{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:47:46Z","timestamp":1791996466249,"version":"4.4.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Insights Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Preoperative prediction of perineural invasion (PNI) in rectal cancer (RC) is challenging due to limited MRI resolution and the neglect of extramural microenvironmental features. We developed a noninvasive framework integrating super-resolution MRI, 2.5D deep learning (DL), and intratumoral-peritumoral radiomics for preoperative PNI prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>A dual-center cohort of 312 RC patients with pathologically confirmed PNI status was analyzed. Preoperative MRI underwent 4\u00d7 super-resolution reconstruction using a generative adversarial network (GAN) to enhance tissue definition. Radiomic features were extracted from the tumor and peritumoral regions (1\u20135\u2009mm). For the 2.5D DL model, the largest tumor cross-section and adjacent axial slices served as multichannel inputs to a ResNet101 backbone using transfer learning. Slice-level features were aggregated to patient-level predictions via multi-instance learning (MIL). Feature selection employed univariate analysis, Pearson correlation, mRMR, and LASSO regression. Model performance was validated via 5-fold cross-validation and an external testing cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The combined model, integrating MIL features, intratumoral radiomics, the optimal (2-mm) peritumoral radiomics, and clinical variables, achieved an area under the curve (AUC) of 0.912 (95% CI: 0.850\u20130.974) on internal validation and 0.868 (95% CI: 0.783\u20130.952) on external testing. Gradient-weighted class activation mapping (Grad-CAM) highlighted the tumor-neural interface, and tumor length was an independent predictor of PNI (OR\u2009=\u20091.062,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.032).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We propose a hybrid radiomic-DL framework leveraging super-resolution MRI and 2.5D spatial context to enhance preoperative prediction of PNI in RC. The model shows potential for risk stratification to support personalized neoadjuvant therapy decisions, with external testing suggesting promising generalizability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>\n                            <jats:bold>Question<\/jats:bold>\n                            How can super-resolution MRI and 2.5D deep learning address the limitations of conventional imaging in predicting preoperative rectal cancer perineural invasion?\n                          <\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>\n                            <jats:bold>Findings<\/jats:bold>\n                            The integrated framework achieved an external testing AUC of 0.868, demonstrating superior performance compared to standalone radiomics and deep learning models.\n                          <\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>\n                            <jats:bold>Critical relevance statement<\/jats:bold>\n                            This study demonstrates a noninvasive framework integrating super-resolution MRI and 2.5D deep learning with intratumoral-peritumoral radiomics, offering a novel approach for preoperative rectal cancer perineural invasion prediction and potential assistance in personalized neoadjuvant therapy decisions.\n                          <\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13244-026-02365-7","type":"journal-article","created":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T17:08:55Z","timestamp":1787418535000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Super-resolution MRI and 2.5D deep learning for intratumoral-peritumoral radiomics in preoperative prediction of rectal cancer perineural invasion"],"prefix":"10.1186","volume":"17","author":[{"given":"Yuhang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dandan","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengming","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apekshya","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuyang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4175-954X","authenticated-orcid":false,"given":"Xiaofu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,22]]},"reference":[{"key":"2365_CR1","doi-asserted-by":"publisher","first-page":"1941","DOI":"10.1002\/ijc.31937","volume":"144","author":"J Ferlay","year":"2019","unstructured":"Ferlay J, Colombet M, Soerjomataram I et al (2019) Estimating the global cancer incidence and mortality in 2018: GLOBOCAN sources and methods. Int J Cancer 144:1941\u20131953","journal-title":"Int J Cancer"},{"key":"2365_CR2","first-page":"17","volume":"73","author":"RL Siegel","year":"2023","unstructured":"Siegel RL, Miller KD, Wagle NS, Jemal A (2023) Cancer statistics, 