{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T22:15:36Z","timestamp":1792188936737,"version":"4.4.0"},"reference-count":30,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T00:00:00Z","timestamp":1776556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Carcinoembryonic antigen (CEA) is widely used in colon cancer management; however, its diagnostic and prognostic accuracy is limited by biological variability, as well as false-positive or false-negative results. Radiomics provides quantitative descriptors of tumor heterogeneity and offers objective assessment of tumor characteristics. This study aimed to evaluate the potential of computed tomography (CT)-based radiomic features to distinguish between CEA-positive and CEA-negative colon cancer patients. Methods: In this retrospective study, 150 patients with histopathologically confirmed colon cancer were screened, and 109 were eligible after image-quality assessment (53 CEA-positive, 56 CEA-negative). A total of 107 radiomic features were extracted from preoperative contrast-enhanced CT images. After z-score normalization, feature robustness was assessed using intra- and inter-observer agreement. Correlation-based feature selection (|\u03c1| \u2265 0.7) was applied. Five machine-learning classifiers\u2014Support Vector Machine (SVM), Decision Tree, Ensemble, k-Nearest Neighbor (k-NN), and Neural Network (NN)\u2014were trained using stratified 5-fold cross-validation. Performance was evaluated using accuracy, recall, specificity, F1-score, and ROC-AUC. Results: The best performance was obtained with 41 selected features. The k-NN classifier achieved the highest accuracy (77.4 \u00b1 2%) and ROC-AUC (0.8523 \u00b1 0.013), while SVM and NN achieved the highest recall (83.0 \u00b1 0.3). These models showed balanced and robust performance in distinguishing CEA-positive from CEA-negative patients. Conclusions: CT-based radiomic analysis combined with machine learning\u2014particularly k-NN, SVM, and neural network classifiers\u2014showed promising performance in differentiating colon cancer patients according to serum CEA status. Radiomic features may provide imaging-based information associated with serum biomarkers such as CEA, potentially enhancing tumor characterization and supporting more personalized decision-making.<\/jats:p>","DOI":"10.3390\/diagnostics16081221","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T07:15:08Z","timestamp":1776669308000},"page":"1221","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CT-Based Radiomic Signatures Associated with Serum CEA Status in Colon Cancer"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0792-9042","authenticated-orcid":false,"given":"Demet","family":"Do\u011fan","sequence":"first","affiliation":[{"name":"Department of Radiology, Faculty of Medicine, \u0130stanbul Okan University, 34947 \u0130stanbul, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7116-2734","authenticated-orcid":false,"given":"Co\u015fku","family":"\u00d6ks\u00fcz","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Izmir Bakircay University, 35665 Izmir, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6565-9488","authenticated-orcid":false,"given":"\u00d6zg\u00fcr","family":"\u00c7ak\u0131r","sequence":"additional","affiliation":[{"name":"Department of Radiology, Faculty of Medicine, Kocaeli University, 41001 Kocaeli, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"O\u011fuzhan","family":"Urhan","sequence":"additional","affiliation":[{"name":"Department of Electronics & Telecommunication Engineering, Kocaeli University, 41001 Kocaeli, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,19]]},"reference":[{"key":"ref_1","unstructured":"International Agency for Research on Cancer (IARC) (2025). Colorectal Cancer Awareness Month 2025, IARC."},{"key":"ref_2","unstructured":"World Health Organization (2023). Colorectal Cancer Fact Sheet, WHO."},{"key":"ref_3","unstructured":"World Health Organization (2024). Global Cancer Burden Data, WHO."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Niedzielska, J., and Jastrz\u0119bski, T. (2025). Carcinoembryonic Antigen (CEA): Origin, Role in Oncology, and Concentrations in Serum and Peritoneal Fluid. J. Clin. Medicine., 14.","DOI":"10.3390\/jcm14093189"},{"key":"ref_5","unstructured":"Kankanala, V.L., Zubair, M., and Mukkamalla, S.K.R. (2024, December 11). Carcinoembryonic Antigen, StatPearls, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK578172\/."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"294","DOI":"10.3393\/ac.2019.11.13","article-title":"A Review of the Role of Carcinoembryonic Antigen in Clinical Practice","volume":"35","author":"Hall","year":"2019","journal-title":"Ann. Coloproctol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e084219","DOI":"10.1136\/bmjopen-2024-084219","article-title":"Grading carcinoembryonic antigen levels can enhance the effectiveness of prognostic stratification in patients with colorectal cancer: A single-centre retrospective study","volume":"14","author":"Xie","year":"2024","journal-title":"BMJ Open"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1111\/j.1463-1318.2008.01591.x","article-title":"Comparison of carcinoembryonic antigen prognostic value in serum and tumour tissue of patients with colorectal cancer","volume":"11","author":"Li","year":"2009","journal-title":"Color. Dis."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1016\/j.ejca.2007.03.021","article-title":"Tumour markers in colorectal cancer: European Group on Tumour Markers (EGTM) guidelines for clinical use","volume":"43","author":"Duffy","year":"2007","journal-title":"Eur. J. Cancer"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"96","DOI":"10.5152\/eurasianjmed.2018.17093","article-title":"Evaluation of the Relationship between Carcinoembryonic Antigen and TNM Stage in Colorectal Cancer","volume":"50","author":"Topdagi","year":"2018","journal-title":"Eurasian J. