What question did this study set out to answer?

This study aims to assess the ability of CT-based radiomic signatures to differentiate CEA-positive from CEA-negative colon cancer patients.

April 22, 2026Open Access

CT-Based Radiomic Signatures Associated with Serum CEA Status in Colon Cancer

DDDemet Doğan CÖCoşku ÖksüzIzmir University ÖÇÖzgür Çakır

Key Points

This study aims to assess the ability of CT-based radiomic signatures to differentiate CEA-positive from CEA-negative colon cancer patients.
Retrospective analysis of 150 colon cancer patients with image quality assessment reducing it to 109 eligible cases.
107 radiomic features extracted from preoperative CT images, followed by z-score normalization and feature selection.
Training of five machine-learning classifiers using stratified 5-fold cross-validation to evaluate performance metrics.
The k-NN classifier achieved the highest accuracy at 77.4% and ROC-AUC of 0.8523.
SVM and neural network classifiers yielded the highest recall at 83.0%.
Selected features contributed to balanced and robust differentiation of CEA-positive and CEA-negative patients.

Abstract

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 (|ρ| ≥ 0.7) was applied. Five machine-learning classifiers—Support Vector Machine (SVM), Decision Tree, Ensemble, k-Nearest Neighbor (k-NN), and Neural Network (NN)—were 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 ± 2%) and ROC-AUC (0.8523 ± 0.013), while SVM and NN achieved the highest recall (83.0 ± 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—particularly k-NN, SVM, and neural network classifiers—showed 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.

Ask AI

Helpful

Bookmark

View Full Paper