Gut decisions based on the liver: A radiomics approach to boost colorectal cancer screening

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hinterberger, Anna, Bohn, Jonas, Trofimova, Dasha, Knabe, Nicolas, Dettling, Julia, Norajitra, Tobias, Isensee, Fabian, Betge, Johannes, Schönberg, Stefan O., Nörenberg, Dominik, Grosu, Sergio, Loges, Sonja, Floca, Ralf, Kather, Jakob Nikolas, Maier-Hein, Klaus, Grawe, Freba
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912673568915456
author Hinterberger, Anna
Bohn, Jonas
Trofimova, Dasha
Knabe, Nicolas
Dettling, Julia
Norajitra, Tobias
Isensee, Fabian
Betge, Johannes
Schönberg, Stefan O.
Nörenberg, Dominik
Grosu, Sergio
Loges, Sonja
Floca, Ralf
Kather, Jakob Nikolas
Maier-Hein, Klaus
Grawe, Freba
author_facet Hinterberger, Anna
Bohn, Jonas
Trofimova, Dasha
Knabe, Nicolas
Dettling, Julia
Norajitra, Tobias
Isensee, Fabian
Betge, Johannes
Schönberg, Stefan O.
Nörenberg, Dominik
Grosu, Sergio
Loges, Sonja
Floca, Ralf
Kather, Jakob Nikolas
Maier-Hein, Klaus
Grawe, Freba
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gut decisions based on the liver: A radiomics approach to boost colorectal cancer screening
Hinterberger, Anna
Bohn, Jonas
Trofimova, Dasha
Knabe, Nicolas
Dettling, Julia
Norajitra, Tobias
Isensee, Fabian
Betge, Johannes
Schönberg, Stefan O.
Nörenberg, Dominik
Grosu, Sergio
Loges, Sonja
Floca, Ralf
Kather, Jakob Nikolas
Maier-Hein, Klaus
Grawe, Freba
Quantitative Methods
Image and Video Processing
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.
title Gut decisions based on the liver: A radiomics approach to boost colorectal cancer screening
topic Quantitative Methods
Image and Video Processing
url https://arxiv.org/abs/2510.23687