AI-powered CT screening for ovarian cancer using deep learning
Official title: Development and Validation of a Deep Learning Model for Ovarian Cancer Identification on CT: A Nationwide Population-Based and International Study
Run by Chang Gung Memorial Hospital · NCT06851429 · Data updated 2026-11-12
A deep learning tool called CAT-OV is being tested to help spot ovarian cancer on CT scans in adults who have had a CT and are undergoing surgery for confirmation.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 20 Years and up |
| Sex | Women only |
| Enrollment | 12578 (estimated) |
| Sponsor | Chang Gung Memorial Hospital Academic / other |
| Drugs / interventions | chemotherapy |
| Locations | 2 sites (Taoyuan City, Guishan District and 1 other locations) |
| Status | Recruiting |
| Started | September 1, 2022 |
| Main results expected | February 7, 2025 |
| Study ends | August 31, 2028 |
| Registry record updated | August 12, 2026 |
| Trial ID | NCT06851429 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Women aged 20 years or older who have undergone a CT scan and are about to have ovarian surgery with histopathology evaluation.
✕Probably not a fit
Patients whose CT scans do not show cancer or whose cancer is not detectable by CT-based AI features may not benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational study develops and evaluates CAT-OV, an AI-based computer-aided diagnosis tool that uses CT images to detect ovarian cancer. The system combines a pelvic localization step with a MIL ensemble classifier to predict cancer presence. Training and validation used retrospective data from Taiwan, the United States, and a real-world nationwide cohort, with careful image preprocessing to improve accuracy. The goal is to see if AI-assisted CT screening can aid earlier detection, while acknowledging the need for further validation before clinical adoption.
Why it matters
Potential benefit: If successful, CAT-OV could support earlier detection of ovarian cancer through CT imaging and potentially improve patient outcomes.
How similar studies have gone: Previous AI and deep learning efforts in imaging have shown promise but require further validation for routine clinical use.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Age ≥ 20 years old. 2. Female 3. undergone a CT scan 4. undergone a CT scan within 180 days prior to ovarian surgery for histopathological evaluation. Exclusion Criteria: 1. Age \< 20 years old. 2. Non-female 3. Non-CT imaging 4. Incorrect image orientation 5. Number of slices \< 10 6. Slice thickness \>10 mm or \< 1 mm 7. Unsuccessful DICM-to-NIfTI 8. Pelvic subvolume extraction failed 9. Non-contrast CT scans 10. Metallic artifacts 11. Inconclusive cases
Where it's running
-
Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital
Taoyuan, Guishan, Taiwan Recruiting -
Chang Gung Memorial Hospital
Taoyuan City, Guishan District, Taiwan Completed
Study contacts
- Principal investigator: Gigin Lin, MD, PhD — Chang Gung Memorial Hospital
- Study coordinator: Gigin Lin, MD, PhD
- Email: giginlin@cgmh.org.tw
- Phone: 886-3-3281200
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
CG-7321: a first-in-human test in advanced solid tumors
We’re testing CG-7321 alone and with fulvestrant to see if it’s safe and tolerable in adults with advanced solid tumors.
-
CR-002 study in adults with advanced solid tumors
This trial tests CR-002 as a single therapy to see if it is safe and tolerable in adults with locally advanced or metastatic solid tumors
-
VT-101 in Advanced Ovarian Cancer: early safety study in adults
This early-phase trial tests VT-101 in adult women with advanced, recurrent, or relapsed epithelial ovarian cancer to see if it is safe, how the body handles it, and whether there are any initial signs of activity.
-
Methylation markers in self-samples to help detect gynecological cancers
This study tests whether self-collected urine and vaginal samples can reveal DNA methylation or other genetic markers that indicate endometrial, ovarian, vulvar, or vaginal cancers in women who are at risk or have postmenopausal bleeding.
-
Radiotherapy for gynecologic cancer with up to 10 metastatic sites
This registry follows adults with gynecologic cancer who have 1 to 10 active metastatic lesions and are treated with radiotherapy as part of routine care to see how such treatments work in real-world settings.
-
EHR-based approach to boost HBOC genetic testing in at-risk women
A new EHR tool-based program tests whether computer prompts and real patient resources can help more women with family histories of breast or ovarian cancer get HBOC genetic testing.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.