Liver MetastasesNCT07871019
CT Radiomics and Deep Learning-Based Non-Invasive Model for Tracing Primary Sites of Adenocarcinoma Liver Metastases: Automatic Differentiation of Multiple Primary Digestive Tumors
An observational study of Liver Metastases and Gastric Adenocarcinoma, run by West China Hospital at 1 site in China.
Trial summary
This is a retrospective observational study. Liver metastasis occurs frequently in digestive-system cancers. Identification of the primary tumor source of liver metastasis may pose clinical challenges. Biopsy is an invasive procedure associated with potential sampling errors. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Liver Metastases, Gastric Adenocarcinoma, Colorectal Adenocarcinoma
- What is being tested?
- Retrospective image analysis
- How many people
- 700 participants
- Where
- 1 siteChina
- Study dates
- Jan 2015to Aug 2026
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Study population: Adult patients with pathologically confirmed adenocarcinoma liver metastases from four primary gastrointestinal adenocarcinoma subtypes (gastric, colorectal, biliary/gallbladder, pancreatic ductal adenocarcinoma). Retrospectively enrolled from a single tertiary hospital.
Who may be able to join
- Pathologically-confirmed hepatic metastases from adenocarcinoma, with a histologically verified primary tumor belonging to one of the four subtypes: gastric adenocarcinoma, colorectal adenocarcinoma (colon or rectal adenocarcinoma), biliary/gallbladder adenocarcinoma, pancreatic ductal adenocarcinoma
- Definite imaging evidence of liver metastases on contrast-enhanced CT
- Complete pretreatment portal-venous-phase contrast-enhanced CT images (slice thickness ≤2.5 mm)
- Complete clinical data (including age, sex, tumor markers, and other clinical information)
Who cannot join
- Coexistence of two or more primary malignant tumors (multiple primary cancers)
- Concurrent primary hepatic tumors (hepatocellular carcinoma, intrahepatic cholangiocarcinoma, etc.) and metastatic lesions
- Poor CT image quality (severe respiratory artifacts, metal artifacts, etc.) substantially impairing lesion visualization
- Maximum diameter of metastatic lesion <5 mm (risk of excessive segmentation error)
- Prior chemotherapy, radiotherapy, or targeted therapy (treatments that may alter imaging features of lesions)
Trial locations and contacts
1 site in 1 country.
About this study
Official title: Non-Invasive Origin Tracing Model for Hepatic Metastases From Adenocarcinoma Based on CT Radiomics and Deep Learning: A Clinical Study for Automatic Differentiation of Multiple Primary Digestive Malignancies
This is a retrospective observational study. Liver metastasis occurs frequently in digestive-system cancers. Identification of the primary tumor source of liver metastasis may pose clinical challenges. Biopsy is an invasive procedure associated with potential sampling errors. This study aims to develop and validate a non-invasive artificial-intelligence model based on contrast-enhanced CT images. The model integrates CT radiomics and deep learning to automatically determine the primary origin of adenocarcinoma liver metastases, including gastric adenocarcinoma, colorectal adenocarcinoma, biliary/gallbladder adenocarcinoma, and pancreatic ductal adenocarcinoma. The investigators will retrieve historical medical records and de-identified abdominal contrast-enhanced CT images from patients diagnosed at West China Hospital, Sichuan University between January 2015 and August 2026. No new intervention or treatment will be administered to participants in this study.
Read the detailed description
Liver metastasis represents the most common form of distant metastasis for digestive adenocarcinomas. Approximately 22% of patients with colorectal cancer and 52% of patients with pancreatic cancer present with liver metastasis at initial diagnosis. Two challenging clinical scenarios are recognized: participants with liver metastases derived from occult primary tumors (carcinoma of unknown primary, CUP), and participants with multiple primary malignancies in whom newly-detected hepatic lesions cannot be distinguished as metastatic deposits versus de-novo primary tumors. Pathological biopsy serves as the gold-standard for differential diagnosis; however, its invasiveness, sampling bias, and limited repeatability restrict routine clinical application. Prior radiomics and deep-learning investigations predominantly addressed binary-classification tasks and lacked multi-class external validation. This retrospective study will enroll approximately 500-700 eligible participants with pathologically-confirmed adenocarcinoma liver metastases. The investigators will extract radiomic features from pretreatment portal-venous-phase contrast-enhanced CT images, and construct and validate an integrated radiomics-deep-learning model for four-class primary-site differentiation. All imaging and clinical datasets will undergo full de-identification prior to analysis. No participant will receive novel clinical interventions for the purpose of this research.
