The following info and data is provided "as is" to help patients around the globe.
We do not endorse or review these studies in any way.
Brief Title: Convolutional Neural Network in Ovarian Follicle Identification
Official Title: Assessing a Mask Region-based Convolutional Neural Network in Follicle Identification and Measurement During Ovarian Stimulation
Study ID: NCT04545918
Brief Summary: A prospective cohort trial studying patients with infertility undergoing an ovarian stimulation with exogenous gonadotropins. Ovarian monitoring will be performed with a combination of transvaginal ultrasound and 2 dimensional human measurements of the follicle development on the right and left ovaries along with SonoAVC. Human and SonoAVC measurements will then be compared to mask region-based convolutional neural network in follicle identification and measurement during during the ovarian stimulation.
Detailed Description: This is a prospective cohort trial in which a total of 80 female subjects with infertility between the ages of 21 and 42 years of age undergoing ovarian stimulation will be recruited. After giving informed written consent the subject to undergo standard ovarian ultrasound monitoring with transvaginal ultrasounds during the ovarian stimulation. Monitoring will be performed with two-dimensional measurements of each follicle greater than 10 mm in size by the ultrasonographer. SonoAVC will then be applied to both ovaries for automated counting and measurement of the follicles within the ovaries. The patient will then undergo two 6-second ultrasounds of the right and left ovaries which will then be transmitted in a DICOM format to mask regional based recurrent neural network which is been trained and validated for follicle detection and quantification using curated transvaginal ultrasound images.
Minimum Age: 21 Years
Eligible Ages: ADULT
Sex: FEMALE
Healthy Volunteers: No
Coastal Fertility Specialists, Mount Pleasant, South Carolina, United States
Name: John A. Schnorr, MD
Affiliation: Cycle Clarity, Founder
Role: STUDY_CHAIR