Last reviewed · How we verify
NCT06936098
Deep Learning-Based Analysis of Colorectal Cancer Pathology Images: An Innovative Approach for Predicting Colorectal Cancer Subtypes
trial testing CRLM surgery in Colorectal Liver Metastasis (CRLM) in 431 participants. Completed in 6 March 2024.
6 March 2024
Quick facts
| Lead sponsor | Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University |
|---|---|
| Status | Completed |
| Study type | OBSERVATIONAL |
| Enrollment | 431 |
| Start date | 22 May 2023 |
| Primary completion | 6 March 2024 |
| Estimated completion | 6 March 2024 |
| Sites | 1 location across China |
Drugs / interventions tested
- CRLM surgery
Conditions studied
- Colorectal Liver Metastasis (CRLM) — all drugs for Colorectal Liver Metastasis (CRLM) →
- Histopathological Growth Patterns (HGPs) — all drugs for Histopathological Growth Patterns (HGPs) →
- Artificial Intelligence (AI) in Diagnosis — all drugs for Artificial Intelligence (AI) in Diagnosis →
- Vision Transformer (ViT) — all drugs for Vision Transformer (ViT) →
Sponsor
Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
Who can join
Adults 18 to 75, any sex, with Colorectal Liver Metastasis (CRLM) or Histopathological Growth Patterns (HGPs). Patients with the condition only — healthy volunteers not accepted.
Sponsor's own description
Colorectal cancer (CRC) is a leading cause of mortality in China, with metastasis significantly contributing to poor outcomes. Histopathological growth patterns (HGPs) in colorectal liver metastasis (CRLM) provide vital prognostic insights, yet the limited number of pathologists highlights the need for auxiliary diagnostic tools. Recent advancements in artificial intelligence (AI) have demonstrated potential in enhancing diagnostic precision, prompting the development of specialized AI models like COFFEE to improve the classification and management of HGPs in CRLM patients. This study aims to develop and validate a Transformer-based deep learning model, COFFEE, for the classification of colorectal cancer subtypes using whole slide images (WSIs) from patients diagnosed with colorectal cancer liver metastasis. The model is pre-trained using self-supervised learning (DINO) on WSIs from the TCGA-COAD cohort, utilizing a Vision Transformer (ViT) architecture to extract 384-dimensional feature vectors from 256×256 pixel patches. The COFFEE model integrates a Transformer-based Multiple Instance Learning (TransMIL) framework, incorporating multi-head self-attention and Pyramid Position Encoding Generator (PPEG) modules to aggregate spatial and morphological information. The study includes training, testing, and prospective validation cohorts and evaluates the performance of the model in both binary and multi-class classification settings, as well as its potential to assist pathologists in clinical workflows.
Publications & conference data
1 peer-reviewed publication reference this trial (live from Europe PMC):
-
Artificial intelligence-powered copilots for precision diagnosis and surgical assessment of histological growth patterns in resectable colorectal liver metastases: a prospective study.
Lin R, Chen Y, Li Y, Tan Y, et al · · 2025 · cited 2× · PMID 40638258 · DOI 10.1097/js9.0000000000002922
Verify or expand the search:
- PubMed search for NCT06936098
- Europe PMC full search
- ASCO Meeting Library
- ESMO Meeting Library
- bioRxiv preprints
- medRxiv preprints
- Google Scholar
Related trials
Other recruiting trials for Colorectal Liver Metastasis (CRLM)
Currently open trials in the same condition.
- NCT07385521 — The Use of Artificial Intelligence for the Prediction of Recurrence After Resection of Colorectal Liver Metastases · recruiting
- NCT07027605 — Multi-Reader Multi-Case Trial Evaluating Computer-Aided Tool for Prognostic Prediction of Colorectal Liver Metastases · recruiting
- NCT06988852 — FOLFOX-HAIC as Conversion Treatment for Initially Unresectable Colorectal Liver Metastasis · Phase 2 · recruiting
Other Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University trials
Trials by the same sponsor.
- NCT07168083 — Efficacy and Safety of Sacituzumab in Patients With OCCC After Immunotherapy Progression · not yet recruiting
- NCT07413497 — A Prospective Observational Clinical Study on Exploring the Value of Surgical Excision Combined With 32P Application in · not yet recruiting
- NCT07461077 — Noninvasive Implantation Potential vs Morphology-Based Selection in IVF Single Blastocyst Transfer · NA · not yet recruiting
- NCT07533526 — Effects of Instrument-Assisted Constant-Speed Injection Versus Manual Injection on Pain From Large-Volume Subcutaneous I · NA · not yet recruiting
- NCT07408648 — A Clinical Study on the Efficacy and Safety of Hetrombopag in the Treatment of Thrombocytopenia Induced by Gynecological · Phase 2 · not yet recruiting
Verify against primary sources
- ClinicalTrials.gov — authoritative US registry record
- WHO ICTRP — international registry index
- EU Clinical Trials Register
- Sponsor press releases (Google)
- Trial protocol + status: ClinicalTrials.gov NCT06936098 (US National Library of Medicine, public domain)
- Publications: Europe PMC API search by NCT ID, retrieved 10 June 2026
- Drug + disease cross-links: matched in real time against Drug Landscape's normalised drug + company + condition tables
- Sponsor: as reported to ClinicalTrials.gov by Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
- Last refreshed: 20 April 2025
Drug Landscape aggregates and links these public records for informational use only. Always verify against the primary source before clinical or regulatory decisions. Canonical URL: https://druglandscape.com/trial/NCT06936098.
Primary sources · FDA · ClinicalTrials.gov · EMA · SEC EDGAR · ChEMBL · Wikidata · full sourcing