- Conditions
- Liver Metastases, Gastric Adenocarcinoma, Colorectal Adenocarcinoma, Biliary Tract Adenocarcinoma, Pancreatic Ductal Adenocarcinoma
- Being tested
- Retrospective image analysis
- Keywords
- radiomics, deep learning, contrast-enhanced CT, hepatic metastasis, primary site tracing, retrospective study
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Retrospective image analysisOther
No prospective intervention is applied to participants. This study only performs retrospective analysis of previously acquired contrast-enhanced CT images and clinical data, no new diagnostic or therapeutic procedures are performed for study purposes.
| Study group | Role | What they receive |
|---|---|---|
| Patients with adenocarcinoma liver metastases | This cohort includes patients with pathologically confirmed adenocarcinoma liver metastases from four primary digestive tumors (gastric, colorectal, biliary tract and gallbladder, pancreatic ductal adenocarcinoma). Retrospective collection of de-identified pretreatment contrast-enhanced CT images and clinical data. No study-related intervention is performed. Receives: Other: Retrospective image analysis |
What is being measured
The primary outcome is the main question the study is designed to answer.
Overall classification accuracy of the combined radiomics-deep learning model for multi-class primary-site prediction of adenocarcinoma liver metastases
Proportion of correctly predicted primary tumor sites among all participants with pathologically-confirmed adenocarcinoma liver metastases, calculated from CT-based radiomics-deep-learning model predictions against reference pathological diagnosis.
Measured: At baseline (time of the pretreatment contrast-enhanced CT scan)
Secondary outcomes (2)
Area under the receiver-operating-characteristic curve (AUC) of the radiomics-deep learning model for each primary tumor category
Model AUC values calculated separately for each of the four digestive adenocarcinoma primary tumor subtypes, using pathological diagnosis as reference standard.
Measured: At baseline (time of the pretreatment contrast-enhanced CT scan)
Sensitivity and specificity of the radiomics-deep learning model for primary-site classification of each tumor subtype
Per-tumor-category sensitivity and specificity of the multi-class prediction model, with pathological diagnosis serving as ground-truth reference.
Measured: At baseline (time of the pretreatment contrast-enhanced CT scan)
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted13 Oct 2026
- Study startJan 2015
- Primary completionAug 2026
- Study completionAug 2026
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (8)Papers the sponsor has linked to this study.
- Other trials for Liver MetastasesStudies of the same condition, open and under way.
- More trials run by West China HospitalThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Case only
- Time perspective
- Retrospective
- Enrolment
- 700 participants (actual)
Sponsor and investigators
- Lead sponsor
- West China Hospital
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Dai Ruihong, West China Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07871019
- Sponsor's protocol ID
- 20262366
- Status last verified
- Oct 2026
- First submitted
- 27 Sep 2026
- Last updated
- 13 Oct 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Undecided
Publications
Chen C, Lu C, Viswanathan V, Maveal B, Maheshwari B, Willis J, Madabhushi A. Identifying primary tumor site of origin for liver metastases via a combination of handcrafted and deep learning features. J Pathol Clin Res. 2024 Jan;10(1):e344. doi: 10.1002/cjp2.344. Epub 2023 Oct 11.
PubMed 37822044Xin H, Zhang Y, Lai Q, Liao N, Zhang J, Liu Y, Chen Z, He P, He J, Liu J, Zhou Y, Yang W, Zhou Y. Automatic origin prediction of liver metastases via hierarchical artificial-intelligence system trained on multiphasic CT data: a retrospective, multicentre study. EClinicalMedicine. 2024 Feb 1;69:102464. doi: 10.1016/j.eclinm.2024.102464. eCollection 2024 Mar.
