{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:08:55Z","timestamp":1773259735293,"version":"3.50.1"},"reference-count":59,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"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. Genet."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Cervical cancer remains a major global health burden, and accurate pathological classification is essential for personalized treatment planning. However, conventional radiomics studies often rely on manual lesion delineation and are limited in extracting meaningful imaging biomarkers from heterogeneous cervical cancer lesions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We proposed a convolutional recurrent feature extraction (CRFE)-based automatic segmentation framework for cervical cancer MRI images and developed histogram-based imaging features reflecting lesion pixel concentration trends. These features were integrated with conventional radiomics and clinical features. Feature engineering and machine learning classifiers, including random forest (RF), XGBoost, support vector machine, and logistic regression, were evaluated to construct an auxiliary diagnostic model for pathological classification. The dataset included 114 patients with cervical cancer who underwent MRI examinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The CRFE segmentation model achieved an Intersection over Union (IoU) of 0.9443, a Dice coefficient of 0.5980, and an F1-score of 0.7085. Feature selection retained 30 key imaging biomarkers, including the median of the histogram, GLSZM large-area low gray-level emphasis (LoG,\n                      <jats:italic>\u03c3<\/jats:italic>\n                      = 2.0\n                      <jats:italic>mm<\/jats:italic>\n                      , 3D), and GLRLM long-run low gray-level emphasis (LoG,\n                      <jats:italic>\u03c3<\/jats:italic>\n                      = 2.0\n                      <jats:italic>mm<\/jats:italic>\n                      , 3D). Among the evaluated classifiers, the RF model achieved the best performance, with an accuracy of 87.27% and an F1-score of 86.91% in pathological classification.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed deep learning\u2013radiomics framework enables accurate lesion segmentation and effective pathological classification of cervical cancer. This auxiliary diagnostic model may reduce unnecessary invasive procedures and improve early screening and clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fgene.2026.1685927","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T03:32:17Z","timestamp":1773199937000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An auxiliary diagnosis model for the pathological classification of cervical cancer based on radiomics biomarkers"],"prefix":"10.3389","volume":"17","author":[{"given":"Mei","family":"Wang","sequence":"first","affiliation":[{"name":"The First Clinical Medical College, Lanzhou University","place":["Lanzhou, China"]},{"name":"Department of Obstetrics and Gynecology, The First Hospital of Lanzhou University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cao","sequence":"additional","affiliation":[{"name":"The First Clinical Medical College, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"The First Clinical Medical College, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peilin","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Second Clinical Medical College, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Lanzhou Jiaotong University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxiang","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jizhao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junqiang","family":"Lei","sequence":"additional","affiliation":[{"name":"The First Clinical Medical College, Lanzhou University","place":["Lanzhou, China"]},{"name":"Gansu Province Clinical Research Center for Radiology Imaging, The First Hospital of Lanzhou University","place":["Lanzhou, China"]},{"name":"Intelligent Imaging Medical Engineering Research Center of Gansu Province, The First Hospital of Lanzhou University","place":["Lanzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"228","DOI":"10.3390\/electronics11020228","article-title":"Rdpvr: random data partitioning with voting rule for machine learning from class-imbalanced datasets","volume":"11","author":"Ahmad","year":"2022","journal-title":"Electronics"},{"key":"B2","doi-asserted-by":"publisher","first-page":"80151","DOI":"10.1109\/access.2022.3165792","article-title":"Efficient medical diagnosis of human heart diseases using machine learning techniques with and without gridsearchcv","volume":"10","author":"Ahmad","year":"2022","journal-title":"IEEE Access"},{"key":"B3","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/TMI.1983.4307610","article-title":"Comparison of interpolating methods for image resampling","volume":"2","author":"Anthony Parker","year":"2007","journal-title":"IEEE Trans. Medical Imaging"},{"key":"B4","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1148\/radiol.2018172361","article-title":"Radiomics of ct features may be nonreproducible and redundant: influence of ct acquisition parameters","volume":"288","author":"Berenguer","year":"2018","journal-title":"Radiology"},{"key":"B5","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1002\/ijgo.12749","article-title":"Revised figo staging for carcinoma of the cervix uteri","volume":"145","author":"Bhatla","year":"2019","journal-title":"Int. J. Gynecol. and Obstetrics"},{"key":"B7","doi-asserted-by":"publisher","first-page":"3279","DOI":"10.1109\/tkde.2021.3126456","article-title":"A general survey on attention mechanisms in deep learning","volume":"35","author":"Brauwers","year":"2021","journal-title":"IEEE Transactions Knowledge Data Engineering"},{"key":"B8","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1006\/jmps.1999.1279","article-title":"Cross-validation methods","volume":"44","author":"Browne","year":"2000","journal-title":"J. Mathematical