Skip to content

Clinical Study on Predicting Tumor Deposition and Prognosis of Colorectal Cancer by Artificial Intelligence Fusion Model Based on CT Features of Tumor and Peritumoral Regions

Clinical Study on Predicting Tumor Deposition and Prognosis of Colorectal Cancer by Artificial Intelligence Fusion Model Based on CT Features of Tumor and Peritumoral Regions

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600126172
Enrollment
Unknown
Registered
2026-06-04
Start date
2026-06-10
Completion date
Unknown
Last updated
2026-06-08

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Colorectal cancer

Interventions

Gold Standard:The postoperative pathological examination of surgically resected specimens will be used as the reference standard to determine the presence or absence of tumor deposits (TD) in patients
Index test:Radiomics, deep learning and combined models based on preoperative contrast-enhanced CT images will be used to predict the status of tumor deposits (TD) in patients with colorectal cancer.

Sponsors

Hefei First People's Hospital
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. Patients with colorectal cancer confirmed by postoperative pathology after surgical resection; 2. Patients who underwent preoperative contrast-enhanced CT examination with adequate image quality for radiomics/deep learning analysis; 3. Complete pathological information was available to determine the status of tumor deposits (TD); 4. Complete clinical, imaging and pathological data were available;

Exclusion criteria

Exclusion criteria: 1. Patients who received preoperative radiotherapy, chemotherapy, targeted therapy, immunotherapy or other anti-tumor treatments; 2. Patients with poor CT image quality, obvious artifacts or unclear tumor visualization, making image segmentation and feature extraction impossible; 3. Patients with incomplete clinical, imaging or pathological data; 4. Patients with concurrent or previous history of other malignancies; 5. Patients with non-primary colorectal cancer, postoperative recurrent disease or unclear pathological diagnosis;

Design outcomes

Primary

MeasureTime frame
Area under the receiver operating characteristic curve, AUC;

Secondary

MeasureTime frame
Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the model for predicting tumor deposits in colorectal cancer;Clinical utility of the model;Calibration performance of the model;Association between the AI-TD risk score and disease-free survival;

Countries

China

Contacts

Public ContactYonghai Li

Hefei First People's Hospital

liyonghai20@163.com+86 551 62183010

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jun 11, 2026