PubMed 38333364Tharmaseelan H, Vellala AK, Hertel A, Tollens F, Rotkopf LT, Rink J, Woznicki P, Ayx I, Bartling S, Norenberg D, Schoenberg SO, Froelich MF. Tumor classification of gastrointestinal liver metastases using CT-based radiomics and deep learning. Cancer Imaging. 2023 Oct 5;23(1):95. doi: 10.1186/s40644-023-00612-4.
PubMed 37798797Beninato TM, Amin SA, Baine MJ, Lin C. Role of immunotherapy in the overall survival of gastrointestinal cancer patients with liver metastases. Hepat Oncol. 2024 Dec 31;11(1):2403323. doi: 10.1080/20450923.2024.2403323. Epub 2024 Sep 27.
PubMed 39881556Wang S, Feng Y, Swinnen J, Oyen R, Li Y, Ni Y. Incidence and prognosis of liver metastasis at diagnosis: a pan-cancer population-based study. Am J Cancer Res. 2020 May 1;10(5):1477-1517. eCollection 2020.
PubMed 32509393Lehrich BM, Zhang J, Monga SP, Dhanasekaran R. Battle of the biopsies: Role of tissue and liquid biopsy in hepatocellular carcinoma. J Hepatol. 2024 Mar;80(3):515-530. doi: 10.1016/j.jhep.2023.11.030. Epub 2023 Dec 15.
PubMed 38104635Pan SY, Huang CP, Chen WC. Synchronous/Metachronous Multiple Primary Malignancies: Review of Associated Risk Factors. Diagnostics (Basel). 2022 Aug 11;12(8):1940. doi: 10.3390/diagnostics12081940.
PubMed 36010291Cao BY, Tong F, Zhang LT, Kang YX, Wu CC, Wang QQ, Yang W, Wang J. Risk factors, prognostic predictors, and nomograms for pancreatic cancer patients with initially diagnosed synchronous liver metastasis. World J Gastrointest Oncol. 2023 Jan 15;15(1):128-142. doi: 10.4251/wjgo.v15.i1.128.
PubMed 36684042
Study at a glance
From the registry record, last updated by the sponsor on 13 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Non-Invasive Origin Tracing Model for Hepatic Metastases From Adenocarcinoma Based on CT Radiomics and Deep Learning: A Clinical Study for Automatic Differentiation of Multiple Primary Digestive Malignancies
- ClinicalTrials.gov ID
- NCT07871019
- Acronym / sponsor ID
- 20262366
- Conditions
- Liver Metastases, Gastric Adenocarcinoma, Colorectal Adenocarcinoma, Biliary Tract Adenocarcinoma, Pancreatic Ductal Adenocarcinoma
- Keywords
- radiomics, deep learning, contrast-enhanced CT, hepatic metastasis, primary site tracing, retrospective study
- Study type
- Observational
- Recruitment status
- Completed
- Enrolment
- 700 participants (actual)
- Lead sponsor
- West China HospitalUniversity, hospital or other
- Study start
- Jan 2015 (actual)
- Primary completion
- Aug 2026 (actual)
- Study completion
- Aug 2026 (actual)
- First posted
- 13 Oct 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
This is a retrospective observational study. Liver metastasis occurs frequently in digestive-system cancers. Identification of the primary tumor source of liver metastasis may pose clinical challenges. Biopsy is an invasive procedure associated with potential sampling errors. This study aims to develop and validate a non-invasive artificial-intelligence model based on contrast-enhanced CT images. The model integrates CT radiomics and deep learning to automatically determine the primary origin of adenocarcinoma liver metastases, including gastric adenocarcinoma, colorectal adenocarcinoma, biliary/gallbladder adenocarcinoma, and pancreatic ductal adenocarcinoma. The investigators will retrieve historical medical records and de-identified abdominal contrast-enhanced CT images from patients diagnosed at West China Hospital, Sichuan University between January 2015 and August 2026. No new intervention or treatment will be administered to participants in this study.
