一种4D超声的质量控制方法、设备及程序产品
By using a quality assessment model and a lightweight convolutional neural network to score and adjust 4D ultrasound data, the problems of unquantified imaging quality and insufficient real-time performance in portable ultrasound imaging are solved. This enables automatic optimization of imaging quality and efficient utilization of hardware resources, thereby enhancing its clinical application value.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- THE FIRST AFFILIATED HOSPITAL OF WENZHOU MEDICAL UNIV
- Filing Date
- 2026-03-26
- Publication Date
- 2026-07-17
AI Technical Summary
Existing portable ultrasound imaging technology lacks imaging quality control, resulting in the absence of quantitative standards for imaging quality, invalid data consuming hardware resources, and the lack of quality feedback mechanisms, which affects its clinical application value and real-time performance.
A quality assessment model is used to score and classify 4D ultrasound data streams. Imaging parameters are automatically adjusted or a rescan is prompted through gating quality judgment. Feature extraction and quality assessment are performed by combining a lightweight convolutional neural network with self-supervised pre-training and supervised fine-tuning.
It enables quantitative assessment and automatic optimization of 4D ultrasound imaging quality, improves the accuracy and real-time performance of imaging quality, reduces hardware resource consumption, and enhances clinical examination efficiency and diagnostic accuracy.
Smart Images
Figure CN121904565B_ABST