2023. CA Cancer J Clin 73:17\u201348","journal-title":"CA Cancer J Clin"},{"key":"2365_CR3","first-page":"233","volume":"73","author":"RL Siegel","year":"2023","unstructured":"Siegel RL, Wagle NS, Cercek A et al (2023) Colorectal cancer statistics, 2023. CA Cancer J Clin 73:233\u2013254","journal-title":"CA Cancer J Clin"},{"key":"2365_CR4","doi-asserted-by":"crossref","unstructured":"Edge SB, Compton CC (2010) The American Joint Committee on Cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM. Ann Surg Oncol 17:1471\u20131474","DOI":"10.1245\/s10434-010-0985-4"},{"key":"2365_CR5","doi-asserted-by":"publisher","first-page":"3379","DOI":"10.1002\/cncr.24396","volume":"115","author":"C Liebig","year":"2009","unstructured":"Liebig C, Ayala G, Wilks JA et al (2009) Perineural invasion in cancer: a review of the literature. Cancer 115:3379\u20133391","journal-title":"Cancer"},{"key":"2365_CR6","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.jss.2015.03.101","volume":"199","author":"T Suzuki","year":"2015","unstructured":"Suzuki T, Suwa K, Ogawa M et al (2015) Adjuvant chemotherapy for the perineural invasion of colorectal cancer. J Surg Res 199:84\u201389","journal-title":"J Surg Res"},{"key":"2365_CR7","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1007\/s11605-015-2761-z","volume":"19","author":"Y Yang","year":"2015","unstructured":"Yang Y, Huang X, Sun J et al (2015) Prognostic value of perineural invasion in colorectal cancer: a meta-analysis. J Gastrointest Surg 19:1113\u20131122","journal-title":"J Gastrointest Surg"},{"key":"2365_CR8","first-page":"1","volume":"20","author":"AJ Franke","year":"2021","unstructured":"Franke AJ, Skelton WP, George TJ, Iqbal A (2021) A comprehensive review of randomized clinical trials shaping the landscape of rectal cancer therapy. Clin Colorectal Canc 20:1\u201319","journal-title":"Clin Colorectal Canc"},{"key":"2365_CR9","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1016\/j.suc.2020.02.014","volume":"100","author":"N Wilkinson","year":"2020","unstructured":"Wilkinson N (2020) Management of rectal cancer. Surg Clin North Am 100:615\u2013628","journal-title":"Surg Clin North Am"},{"key":"2365_CR10","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1245\/s10434-009-0796-7","volume":"17","author":"R Lombardi","year":"2010","unstructured":"Lombardi R, Cuicchi D, Pinto C et al (2010) Clinically-staged T3N0 rectal cancer: Is preoperative chemoradiotherapy the optimal treatment? Ann Surg Oncol 17:838\u2013845","journal-title":"Ann Surg Oncol"},{"key":"2365_CR11","doi-asserted-by":"publisher","first-page":"iv263","DOI":"10.1093\/annonc\/mdy161","volume":"29","author":"R Glynne-Jones","year":"2018","unstructured":"Glynne-Jones R, Wyrwicz L, Tiret E et al (2018) Rectal cancer: ESMO clinical practice guidelines for diagnosis, treatment and follow-up. Ann Oncol 29:iv263","journal-title":"Ann Oncol"},{"key":"2365_CR12","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.radonc.2019.01.002","volume":"133","author":"JH Song","year":"2019","unstructured":"Song JH, Yu M, Kang KM et al (2019) Significance of perineural and lymphovascular invasion in locally advanced rectal cancer treated by preoperative chemoradiotherapy and radical surgery: Can perineural invasion be an indication of adjuvant chemotherapy? Radiother Oncol 133:125\u2013131","journal-title":"Radiother Oncol"},{"key":"2365_CR13","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1080\/0284186X.2016.1230274","volume":"55","author":"M Nikberg","year":"2016","unstructured":"Nikberg M, Chabok A, Letocha H et al (2016) Lymphovascular and perineural invasion in stage II rectal cancer: a report from the Swedish colorectal cancer registry. Acta Oncol 55:1418\u20131424","journal-title":"Acta Oncol"},{"key":"2365_CR14","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1097\/COC.0000000000000214","volume":"40","author":"P Chablani","year":"2017","unstructured":"Chablani P, Nguyen P, Pan X et al (2017) Perineural invasion predicts for distant metastasis in locally advanced rectal cancer treated with neoadjuvant chemoradiation and surgery. Am J Clin Oncol 40:561\u2013568","journal-title":"Am J Clin Oncol"},{"key":"2365_CR15","doi-asserted-by":"publisher","first-page":"12159","DOI":"10.3390\/ijms241512159","volume":"24","author":"V Dapr\u00e0","year":"2023","unstructured":"Dapr\u00e0 V, Airoldi M, Bartolini M et al (2023) Total neoadjuvant treatment for locally advanced rectal cancer patients: Where do we stand? Int J Mol Sci 24:12159","journal-title":"Int J Mol Sci"},{"key":"2365_CR16","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1007\/s00261-020-02710-4","volume":"46","author":"J Chen","year":"2021","unstructured":"Chen J, Chen Y, Zheng D et al (2021) Pretreatment MR-based radiomics nomogram as potential imaging biomarker for individualized assessment of perineural invasion status in rectal cancer. Abdom Radiol 