameters. Model efficacy in predicting MSI/dMMR and its associations with disease-free survival were evaluated. Primary statistical methods included logistic and Cox regression analyses. Results In total, 511 patients (median age, 67 years [IQR, 60-73 years]; 333 male) were included. The nomogram incorporated sex, clinical N stage, CT attenuation on 40-keV virtual monoenergetic images, and normalized iodine density during the venous phase. It achieved areas under the receiver operating characteristic curve of 0.87 (95% CI: 0.81, 0.93), 0.87 (95% CI: 0.78, 0.96), 0.91 (95% CI: 0.83, 0.99), 0.89 (95% CI: 0.80, 0.98), and 0.86 (95% CI: 0.76, 0.96) across the five respective cohorts: training, validation, external test, prospective test, and neoadjuvant chemotherapy. In the external test cohort, the nomogram correctly identified 9.76% (four of 41) of the patients misclassified with preoperative biopsy. Furthermore, it stratified patients into distinct disease-free survival risk groups in the training (hazard ratio, 2.04 [95% CI: 1.35, 3.09]; <i>P</i> < .001) and validation (hazard ratio, 2.97 [95% CI: 1.46, 6.05]; <i>P</i> = .003) cohorts. Conclusion The spectral CT-based nomogram enabled preoperative prediction of MSI/dMMR status and prognostic assessment in patients with EGJA. <b>Keywords:</b> Esophagogastric Junction Adenocarcinoma, Spectral CT, Nomogram, Primary Neoplasms, CT-Spectral, Neoplasms-Primary, Pathology, Tumor Immune Microenvironment, Pre-clinical Models Chinese Clinical Trial Registry identifier nos. ChiCTR2500097335 and ChiCTR2500101639 <i>Supplemental material is available for this article.</i> © The Author(s) 2026. Published by the Radiological Society of North America under a CC BY 4.0 license.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e250654"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620324/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148892343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectral CT and Photon-counting Detector CT: Principles and Applications in Neuroradiology.","authors":"Jennifer C Hayes, Ashok Srinivasan, Jayapalli Rajiv Bapuraj","doi":"10.1148/rycan.250506","DOIUrl":"10.1148/rycan.250506","url":null,"abstract":"<p><p>Spectral CT and photon-counting detector (PCD) CT are recent innovations in imaging that have gained increasing use as diagnostic tools. Both modalities leverage advanced detector technologies-PCD CT uses detectors that count individual x-ray photons and measure their energies, while spectral CT separates x-ray energies at dual or multiple levels. These approaches provide higher spatial resolution, improved contrast-to-noise ratio, and reduced noise and enable multienergy imaging from a single acquisition. These techniques enhance visualization of tissue characteristics and reduce artifacts compared with conventional energy-integrating detector CT. This review article introduces the fundamental principles of spectral CT and PCD CT, their advantages in neuro-oncologic applications, and their potential to improve diagnostic imaging through enhanced image quality and quantitative accuracy. <b>Keywords:</b> Physics, CT-Photon-counting, Pediatrics, CT-Spectral © RSNA, 2026.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e250506"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620471/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148685585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Percutaneous Cryoablation Versus Microwave Ablation for Hepatocellular Carcinoma: Comparative Study of Safety and Oncologic Outcomes.","authors":"David-Dimitris Chlorogiannis, Sharath K Bhagavatula, Stuart G Silverman, Borna E Dabiri, Kemal Tuncali, Vincent M Levesque, Ravi V Gottumukkala, Zhou Lan, Paul B Shyn","doi":"10.1148/rycan.250442","DOIUrl":"10.1148/rycan.250442","url":null,"abstract":"<p><p>Purpose To compare safety and oncologic outcomes of percutaneous image-guided hepatic cryoablation and microwave ablation (MWA) for treating hepatocellular carcinoma (HCC). Materials and Methods This single center, retrospective study evaluated percutaneous image-guided cryoablation and MWA procedures in patients with HCC from December 2015 to December 2023. Adverse events (AEs) were recorded per procedure. Technical success and local tumor progression-free survival were assessed per tumor and compared after propensity score matching. Intrahepatic progression-free survival, extrahepatic progression-free survival, and overall survival were measured per patient when cryoablation or MWA was used as the initial curative-intent treatment for early-stage HCC. Survival metrics were estimated using Kaplan-Meier curves and compared using log-rank