AI-based body composition mapping from CT scans to predict outcomes after TACE for liver cancer
Deep Learning-Based Multidimensional Body Composition Mapping for Predicting Clinical Outcomes in Hepatocellular Carcinoma Patients Undergoing TACE
This project will test whether an AI that analyzes routine CT scans can help predict survival and treatment response for adults with hepatocellular carcinoma who receive TACE.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 300 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Union Hospital, Tongji Medical College, Huazhong University of Science and Technology Academic / other |
| Locations | 1 site (Wuhan, Hubei) |
| Trial ID | NCT07235410 on ClinicalTrials.gov |
What this trial studies
This single-center observational project uses deep learning to automatically analyze pre-treatment CT scans from adult HCC patients who underwent transarterial chemoembolization (TACE) between January 1, 2018 and May 31, 2024. The algorithm will quantify multidimensional body composition features such as organ sizes and muscle/fat condition across the abdomen and link these imaging features with clinical records. Patients with poor image quality, other active malignancies, loss to follow-up, or incomplete records will be excluded. The resulting model aims to predict survival and treatment outcomes after TACE to support more personalized treatment decisions.
Who should consider this trial
Good fit: Ideal candidates are adults (over 18) with hepatocellular carcinoma who underwent TACE and have good-quality pre-treatment CT scans and complete medical records.
Not a fit: Patients without usable CT images, with other active cancers, incomplete records, or who did not receive TACE would likely not benefit from this model.
Why it matters
Potential benefit: If successful, the tool could help doctors personalize TACE decisions by identifying patients most likely to benefit and those at higher risk of poor outcomes.
How similar studies have performed: Related radiomics and machine-learning approaches in liver cancer and other oncology settings have shown promising predictive signals, but deep-learning body composition mapping requires further validation.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Patients diagnosed with "Hepatocellular Carcinoma" from January 1, 2018 to May 31, 2024; 2. Age \> 18 years old. Exclusion Criteria: 1. Poor image quality; 2. Loss of follow-up; 3. Presence of another type of malignant tumor other than liver cancer; 4. Incomplete medical records.
Where this trial is running
Wuhan, Hubei
- Union Hospital, Tongji Medical College, Huazhong University of Science and Technology — Wuhan, Hubei, China (Recruiting)
Study contacts
- Study coordinator: Yuanyuan Chu
- Email: whunionlunli@126.com
- Phone: +8602785726375
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.