46:847\u2013857","journal-title":"Abdom Radiol"},{"key":"2365_CR17","doi-asserted-by":"publisher","first-page":"2233","DOI":"10.3748\/wjg.v30.i16.2233","volume":"30","author":"Y Liu","year":"2024","unstructured":"Liu Y, Sun BJ, Zhang C et al (2024) Preoperative prediction of perineural invasion of rectal cancer based on a magnetic resonance imaging radiomics model: a dual-center study. World J Gastroenterol 30:2233\u20132248","journal-title":"World J Gastroenterol"},{"key":"2365_CR18","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1002\/jmri.28381","volume":"57","author":"C Wong","year":"2023","unstructured":"Wong C, Fu Y, Li M et al (2023) MRI-based artificial intelligence in rectal cancer. J Magn Reson Imaging 57:45\u201356","journal-title":"J Magn Reson Imaging"},{"key":"2365_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2022.102088","volume":"99","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Liao Q, Ding L, Zhang J (2022) Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: an empirical study of 2.5D solutions. Comput Med Imaging Graph 99:102088","journal-title":"Comput Med Imaging Graph"},{"key":"2365_CR20","first-page":"338","volume":"11766","author":"H Zhang","year":"2019","unstructured":"Zhang H, Valcarcel AM, Bakshi R et al (2019) Multiple sclerosis lesion segmentation with Tiramisu and 2.5D stacked slices. Med Image Comput Comput Assist Interv 11766:338\u2013346","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"2365_CR21","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1007\/s00234-022-02902-3","volume":"64","author":"H Takao","year":"2022","unstructured":"Takao H, Amemiya S, Kato S et al (2022) Deep-learning 2.5-dimensional single-shot detector improves the performance of automated detection of brain metastases on contrast-enhanced CT. Neuroradiology 64:1511\u20131518","journal-title":"Neuroradiology"},{"key":"2365_CR22","doi-asserted-by":"publisher","first-page":"273","DOI":"10.21037\/qims-23-846","volume":"14","author":"L Huang","year":"2024","unstructured":"Huang L, Zhao Z, An L et al (2024) 2.5D transfer deep learning model for segmentation of contrast-enhancing lesions on brain magnetic resonance imaging of multiple sclerosis and neuromyelitis optica spectrum disorder. Quant Imaging Med Surg 14:273\u2013290","journal-title":"Quant Imaging Med Surg"},{"key":"2365_CR23","doi-asserted-by":"publisher","first-page":"6359","DOI":"10.1007\/s00330-023-09573-5","volume":"33","author":"Y Xiong","year":"2023","unstructured":"Xiong Y, Guo W, Liang Z et al (2023) Deep learning-based diagnosis of osteoblastic bone metastases and bone islands in computed tomograph images: a multicenter diagnostic study. Eur Radiol 33:6359\u20136368","journal-title":"Eur Radiol"},{"key":"2365_CR24","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1007\/s10278-024-01231-6","volume":"38","author":"Y Wang","year":"2025","unstructured":"Wang Y, Chen A, Wang K et al (2025) Predictive study of machine learning-based multiparametric MRI radiomics nomogram for perineural invasion in rectal cancer: a pilot study. J Imaging Inform Med 38:1224\u20131235","journal-title":"J Imaging Inform Med"},{"key":"2365_CR25","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.828904","volume":"12","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Peng J, Liu J et al (2022) Preoperative prediction of perineural invasion status of rectal cancer based on radiomics nomogram of multiparametric magnetic resonance imaging. Front Oncol 12:828904","journal-title":"Front Oncol"},{"key":"2365_CR26","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-021-00408-4","volume":"21","author":"YS Yang","year":"2021","unstructured":"Yang YS, Qiu YJ, Zheng GH et al (2021) High resolution MRI-based radiomic nomogram in predicting perineural invasion in rectal cancer. Cancer Imaging 21:40","journal-title":"Cancer Imaging"},{"key":"2365_CR27","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-88831-2","volume":"11","author":"Y Guo","year":"2021","unstructured":"Guo Y, Wang Q, Guo Y et al (2021) Preoperative prediction of perineural invasion with multi-modality radiomics in rectal cancer. Sci Rep 11:9429","journal-title":"Sci Rep"},{"key":"2365_CR28","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.humpath.2017.03.027","volume":"65","author":"LS Lino-Silva","year":"2017","unstructured":"Lino-Silva LS, Salcedo-Hern\u00e1ndez RA, Espa\u00f1a-Ferrufino A et al (2017) Extramural perineural invasion in pT3 and pT4 rectal adenocarcinoma as prognostic factor after preoperative chemoradiotherapy. Hum Pathol 65:107\u2013112","journal-title":"Hum Pathol"},{"key":"2365_CR29","doi-asserted-by":"publisher","first-page":"432","DOI":"10.3390\/cancers15020432","volume":"15","author":"V Bourbonne","year":"2023","unstructured":"Bourbonne V, Schick U, Pradier O et al (2023) Radiomics approaches for the prediction of pathological complete response