Detailed description
Liver metastasis represents the most common form of distant metastasis for digestive adenocarcinomas. Approximately 22% of patients with colorectal cancer and 52% of patients with pancreatic cancer present with liver metastasis at initial diagnosis. Two challenging clinical scenarios are recognized: participants with liver metastases derived from occult primary tumors (carcinoma of unknown primary, CUP), and participants with multiple primary malignancies in whom newly-detected hepatic lesions cannot be distinguished as metastatic deposits versus de-novo primary tumors. Pathological biopsy serves as the gold-standard for differential diagnosis; however, its invasiveness, sampling bias, and limited repeatability restrict routine clinical application. Prior radiomics and deep-learning investigations predominantly addressed binary-classification tasks and lacked multi-class external validation. This retrospective study will enroll approximately 500-700 eligible participants with pathologically-confirmed adenocarcinoma liver metastases. The investigators will extract radiomic features from pretreatment portal-venous-phase contrast-enhanced CT images, and construct and validate an integrated radiomics-deep-learning model for four-class primary-site differentiation. All imaging and clinical datasets will undergo full de-identification prior to analysis. No participant will receive novel clinical interventions for the purpose of this research.
Study design
- Observational model
- Case only
- Time perspective
- Retrospective
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| Patients with adenocarcinoma liver metastases | – | Other: Retrospective image analysisThis cohort includes patients with pathologically confirmed adenocarcinoma liver metastases from four primary digestive tumors (gastric, colorectal, biliary tract and gallbladder, pancreatic ductal adenocarcinoma). Retrospective collection of de-identified pretreatment contrast-enhanced CT images and clinical data. No study-related intervention is performed. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- Adult patients with pathologically confirmed adenocarcinoma liver metastases from four primary gastrointestinal adenocarcinoma subtypes (gastric, colorectal, biliary/gallbladder, pancreatic ductal adenocarcinoma). Retrospectively enrolled from a single tertiary hospital.
Key inclusion criteria (4 listed)
- Pathologically-confirmed hepatic metastases from adenocarcinoma, with a histologically verified primary tumor belonging to one of the four subtypes: gastric adenocarcinoma, colorectal adenocarcinoma (colon or rectal adenocarcinoma), biliary/gallbladder adenocarcinoma, pancreatic ductal adenocarcinoma
- Definite imaging evidence of liver metastases on contrast-enhanced CT
- Complete pretreatment portal-venous-phase contrast-enhanced CT images (slice thickness ≤2.5 mm)
- Complete clinical data (including age, sex, tumor markers, and other clinical information)
Key exclusion criteria (5 listed)
- Coexistence of two or more primary malignant tumors (multiple primary cancers)
- Concurrent primary hepatic tumors (hepatocellular carcinoma, intrahepatic cholangiocarcinoma, etc.) and metastatic lesions
- Poor CT image quality (severe respiratory artifacts, metal artifacts, etc.) substantially impairing lesion visualization
- Maximum diameter of metastatic lesion <5 mm (risk of excessive segmentation error)
- Prior chemotherapy, radiotherapy, or targeted therapy (treatments that may alter imaging features of lesions)
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Retrospective image analysisNo prospective intervention is applied to participants. This study only performs retrospective analysis of previously acquired contrast-enhanced CT images and clinical data, no new diagnostic or therapeutic procedures are performed for study purposes. | Other | Patients with adenocarcinoma liver metastases |
Primary outcome
Overall classification accuracy of the combined radiomics-deep learning model for multi-class primary-site prediction of adenocarcinoma liver metastases
Time frame: At baseline (time of the pretreatment contrast-enhanced CT scan)
Proportion of correctly predicted primary tumor sites among all participants with pathologically-confirmed adenocarcinoma liver metastases, calculated from CT-based radiomics-deep-learning model predictions against reference pathological diagnosis.
2 secondary outcomes
Area under the receiver-operating-characteristic curve (AUC) of the radiomics-deep learning model for each primary tumor category
Time frame: At baseline (time of the pretreatment contrast-enhanced CT scan)
Sensitivity and specificity of the radiomics-deep learning model for primary-site classification of each tumor subtype
Time frame: At baseline (time of the pretreatment contrast-enhanced CT scan)
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 13 Oct 2026.
- Background: PubMed 37822044Chen C, Lu C, Viswanathan V, Maveal B, Maheshwari B, Willis J, Madabhushi A. Identifying primary tumor site of origin for liver metastases via a combination of handcrafted and deep learning features. J Pathol Clin Res. 2024 Jan;10(1):e344. doi: 10.1002/cjp2.344. Epub 2023 Oct 11.
