AI-based prediction of liver metastasis after colorectal cancer surgery

A Multicenter, Retrospective, Observational Study to Develop and Validate a Multimodal Deep Learning Model for Predicting Metachronous Liver Metastasis in Colorectal Cancer Patients After Curative Resection

Observational Tongji Hospital · NCT07399236

This project will try a deep learning model that combines CT scans, digitized pathology slides, and routine clinical data to predict which stage I–III colorectal cancer patients are likely to develop liver metastases after curative surgery.

Quick facts

Study typeObservational
Enrollment1500 (estimated)
Ages18 Years to 75 Years
SexAll
SponsorTongji Hospital Academic / other
Locations1 site (Wuhan, Hubei)
Trial IDNCT07399236 on ClinicalTrials.gov

What this trial studies

This retrospective analysis uses existing clinical records, preoperative contrast-enhanced CT images, and digitized histopathology whole-slide images to build a multimodal deep learning model for predicting metachronous liver metastasis after curative resection. The model's discriminative performance will be measured by area under the ROC curve (AUC) and compared against conventional prognostic factors such as TNM stage and serum CEA. Only archival data are used, so there is no patient contact or intervention. The goal is to create a validated, data-driven risk stratification tool that could inform personalized surveillance and adjuvant treatment decisions if further prospective validation supports its use.

Who should consider this trial

Good fit: Ideal candidates are adults 18–75 with histologically confirmed colon or rectal adenocarcinoma who underwent R0 resection, had a preoperative contrast-enhanced abdominal/pelvic CT within one month before surgery, and have complete clinical, imaging, and pathology records with regular follow-up.

Not a fit: Patients with previous other malignancies, prior liver surgery or transplantation, missing required data, perioperative death (within 30 days), or lacking regular follow-up would not be included and therefore would not benefit from this analysis.

Why it matters

Potential benefit: If successful, the model could help doctors identify patients at higher risk of liver metastases so follow-up and treatment can be better personalized.

How similar studies have performed: Previous imaging- or pathology-based AI and radiomics studies have shown promising but variable results, and fully validated multimodal models for predicting liver metastasis remain limited.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Age 18-75 years, any gender.
* Histologically confirmed primary colon or rectal adenocarcinoma.
* Underwent curative radical resection (R0 resection) for colorectal cancer.
* Preoperative contrast-enhanced abdominal/pelvic CT scan performed within 1 month before surgery, with acceptable image quality.
* No evidence of distant metastasis (including synchronous liver metastasis) on preoperative or intraoperative exploration.

Exclusion Criteria:

* History of other malignant tumors.
* Previous history of liver surgery or liver transplantation.
* Missing clinical, imaging, or pathological data required for the study.
* Death within the perioperative period (within 30 days after surgery).
* Lack of regular follow-up information.

Where this trial is running

Wuhan, Hubei

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Colorectal Cancer Liver MetastasesColorectal cancer liver metastasesdeep learningmultimodalpredictive model
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.