Adnexal Mass, Ovarian Neoplasms
Conditions
Brief summary
Research on automatic detection of ovarian mass and intelligent auxiliary diagnosis system based on multimodal ultrasound images.
Detailed description
Investigators aimed to develop an ultrasonic intelligent diagnosis system for ovarian mass based on multimodal ultrasound images.
Interventions
DIAGNOSTIC_TESTArtificial intelligence model
Using the artificial intelligence model to diagnosis benign, borderline, and malignant ovarian masses.
Sponsors
The Second Affiliated Hospital of Harbin Medical University
Sichuan provincial maternity and child health care hospital
The Affiliated Hospital of Qingdao University
Aksu First People's Hospital
Women's Hospital School Of Medicine Zhejiang University
Zhejiang Provincial People's Hospital
Study design
Observational model
OTHER
Time perspective
OTHER
Eligibility
Sex/Gender
FEMALE
Healthy volunteers
Yes
Inclusion criteria
1. During gynecological ultrasound examination, at least one patient with persistent ovarian tumor was found. 2. The patient underwent surgical treatment and the histopathological results.
Exclusion criteria
1. Histopathological analysis confirms non-ovarian tumor; 2. Histopathological results are inconclusive; 3. Issues with image quality: the ovarian mass is incomplete and does not show some surrounding tissues (but the mass is too large to exclude completely); the images are overly blurry, making it difficult to determine the characteristics of the ovarian mass (possible reasons include hardware quality issues with the ultrasound machine, motion blur, focusing problems, presence of intestinal gas in the patient); gain settings make it difficult to judge the characteristics of the ovarian mass (such as low contrast, excessively dark images, or saturation); the presence of artifacts affects the assessment of ultrasound characteristics of the ovarian mass and should be excluded.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Area under the curve | Through study completion, an average of 1 year | AUC (Area Under the Curve) is a common index used to evaluate the performance of binary classification model. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity | Through study completion, an average of 1 year | Sensitivity refers to the ability of the test to correctly identify a positive result in an individual who actually has the disease. It represents the proportion of cases in which the test is able to detect a positive for the disease |
Other
| Measure | Time frame | Description |
|---|---|---|
| Specificity | Through study completion, an average of 1 year | Specificity refers to the ability of the test to correctly identify a negative result in an individual who does not actually have the disease. It represents the proportion of cases where the disease is negative that the test is able to detect. |
| Accuracy | Through study completion, an average of 1 year | Accuracy refers to the degree to which the results of the diagnostic test are consistent with the actual situation |
| Positive predicative value | Through study completion, an average of 1 year | Positive Predictive Value indicates the probability that a test result will be true if it is positive. In other words, it represents the proportion of individuals who are diagnosed as positive when the test result is positive who actually have the disease |
| Negative predictive value | Through study completion, an average of 1 year | Negative Predictive Value refers to the probability that if a test result is negative, the result will be true negative. It represents the proportion of individuals who are diagnosed as negative when the test results are negative that are truly free of the disease |
Contacts
Primary ContactYingnan Wu, Doctor
Outcome results
None listed