Evaluation of ovarian microvascular structure in PCOS patients based on high-resolution ultrasound imaging technology

Polycystic Ovary Syndrome (PCOS) patients often have ovarian microcirculatory disorders. Traditional color Doppler imaging of microvascular is not sensitive enough and is prone to missed detection or artifact interference. This study is based on a high-frequency probe combined with SMI (Superb Microvascular Imaging) and ultrasound contrast imaging to achieve high signal-to-noise ratio acquisition and dynamic quantification of low-speed blood flow in microvascular, filling the gap in existing technology. This study sets low-pass filtering and low PRF (Pulse Repetition Frequency) to enhance the detection of low-speed flow signals in microvascular. SMI and CEUS (Contrast-Enhanced Ultrasound) sequences are collected in sequence, and the time points are calibrated synchronously on the same section to achieve multimodal image fusion. The ovarian area is semi-automatically segmented based on the U-Net model, and the ROI (Region of Interest) containing the vascular structure is extracted. The vascular density, average diameter, and number of branches are calculated using self-developed image analysis software, and the feature vector is derived. The CEUS time-intensity curve is fitted with a double exponential, and dynamic perfusion parameters such as peak time and perfusion half-life are extracted for microcirculation evaluation and hemodynamic analysis. The experiment shows that in the 10 ovarian ROIs analyzed, the vascular density ranges from 5.43 % to 8.45 %; the average diameter is 5.88 to 6.52 pixels; the branch number consistency difference rate is less than 3 %. The perfusion half-life is distributed between 21.8 and 25.1 s, and the peak time of the PCOS group is delayed by 0.5 s compared with the normal group, indicating that there are significant differences in their microvascular structure and perfusion function.