AI-based prediction of liver metastasis after colorectal cancer surgery
Official title: 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
Run by Tongji Hospital · NCT07399236 · Data updated 2026-11-12
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 type | Observational |
|---|---|
| Ages | 18 Years to 75 Years |
| Sex | All |
| Enrollment | 1500 (estimated) |
| Sponsor | Tongji Hospital Academic / other |
| Locations | 1 site (Wuhan, Hubei) |
| Status | Recruiting |
| Started | January 1, 2015 |
| Main results expected | January 30, 2026 |
| Study ends | January 30, 2026 |
| Registry record updated | February 10, 2026 |
| Trial ID | NCT07399236 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a 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.
✕Probably 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.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
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.
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 gone: 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.
Who can join: the full rules
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 it's running
-
Tongji Hospital
Wuhan, Hubei, China Recruiting
Study contacts
- Study coordinator: Yang wu, M.D.
- Email: 255001907@qq.com
- Phone: 13636076910
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
ctDNA methylation-guided adjuvant therapy after removing colorectal liver metastases
This trial tests whether using a blood test that detects ctDNA methylation after surgery can guide adjuvant therapy for patients who had colorectal cancer spread to the liver and were operated on with no remaining disease.
-
AK104 plus radiotherapy with standard first-line treatment for pMMR/MSS colorectal cancer liver metastases
This trial will test whether adding AK104 and targeted liver radiotherapy to standard first-line therapy helps people with pMMR/MSS colorectal cancer that has spread to the liver.
-
Blood test using exosome microRNAs to find extrahepatic spread in colorectal cancer with liver metastases
This project will test whether a blood test measuring exosome microRNAs can detect extrahepatic metastases in adults whose colorectal cancer has spread to the liver.
-
Comparing two methods to induce liver regeneration in colorectal cancer patients
This study is testing if a new method that combines two types of vein blockage can help colorectal cancer patients with liver issues regenerate their liver better than the standard method.
-
Detecting tumor DNA in small automated capillary blood samples from adults with colorectal cancer liver metastases.
This project will try whether tiny automated capillary (finger‑prick) blood samples can detect circulating tumor DNA in adults with colorectal cancer that has spread to the liver.
-
Computer-aided tool to predict outcomes after simultaneous colorectal and liver surgery
This project will test a web-based computer tool that helps doctors predict 1-, 3-, and 5-year recurrence and survival for adults with colorectal cancer who had liver metastases removed at the same time as their primary tumor.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.