Ovarian Cancer
Conditions
Brief summary
The present study aims to collect early bright field image of patient-derived organoids with ovarian cancer. By leveraging artificial intelligence, this study will seek to construct and refine algorithms that able to predict growth of ovarian cancer organoids.
Interventions
OTHERgrowth prediction of ovarian cancer organoids in the frame of bright field image by leveraging AI
biopsy or puncture: Patients received biopsy or puncture to obtain tumor tissues or Malignant effusion for organoids establishment
Sponsors
Chongqing University Cancer Hospital
Study design
Observational model
COHORT
Time perspective
OTHER
Eligibility
Sex/Gender
FEMALE
Healthy volunteers
No
Inclusion criteria
* Patients must have histologically confirmed diagnosis of epithelial ovarian cancer * Patients received biopsy or puncture to obtain tumor tissues or malignant effusion * Patients voluntarily participated in the study and signed informed consent.
Exclusion criteria
* Non-epithelial ovarian cancer * No sufficient amount of tumor tissues or malignant effusion for organoids establishment.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| AUC of growth prediction performance using deep learning model | up to 3 years | AUC =Area under receiver operating characteristic curve |
| Accuracy of growth prediction using deep learning model | up to 3 years | Accuracy=( the number of correctly classified samples)/( the number of total samples) |
Countries
China
Contacts
Primary ContactDongling Zou, MD
Outcome results
None listed