Psychology"},{"key":"B9","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res"},{"key":"B10","first-page":"1","article-title":"Xgboost: extreme gradient boosting","volume":"1","author":"Chen","year":"2015","journal-title":"R. Package Version 0.4-2"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1609\/aaai.v30i1.10141","article-title":"Deep contextual networks for neuronal structure segmentation","volume":"30","author":"Chen","year":"2016","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"B12","doi-asserted-by":"publisher","first-page":"60","DOI":"10.11919\/j.issn.1002-0829.218014","article-title":"Relationship between omnibus and post-hoc tests: an investigation of performance of the f test in anova","volume":"30","author":"Chen","year":"2018","journal-title":"Shanghai Archives Psychiatry"},{"key":"B13","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J. Clinical Epidemiology"},{"key":"B14","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s40336-014-0064-0","article-title":"Radiomics in pet: principles and applications","volume":"2","author":"Cook","year":"2014","journal-title":"Clin. Transl. Imaging"},{"key":"B15","doi-asserted-by":"publisher","first-page":"124","DOI":"10.12945\/j.aorta.2016.16.014","article-title":"The mystery of the z-score","volume":"4","author":"Curtis","year":"2016","journal-title":"Aorta"},{"key":"B16","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12863-018-0633-8","article-title":"Using recursive feature elimination in random forest to account for correlated variables in high dimensional data","volume":"19","author":"Darst","year":"2018","journal-title":"BMC Genetics"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2028","DOI":"10.1002\/cncr.11679","article-title":"Imaging in cervical cancer","volume":"98","author":"Follen","year":"2003","journal-title":"Cancer Interdiscip. Int. J. Am. Cancer Soc."},{"key":"B18","doi-asserted-by":"publisher","first-page":"90640","DOI":"10.1109\/access.2019.2927009","article-title":"Image compressive sensing reconstruction based on z-score standardized group sparse representation","volume":"7","author":"Gao","year":"2019","journal-title":"IEEE Access"},{"key":"B19","first-page":"393","article-title":"Investigation on the effect of a gaussian blur in image filtering and segmentation","volume-title":"Proceedings ELMAR-2011","author":"Gedraite","year":"2011"},{"key":"B20","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"B21","first-page":"4218","article-title":"Improving robustness using generated data","volume":"34","author":"Gowal","year":"2021","journal-title":"Adv. Neural Information Processing Systems"},{"key":"B23","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.ygyno.2007.06.026","article-title":"Tumor size is of prognostic value in surgically treated figo stage ii cervical cancer","volume":"107","author":"Horn","year":"2007","journal-title":"Gynecol. Oncology"},{"key":"B24","first-page":"1","article-title":"Efficient hardware architecture of softmax layer in deep neural network","author":"Hu","year":"2018"},{"key":"B25","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.soncn.2017.02.005","article-title":"Cervical cancer: prevention and early detection","volume":"3","author":"Kessler","year":"2017","journal-title":"Semin. Oncology Nursing"},{"key":"B26","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1038\/nrg1471","article-title":"Biological robustness","volume":"5","author":"Kitano","year":"2004","journal-title":"Nat. Rev. Genet."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: the process and the challenges","volume":"30","author":"Kumar","year":"2012","journal-title":"Magn. Resonance Imaging"},{"key":"B28","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: the bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat. Reviews Clin. Oncology"},{"key":"B29","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1109\/TIP.2012.2216279","article-title":"Image-difference prediction: from grayscale to color","volume":"22","author":"Lissner","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"B30","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.ins.2019.07.007","article-title":"Attention-based spatio-temporal dependence learning network","volume":"503","author":"Ma","year":"2019","journal-title":"Inf. Sci."},{"key":"B31","doi-asserted-by":"publisher","first-page":"488","DOI":"10.2967\/jnumed.118.222893","article-title":"Introduction to radiomics","volume":"61","author":"Mayerhoefer","year":"2020","journal-title":"J. Nucl. Med."},{"key":"B32","first-page":"15","article-title":"A review of evaluation metrics in machine learning algorithms","volume-title":"Computer science on-line conference","author":"Naidu","year":"2023"},{"key":"B33","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/s0020-0255(96)00200-9","article-title":"The generalized sigmoid activation function: competitive supervised learning","volume":"99","author":"Narayan","year":"1997","journal-title":"Inf. Sciences"},{"key":"B34","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A review on the attention mechanism of deep learning","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"key":"B35","first-page":"1","article-title":"Segmentation of cervical cancer from mri images: an overview","author":"Oussahi","year":"2024"},{"key":"B36","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/1472-6947-13-72","article-title":"Appraisal of the karnofsky performance status and proposal of a simple algorithmic system for its evaluation","volume":"13","author":"P\u00e9us","year":"2013","journal-title":"BMC Medical Informatics Decision Making"},{"key":"B37","doi-asserted-by":"publisher","first-page":"S540","DOI":"10.1111\/j.1600-0463.2001.tb05811.x","article-title":"Tissue-specific expression pattern of estrogen receptors (er): quantification of er\u03b1 and er\u03b2 mrna with real-time rt-pcr","volume":"109","author":"Pfaffl","year":"2001","journal-title":"Apmis"},{"key":"B38","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1109\/TIP.2012.2221728","article-title":"Image noise level estimation by principal component analysis","volume":"22","author":"Pyatykh","year":"2012","journal-title":"IEEE