FindTrial
Sign In

Retrospective imaging studies of gastric cancer: deep learning on peritoneal metastasis

Development and Validation of a Deep Learning Method for Preoperative Prediction of Peritoneal Metastasis in Gastric Cancer.

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR1900028437
Enrollment
Unknown
Registered
2019-12-21
Start date
2020-01-01
Completion date
Unknown
Last updated
2020-01-06

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

Conditions

gastric cancer

Interventions

Gold Standard:Surgical pathology results
Index test:deep&#32
learning&#32
based&#32
on&#32
CT&#32
images.

Sponsors

West China Hospital, Sichuan University
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. diagnosed gastric adenocarcinoma by endoscopy–biopsy pathology; 2. with available contrast-enhanced CT within 2 weeks before laparoscopy or surgery performed in our hospital; 3. the venous images (2 mm slice) were used to draw ROIs; 4. without typical PM indications on CT (omental nodules or omental cake, extensive ascites, irregular thickening with high peritoneal enhancement); 5 without other evidence of distant metastasis and no other cancers; 6. body mass index >= 24.

Exclusion criteria

Exclusion criteria: 1. previous abdominal surgery; 2. previous abdominal malignancies or inflammatory diseases; 3. time interval between CT and laparoscopy or operation longer than 2 weeks; 4. poor CT image quality for post-processing due to artifacts.

Design outcomes

Primary

MeasureTime frame
metastasis;SPE, SEN, ACC, AUC of ROC;—

Countries

China

Contacts

Public ContactBin Song

West China Hospital, Sichuan University

songlab_radiology@163.com+86 028 85423680

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026