{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:11:26Z","timestamp":1753891886175,"version":"3.41.2"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Accurate preoperative evaluation of rectal cancer lung metastases (RCLM) is critical for implementing precise medicine. While artificial intelligence (AI) methods have been successful in detecting liver and lymph node metastases using magnetic resonance (MR) images, research on lung metastases is still limited. Utilizing MR images to classify RCLM could potentially reduce ionizing radiation exposure and the costs associated with chest CT in patients without metastases. This study aims to develop and validate a transformer-based deep learning (DL) model based on pelvic MR images, integrated with clinical features, to predict RCLM.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 819 patients with histologically confirmed rectal cancer who underwent preoperative pelvis MRI and carcinoembryonic antigen (CEA) tests were enrolled. Six state-of-the-art DL methods (Resnet18, EfficientNetb0, MobileNet, ShuffleNet, DenseNet, and our transformer-based model) were trained and tested on T2WI and DWI to predict RCLM. The predictive performance was assessed using the receiver operating characteristic (ROC) curve.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our transformer-based DL model achieved impressive results in the independent test set, with an AUC of 83.74% (95% CI, 72.60%-92.83%), a sensitivity of 80.00%, a specificity of 78.79%, and an accuracy of 79.01%. Specifically, for stage T4 and N2 rectal cancer cases, the model achieved AUCs of 96.67% (95% CI, 87.14%-100%, 93.33% sensitivity, 89.04% specificity, 94.74% accuracy), and 96.83% (95% CI, 88.67%-100%, 100% sensitivity, 83.33% specificity, 88.00% accuracy) respectively, in predicting RCLM. Our DL model showed a better predictive performance than other state-of-the-art DL methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The superior performance demonstrates the potential of our work for predicting RCLM, suggesting its potential assistance in personalized treatment and follow-up plans.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2025.1496820","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T05:22:54Z","timestamp":1738819374000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A pelvis MR transformer-based deep learning model for predicting lung metastases risk in patients with rectal cancer"],"prefix":"10.3389","volume":"15","author":[{"given":"Yin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruolin","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongju","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangyou","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhua","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liming","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,2,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21772","article-title":"Colorectal cancer\u00a0statistics, 2023","volume":"73","author":"Siegel","year":"2023","journal-title":"Ca: A Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1097\/CM9.0000000000002108","article-title":"Cancer statistics in China and United States, 2022: profiles, trends, and determinants","volume":"135","author":"Xia","year":"2022","journal-title":"Chin Med J"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1136\/gut.2010.211557","article-title":"Epidemiology, management and prognosis of colorectal cancer with lung metastases: a 30-year population-based study","volume":"59","author":"Mitry","year":"2010","journal-title":"Gut"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2013.10.009","article-title":"Occurrence and survival of synchronous pulmonary metastases in colorectal cancer: a nationwide cohort study","volume":"50","author":"Nordholm-Carstensen","year":"2014","journal-title":"Eur J Cancer"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/s11605-008-0757-7","article-title":"How uncommon are isolated lung metastases in colorectal cancer? A review from database of 754 patients over 4 years","volume":"13","author":"Tan","year":"2009","journal-title":"J Gastrointestinal Surgery"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1634\/theoncologist.2012-0142","article-title":"The role of lung metastasis resection in improving outcome of colorectal cancer patients: results from a large retrospective study","volume":"17","author":"Tampellini","year":"2012","journal-title":"Oncologist"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s12029-016-9818-4","article-title":"Systemic versus local therapies for colorectal cancer pulmonary metastasis: what to choose and when","volume":"47","author":"Ibrahim","year":"2016","journal-title":"J Gastrointestinal Cancer"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s00384-019-03434-8","article-title":"Incidence and prognosis of pulmonary metastasis in colorectal cancer: a population-based study","volume":"35","author":"Ge","year":"2020","journal-title":"Int J Colorectal Disease"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2628","DOI":"10.21037\/jtd-2019-pm-14","article-title":"Pulmonary metastasectomy in colorectal carcinoma","volume":"13","author":"Beckers","year":"2021","journal-title":"J Thorac Disease"},{"key":"B10","doi-asserted-by":"publisher","first-page":"6654","DOI":"10.1038\/s41467-021-26990-6","article-title":"Deep learning for the prediction of early on-treatment response in metastatic colorectal cancer from serial medical imaging","volume":"12","author":"Lu","year":"2021","journal-title":"Nat Commun"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2021.103442","article-title":"Deep learning radiomics-based prediction of distant metastasis in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy: A multicentre study","volume":"69","author":"Liu","year":"2021","journal-title":"Ebiomedicine"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2015.65.9128","article-title":"Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer","volume":"34","author":"Huang","year":"2016","journal-title":"J Clin Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v27.i18.2122","article-title":"Magnetic resonance imaging-based