testing. Results A total of 176 ablation procedures in 123 patients with 228 HCCs enabled three cohort analyses (mean age ± SD, 69 years ± 9; 85 male). Per-procedure AE analysis of 170 procedures (69 cryoablation and 101 MWA) showed no evidence of differences in overall or major AE rates (cryoablation: overall AEs, 19%, major AEs, 1%; MWA: overall AEs, 10%, major AEs, 3%; <i>P</i> = .60). After propensity score matching, 158 HCC tumors were studied (79 cryoablation and 79 MWA): technical success for both modalities was 97% (<i>P</i> = .96); 3-year per-tumor local tumor progression-free survival rates were 57% for cryoablation and 58% for MWA (<i>P</i> = .53). Per-patient analysis of 51 patients with early-stage HCC (17 cryoablation and 34 MWA) yielded 1-year intrahepatic progression-free survival, extrahepatic progression-free survival, and overall survival rates of 82%, 88%, and 100% for cryoablation and 73%, 94%, and 88% for MWA, respectively, without evidence of a difference in any survival outcome (<i>P</i> = .76). Conclusion Percutaneous cryoablation and MWA demonstrated similar favorable safety and oncologic outcomes for initial treatment of HCC. <b>Keywords:</b> Comparative Studies, Ablation Techniques, CT, Interventional-Oncology, Abdomen/GI, Liver © RSNA, 2026.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e250442"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620330/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148945591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusion-weighted Imaging and ADC Mapping for Early Prediction of Pathologic Complete Response in Breast Cancer.","authors":"Pratiksha Yadav","doi":"10.1148/rycan.260464","DOIUrl":"10.1148/rycan.260464","url":null,"abstract":"","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e260464"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148945585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Vision Transformer- and Radiomics-based Model for Predicting Liver Metastasis-Free Survival in Patients with Rectal Cancer.","authors":"Zhuofu Li, Chao Sun, Xiaoxuan Wang, Song Tian, Zhaoxiang Ye","doi":"10.1148/rycan.250440","DOIUrl":"10.1148/rycan.250440","url":null,"abstract":"<p><p>Purpose To develop and validate a multimodal random survival forest (RSF) model integrating three-dimensional vision transformer (ViT-3D) architecture, radiomic features, and clinical variables derived from rectal MR images to predict liver metastasis-free survival (LMFS) in patients with rectal cancer (RC). Materials and Methods This retrospective study included patients with pathologically confirmed RC treated at three institutions from January 2019 to December 2022. A multimodal RSF model (RSF-combined) incorporating ViT-3D-derived deep learning features, radiomic features, and clinical variables was developed. Comparator RSF, extreme gradient boosting, and Cox proportional hazards models using clinical and MRI-derived data were also constructed. Model performance was evaluated using time-dependent receiver operating characteristic analysis. Model interpretability was assessed using Shapley additive explanations analysis to quantify feature contributions to individual risk predictions. Results A total of 548 patients with RC (mean age ± SD, 61.68 years ± 9.93; 356 males) were included (404 for training, 144 for testing). The RSF-combined model outperformed Cox and extreme gradient boosting models in LMFS prediction across all time points, achieving area under the receiver operating characteristic curve values of 0.72, 0.78, and 0.73 at 1, 3, and 5 years, respectively, in the external test set. Shapley additive explanations summary plots demonstrated how individual feature values dynamically influenced predicted LMFS risk. Risk stratification based on the optimal cutoff and the median RSF-combined risk score yielded significant separation of LMFS curves (log-rank test, hazard ratio: 2.09 [95% CI: 1.20, 3.27], <i>P</i> = .002, and hazard ratio: 1.92 [95% CI: 1.13, 3.25], <i>P</i> = .02, respectively). Conclusion A multimodal RSF-combined model integrating deep learning, radiomic, and clinical features enabled accurate, individualized prediction of postoperative LMFS in patients with RC. <b>Keywords:</b> Deep Learning, Liver Metastasis, Liver Metastasis-Free Survival, MRI, Radiomics, Rectal Cancer <i>Supplemental material is available for this article.</i> © RSNA, 2026.</p>","PeriodicalId":20786,"journal":{"name":"Radiology. Imaging cancer","volume":"8 5","pages":"e250440"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620317/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148991211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}