- Background: PubMed 38333364Xin H, Zhang Y, Lai Q, Liao N, Zhang J, Liu Y, Chen Z, He P, He J, Liu J, Zhou Y, Yang W, Zhou Y. Automatic origin prediction of liver metastases via hierarchical artificial-intelligence system trained on multiphasic CT data: a retrospective, multicentre study. EClinicalMedicine. 2024 Feb 1;69:102464. doi: 10.1016/j.eclinm.2024.102464. eCollection 2024 Mar.
- Background: PubMed 37798797Tharmaseelan H, Vellala AK, Hertel A, Tollens F, Rotkopf LT, Rink J, Woznicki P, Ayx I, Bartling S, Norenberg D, Schoenberg SO, Froelich MF. Tumor classification of gastrointestinal liver metastases using CT-based radiomics and deep learning. Cancer Imaging. 2023 Oct 5;23(1):95. doi: 10.1186/s40644-023-00612-4.
- Background: PubMed 39881556Beninato TM, Amin SA, Baine MJ, Lin C. Role of immunotherapy in the overall survival of gastrointestinal cancer patients with liver metastases. Hepat Oncol. 2024 Dec 31;11(1):2403323. doi: 10.1080/20450923.2024.2403323. Epub 2024 Sep 27.
- Background: PubMed 32509393Wang S, Feng Y, Swinnen J, Oyen R, Li Y, Ni Y. Incidence and prognosis of liver metastasis at diagnosis: a pan-cancer population-based study. Am J Cancer Res. 2020 May 1;10(5):1477-1517. eCollection 2020.
- Background: PubMed 38104635Lehrich BM, Zhang J, Monga SP, Dhanasekaran R. Battle of the biopsies: Role of tissue and liquid biopsy in hepatocellular carcinoma. J Hepatol. 2024 Mar;80(3):515-530. doi: 10.1016/j.jhep.2023.11.030. Epub 2023 Dec 15.
- Background: PubMed 36010291Pan SY, Huang CP, Chen WC. Synchronous/Metachronous Multiple Primary Malignancies: Review of Associated Risk Factors. Diagnostics (Basel). 2022 Aug 11;12(8):1940. doi: 10.3390/diagnostics12081940.
- Background: PubMed 36684042Cao BY, Tong F, Zhang LT, Kang YX, Wu CC, Wang QQ, Yang W, Wang J. Risk factors, prognostic predictors, and nomograms for pancreatic cancer patients with initially diagnosed synchronous liver metastasis. World J Gastrointest Oncol. 2023 Jan 15;15(1):128-142. doi: 10.4251/wjgo.v15.i1.128.
- Individual participant dataSharing planned: Undecided
Related trials for Liver Metastases
Not yet recruitingPhase 1
Hepatic Artery Infusion of Carfilzomib in Participants With Liver Metastatic Disease Previously Treated With Hepatic Artery Infusion Pump Therapy
Colorectal Neoplasms, Neoplasms
Recruiting
Immune Response to Percutaneous Hepatic Perfusion With Melphalan for Ocular Melanoma Metastatic to the Liver
Uveal Melanoma
Active, not recruitingPhase 2
A Study of Novel Study Interventions and Combinations in Participants With Colorectal Cancer
Metastatic Colorectal Cancer
Recruiting
TheraSphere Japan Pre-Market Study
Liver Neoplasms
Active, not recruiting
Surgical Margin Assessment Using Intra-operative High-resolution PET/CT in Patients With Cancers Referred to Surgical Resection, an Exploratory Pilot Study
Breast Cancer, Head and Neck Cancers
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
The record lists no contact. Use the official record to reach the sponsor.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Liver Metastases and Gastric Adenocarcinoma, run by West China Hospital at 1 site in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 4 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 13 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Overall classification accuracy of the combined radiomics-deep learning model for multi-class primary-site prediction of adenocarcinoma liver metastases (time frame: At baseline (time of the pretreatment contrast-enhanced CT scan)). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07871019, which also lists 8 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 13 Oct 2026.