Preprint

DKFZ-2025-02779

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Gut decisions based on the liver: A radiomics approach to boost colorectal cancer screening

Hinterberger, A. (First author)DKFZ* ; Bohn, J.DKFZ* ; Trofimova, D.DKFZ* ; Knabe, N. ; Dettling, J. ; Norajitra, T.DKFZ* ; Isensee, F.DKFZ* ; Betge, J.DKFZ* ; Schönberg, S. O. ; Nörenberg, D. ; Grosu, S. ; Loges, S.DKFZ* ; Floca, R.DKFZ* ; Kather, J. N.DKFZ* ; Maier-Hein, K. (Last author)DKFZ* ; Grawe, F. (Last author)DKFZ*

2025
arXiv

Abstract: Non-invasive colorectal cancer (CRC) screening represents a key opportunity to improve colonoscopy participation rates and reduce CRC mortality. This study explores the potential of the gut-liver axis for predicting colorectal neoplasia through liver-derived radiomic features extracted from routine CT images as a novel opportunistic screening approach. In this retrospective study, we analyzed data from 1,997 patients who underwent colonoscopy and abdominal CT. Patients either had no colorectal neoplasia (n=1,189) or colorectal neoplasia (n_total=808; adenomas n=423, CRC n=385). Radiomics features were extracted from 3D liver segmentations using the Radiomics Processing ToolKit (RPTK), which performed feature extraction, filtering, and classification. The dataset was split into training (n=1,397) and test (n=600) cohorts. Five machine learning models were trained with 5-fold cross-validation on the 20 most informative features, and the best model ensemble was selected based on the validation AUROC. The best radiomics-based XGBoost model achieved a test AUROC of 0.810, clearly outperforming the best clinical-only model (test AUROC: 0.457). Subclassification between colorectal cancer and adenoma showed lower accuracy (test AUROC: 0.674). Our findings establish proof-of-concept that liver-derived radiomics from routine abdominal CT can predict colorectal neoplasia. Beyond offering a pragmatic, widely accessible adjunct to CRC screening, this approach highlights the gut-liver axis as a novel biomarker source for opportunistic screening and sparks new mechanistic hypotheses for future translational research.

Keyword(s): Quantitative Methods (q-bio.QM) ; Image and Video Processing (eess.IV) ; FOS: Biological sciences ; FOS: Electrical engineering, electronic engineering, information engineering

Note: https://arxiv.org/pdf/2510.23687

---

Contributing Institute(s):

1. NWG KKE Translationale Molekulare Bildgebung im Onkologischen Therapiemonitoring (E310)
2. E230 Medizinische Bildverarbeitung (E230)
3. DKTK HD zentral (HD01)
4. Personalisierte Medizinische Onkologie (A420)

Research Program(s):

1. 315 - Bildgebung und Radioonkologie (POF4-315) (POF4-315)

Appears in the scientific report 2025

---