after neoadjuvant treatment in locally advanced rectal cancer: ready for prime time? Cancers 15:432","journal-title":"Cancers"},{"key":"2365_CR30","doi-asserted-by":"publisher","first-page":"7040","DOI":"10.3390\/ijms21197040","volume":"21","author":"FDE De Palma","year":"2020","unstructured":"De Palma FDE, Luglio G, Tropeano FP et al (2020) The role of micro-RNAs and circulating tumor markers as predictors of response to neoadjuvant therapy in locally advanced rectal cancer. Int J Mol Sci 21:7040","journal-title":"Int J Mol Sci"},{"key":"2365_CR31","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.cytogfr.2009.11.001","volume":"21","author":"F Marchesi","year":"2010","unstructured":"Marchesi F, Piemonti L, Mantovani A, Allavena P (2010) Molecular mechanisms of perineural invasion, a forgotten pathway of dissemination and metastasis. Cytokine Growth Factor Rev 21:77\u201382","journal-title":"Cytokine Growth Factor Rev"},{"key":"2365_CR32","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1007\/s13402-023-00901-x","volume":"47","author":"B Han","year":"2024","unstructured":"Han B, Guan X, Ma M et al (2024) Stiffened tumor microenvironment enhances perineural invasion in breast cancer via integrin signaling. Cell Oncol 47:867\u2013882","journal-title":"Cell Oncol"},{"key":"2365_CR33","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1186\/s13046-023-02730-0","volume":"42","author":"X Li","year":"2023","unstructured":"Li X, Wang Y, Zhai Z et al (2023) Predicting response to immunotherapy in gastric cancer via assessing perineural invasion-mediated inflammation in tumor microenvironment. J Exp Clin Cancer Res 42:206","journal-title":"J Exp Clin Cancer Res"},{"key":"2365_CR34","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.mri.2019.05.038","volume":"64","author":"C Zhao","year":"2019","unstructured":"Zhao C, Shao M, Carass A et al (2019) Applications of a deep learning method for anti-aliasing and super-resolution in MRI. Magn Reson Imaging 64:132\u2013141","journal-title":"Magn Reson Imaging"},{"key":"2365_CR35","first-page":"vdad023","volume":"5","author":"S Chakrabarty","year":"2023","unstructured":"Chakrabarty S, LaMontagne P, Shimony J et al (2023) MRI-based classification of IDH mutation and 1p\/19q codeletion status of gliomas using a 2.5D hybrid multi-task convolutional neural network. Neurooncol Adv 5:vdad023","journal-title":"Neurooncol Adv"},{"key":"2365_CR36","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1016\/j.neuroimage.2017.04.041","volume":"170","author":"H Chen","year":"2018","unstructured":"Chen H, Dou Q, Yu L et al (2018) VoxResNet: deep voxelwise residual networks for brain segmentation from 3D MR images. Neuroimage 170:446\u2013455","journal-title":"Neuroimage"},{"key":"2365_CR37","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3390\/bioengineering10020181","volume":"10","author":"A Avesta","year":"2023","unstructured":"Avesta A, Hossain S, Lin M et al (2023) Comparing 3D, 2.5D, and 2D approaches to brain image auto-segmentation. Bioengineering 10:181","journal-title":"Bioengineering"},{"key":"2365_CR38","doi-asserted-by":"publisher","first-page":"5610","DOI":"10.3748\/wjg.v27.i33.5610","volume":"27","author":"M Li","year":"2021","unstructured":"Li M, Jin YM, Zhang YC et al (2021) Radiomics for predicting perineural invasion status in rectal cancer. World J Gastroenterol 27:5610\u20135621","journal-title":"World J Gastroenterol"},{"key":"2365_CR39","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1080\/23808993.2019.1585805","volume":"4","author":"VS Parekh","year":"2019","unstructured":"Parekh VS, Jacobs MA (2019) Deep learning and radiomics in precision medicine. Expert Rev Precis Med Drug Dev 4:59\u201372","journal-title":"Expert Rev Precis Med Drug Dev"}],"container-title":["Insights into Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-026-02365-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13244-026-02365-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-026-02365-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T17:08:58Z","timestamp":1787418538000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13244-026-02365-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2365"],"URL":"https:\/\/doi.org\/10.1186\/s13244-026-02365-7","relation":{},"ISSN":["1869-4101"],"issn-type":[{"value":"1869-4101","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,22]]},"assertion":[{"value":"10 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This retrospective multicohort study was approved by the institutional review Board of the Second Affiliated Hospital of Harbin Medical University (YJSKY2025-086) and Zhuhai People\u2019s Hospital (2025-66). The requirement for written informed consent was waived by the respective institutional review boards due to the retrospective nature of the study.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"205"}}