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"653","DOI":"10.6004\/jnccn.2021.7101","article-title":"Current surveillance after treatment is not sufficient for patients with rectal cancer with negative baseline CEA","volume":"20","author":"Shen","year":"2022","journal-title":"J. Natl. Compr. Canc Netw."},{"key":"ref_12","first-page":"CD011134","article-title":"Blood CEA levels for detecting recurrent colorectal cancer","volume":"2015","author":"Nicholson","year":"2015","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1296","DOI":"10.1007\/s11547-021-01389-x","article-title":"A deep look into radiomics","volume":"126","author":"Scapicchio","year":"2021","journal-title":"Radiol. Med."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Fan, S., Cui, X., Liu, C., Li, X., Zheng, L., Song, Q., Qi, J., Ma, W., and Ye, Z. (2021). CT-based radiomics signature: A potential biomarker for predicting postoperative recurrence risk in stage II colorectal cancer. Front. Oncol., 11.","DOI":"10.3389\/fonc.2021.644933"},{"key":"ref_15","first-page":"e95","article-title":"Radiomics for the prediction of treatment outcome and long-term outcome in colorectal cancer","volume":"20","author":"Staal","year":"2021","journal-title":"Clin. Color. Cancer"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2888","DOI":"10.3748\/wjg.v29.i19.2888","article-title":"Radiomics in colorectal cancer patients","volume":"29","author":"Inchingolo","year":"2023","journal-title":"World J. Gastroenterol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gopika, N., and AMeena Kowshalaya, M.E. (2018, January 15\u201316). Correlation Based Feature Selection Algorithm for Machine Learning. Proceedings of the 2018 3rd International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India.","DOI":"10.1109\/CESYS.2018.8723980"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1007\/s11277-019-06504-w","article-title":"Correlation based feature selection algorithms for varying datasets of different dimensionality","volume":"108","author":"Kowshalya","year":"2019","journal-title":"Wirel. Pers. Commun."},{"key":"ref_19","unstructured":"Wu, J., Toscano-Palmerin, S., Frazier, P.I., and Wilson, A.G. (2019). Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Guo, T., Cheng, B., Li, Y., Li, Y., Chen, S., Lian, G., Li, J., Gao, M., Huang, K., and Huang, Y. (2024). A radiomics model for predicting perineural invasion in stage II-III colon cancer based on computed tomography. BMC Cancer, 24.","DOI":"10.1186\/s12885-024-12951-x"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Montagnon, E., Cerny, M., Hamilton, V., Derennes, T., Ilinca, A., Elforaici, M.E.A., Jabbour, G., Rafie, E., Wu, A., and Perdigon Romero, F. (2024). Radiomics analysis of baseline computed tomography to predict oncological outcomes in patients treated for resectable colorectal cancer liver metastasis. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0307815"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"40","DOI":"10.21147\/j.issn.1000-9604.2018.01.05","article-title":"Individualized prediction of perineural invasion in colorectal cancer: Development and validation of a radiomics prediction model","volume":"30","author":"Huang","year":"2018","journal-title":"Chin. J. Cancer Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1186\/s12967-022-03262-5","article-title":"Radiomic analysis for predicting prognosis of colorectal cancer from preoperative 18F-FDG PET\/CT","volume":"20","author":"Lv","year":"2022","journal-title":"J. Transl. Med."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Safakish, A., Sannachi, L., DiCenzo, D., Kolios, C., Pejovi\u0107-Mili\u0107, A., and Czarnota, G.J. (2023). Predicting head and neck cancer treatment outcomes with pre-treatment quantitative ultrasound texture features and optimising machine learning classifiers with texture-of-texture features. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.1258970"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Quiaoit, K., DiCenzo, D., Fatima, K., Bhardwaj, D., Sannachi, L., Gangeh, M., Sadeghi-Naini, A., Dasgupta, A., Kolios, M.C., and Trudeau, M. (2020). Quantitative ultrasound radiomics for therapy response monitoring in patients with locally advanced breast cancer: Multi-institutional study results. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0236182"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"13745","DOI":"10.1038\/s41598-023-40906-y","article-title":"Advancing prostate cancer detection: A comparative analysis of PCLDA-SVM and PCLDA-KNN classifiers for enhanced diagnostic accuracy","volume":"13","author":"Dubey","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"42","DOI":"10.14445\/22315381\/IJETT-V70I12P206","article-title":"Prostate Cancer Detection using Radiomics-based Feature Analysis with ML Algorithms and MR Images","volume":"70","author":"Rajesh","year":"2022","journal-title":"Int. J. Eng. Trends Technol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Parmar, C., Grossmann, P., Rietveld, D., Rietbergen, M.M., Lambin, P., and Aerts, H.J.W.L. (2015). Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer. Front. Oncol., 5.","DOI":"10.3389\/fonc.2015.00272"},{"key":"ref_29","doi-asserted-by":"crossref","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. Rev. Clin. Oncol."},{"key":"ref_30","first-page":"366","article-title":"Exploring radiomics research quality scoring tools: A comparative analysis of METRICS and RQS","volume":"30","author":"Cuocolo","year":"2024","journal-title":"Diagn. Interv. Radiol."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1221\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T07:34:40Z","timestamp":1776670480000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1221"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,19]]},"references-count":30,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["diagnostics16081221"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16081221","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,19]]}}}