artificial intelligence model in rectal cancer","volume":"27","author":"Wang","year":"2021","journal-title":"World J Gastroenterology"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.222223","article-title":"An MRI deep learning model predicts outcome in rectal cancer","volume":"307","author":"Jiang","year":"2023","journal-title":"Radiology"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-09450-1","article-title":"Prediction of lymph node metastasis in stage T1\u20132 rectal cancers with MRI-based deep learning","volume":"33","author":"Wan","year":"2023","journal-title":"Eur Radiology"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06328-z","article-title":"Rectal cancer: can\u00a0T2WI histogram of the primary tumor help predict the existence of lymph node metastasis","volume":"29","author":"Yang","year":"2019","journal-title":"Eur Radiology"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20180655","article-title":"Diffusion-weighted imaging in rectal cancer: current applications and future perspectives","volume":"92","author":"Schurink","year":"2019","journal-title":"Br J Radiology"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2020.102780","article-title":"Deep learning\u2013based fully automated detection and segmentation of lymph nodes on multiparametric-mri for rectal cancer: A multicentre study","volume":"56","author":"Zhao","year":"2020","journal-title":"Ebiomedicine"},{"key":"B19","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/s43856-023-00282-0","article-title":"Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning","volume":"3","author":"Krogue","year":"2023","journal-title":"Commun Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2020.09.027","article-title":"Artificial intelligence system to determine risk of T1 colorectal cancer metastasis to lymph\u00a0node","volume":"160","author":"Kudo","year":"2021","journal-title":"Gastroenterology"},{"key":"B21","doi-asserted-by":"publisher","first-page":"912","DOI":"10.3348\/kjr.2020.0447","article-title":"Diagnostic performance of deep learning-based lesion detection algorithm in CT for detecting hepatic metastasis from colorectal cancer","volume":"22","author":"Kim","year":"2021","journal-title":"Korean J Radiology"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-020-03686-0","article-title":"Liver imaging features by convolutional neural network to predict the metachronous liver metastasis in stage I-III colorectal cancer patients based on preoperative abdominal CT scan","volume":"21","author":"Lee","year":"2020","journal-title":"BMC Bioinf"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19803-8_33","article-title":"Unimiss: Universal medical self-supervised learning via breaking dimensionality barrier","volume-title":"Computer Vision\u2013ECCV 2022. ECCV 2022. Lecture Notes in Computer Science","author":"Xie","year":"2022"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2013.54.3769","article-title":"Tumor regression grading after preoperative chemoradiotherapy for locally advanced rectal carcinoma revisited: updated results of the CAO\/ARO\/AIO-94 trial","volume":"32","author":"Fokas","year":"2014","journal-title":"J Clin Oncol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans On Med Imaging"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1783","article-title":"Sample sizes for clinical trials with normal data","volume":"23","author":"Julious","year":"2004","journal-title":"Stat Med"},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1145\/3450439.3451868","volume-title":"Predictive models for colorectal cancer recurrence using multi-modal healthcare data.","author":"Ho","year":"2021"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13045-019-0702-0","article-title":"Expert consensus on multidisciplinary therapy of colorectal cancer with lung metastases","volume":"12","author":"Li","year":"2019","journal-title":"J Hematol \\& Oncol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.2940","article-title":"Classic models for dynamic contrast-enhanced MRI","volume":"26","author":"Sourbron","year":"2013","journal-title":"Nmr Biomedicine"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v28.i1.108","article-title":"Artificial intelligence in the diagnosis and management of colorectal cancer liver metastases","volume":"28","author":"Rompianesi","year":"2022","journal-title":"World J Gastroenterology"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180014","article-title":"Deep learning for automated segmentation of liver lesions at CT in patients with colorectal cancer liver metastases","volume":"1","author":"Vorontsov","year":"2019","journal-title":"Radiology: Artif Intelligence"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.3957","article-title":"Development and validation of MRI-based deep learning models for prediction of microsatellite instability in rectal cancer","volume":"10","author":"Zhang","year":"2021","journal-title":"Cancer Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"874","DOI":"10.6004\/jnccn.2018.0061","article-title":"NCCN clinical practice guidelines in oncology","volume":"16","author":"Benson","year":"2018","journal-title":"J Natl Compr Cancer Network"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11092599","article-title":"Lymph nodes evaluation in rectal cancer: where do we stand and future perspective","volume":"11","author":"Borgheresi","year":"2022","journal-title":"J Clin Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/s12149-021-01580-0","article-title":"FDG PET\/MRI in rectal cancer","volume":"35","author":"Crimi","year":"2021","journal-title":"Ann Nucl Med"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1496820\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T05:22:57Z","timestamp":1738819377000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1496820\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,6]]},"references-count":35,"alternative-id":["10.3389\/fonc.2025.1496820"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1496820","relation":{},"ISSN":["2234-943X"],"issn-type":[{"type":"electronic","value":"2234-943X"}],"subject":[],"published":{"date-parts":[[2025,2,6]]},"article-number":"1496820"}}