Transactions Image Processing"},{"key":"B39","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1007\/978-1-4419-9326-7_11","article-title":"Random forest for bioinformatics","volume-title":"Ensemble machine learning","author":"Qi","year":"2012"},{"key":"B40","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1148\/radiology.209.2.9807581","article-title":"Effects of age, breast density, ethnicity, and estrogen replacement therapy on screening mammographic sensitivity and cancer stage at diagnosis: review of 183,134 screening mammograms in albuquerque, new mexico","volume":"209","author":"Rosenberg","year":"1998","journal-title":"Radiology"},{"key":"B41","first-page":"196","article-title":"Color image to grayscale image conversion","author":"Saravanan","year":"2010"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1214\/19-aos1875","article-title":"Nonparametric regression using deep neural networks with ReLU activation function","volume":"48","author":"Schmidt-Hieber","year":"2020","journal-title":"Ann. Statistics"},{"key":"B43","doi-asserted-by":"publisher","first-page":"5164970","DOI":"10.1155\/2022\/5164970","article-title":"Modern diagnostic imaging technique applications and risk factors in the medical field: a review","volume":"2022","author":"Shah","year":"2022","journal-title":"BioMed Research International"},{"key":"B44","first-page":"207","article-title":"Support vector machine","volume-title":"Machine learning models and algorithms for big data classification: thinking with examples for effective learning","author":"Shan","year":"2016"},{"key":"B45","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.1109\/tcsvt.2019.2935128","article-title":"Data augmentation using random image cropping and patching for deep cnns","volume":"30","author":"Takahashi","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"B46","doi-asserted-by":"publisher","first-page":"398","DOI":"10.4997\/JRCPE.2020.409","article-title":"Retrospective studies\u2013utility and caveats","volume":"50","author":"Talari","year":"2020","journal-title":"J. R. Coll. Physicians Edinb."},{"key":"B47","doi-asserted-by":"publisher","first-page":"c810","DOI":"10.1136\/bmj.c810","article-title":"Sex, health, and years of sexually active life gained due to good health: evidence from two us population based cross sectional surveys of ageing","volume":"340","author":"Tessler Lindau","year":"2010","journal-title":"BMJ"},{"key":"B48","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/s00404-011-2155-8","article-title":"Prevalence and risk factors of hpv infection among women from various provinces of the world","volume":"285","author":"Vinodhini","year":"2012","journal-title":"Archives Gynecology Obstetrics"},{"key":"B49","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.3390\/electronics12092103","article-title":"A skin cancer classification method based on discrete wavelet down-sampling feature reconstruction","volume":"12","author":"Wu","year":"2023","journal-title":"Electronics"},{"key":"B22","doi-asserted-by":"publisher","first-page":"19","DOI":"10.7275\/9cms-my97","article-title":"Resampling methods: concepts, applications, and justification","volume":"8","author":"Yu","year":"2002","journal-title":"Pract. Assess. Res. Eval."},{"key":"B50","doi-asserted-by":"publisher","first-page":"e13725","DOI":"10.1002\/acm2.13725","article-title":"Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network","volume":"23","author":"Zabihollahy","year":"2022","journal-title":"J. Appl. Clin. Med. Phys"},{"key":"B51","first-page":"1","article-title":"Improved adam optimizer for deep neural networks","author":"Zhang","year":"2018"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1805.07836","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"Zhang","year":"2018","journal-title":"Adv"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.3934\/mbe.2024054","article-title":"The wuc-adam algorithm based on joint improvement of warmup and cosine annealing algorithms","volume":"21","author":"Zhang","year":"2024","journal-title":"Math. Biosci. Eng."},{"key":"B54","first-page":"851","article-title":"Rethinking dice loss for medical image segmentation","author":"Zhao","year":"2020"},{"key":"B55","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10462-024-10721-6","article-title":"A review of convolutional neural networks in computer vision","volume":"57","author":"Zhao","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"B56","first-page":"547","article-title":"Cross validation framework to choose amongst models and datasets for transfer learning","author":"Zhong","year":"2010"},{"key":"B57","doi-asserted-by":"publisher","first-page":"13001","DOI":"10.1609\/aaai.v34i07.7000","article-title":"Random erasing data augmentation","volume":"34","author":"Zhong","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B58","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.neunet.2020.01.018","article-title":"Theory of deep convolutional neural networks: downsampling","volume":"124","author":"Zhou","year":"2020","journal-title":"Neural Netw."},{"key":"B59","first-page":"3","article-title":"Unet++: a nested u-net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"B60","doi-asserted-by":"publisher","first-page":"2983","DOI":"10.1109\/TIP.2016.2548241","article-title":"Learning contextual dependence with convolutional hierarchical recurrent neural networks","volume":"25","author":"Zuo","year":"2016","journal-title":"IEEE Trans. Image Process."}],"container-title":["Frontiers in Genetics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2026.1685927\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T03:32:22Z","timestamp":1773199942000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2026.1685927\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":59,"alternative-id":["10.3389\/fgene.2026.1685927"],"URL":"https:\/\/doi.org\/10.3389\/fgene.2026.1685927","relation":{},"ISSN":["1664-8021"],"issn-type":[{"value":"1664-8021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]},"article-number":"1685927"}}