Ultrasonic volume biological parameter measurement method and measurement system

Abstract

The invention provides an ultrasonic volume biological parameter measurement method and measurement system. The method is characterized by training a classifier; segmenting out an anatomical structurein input ultrasonic volume data based on a classifier; and obtaining anatomical structure volume according to the anatomical structure. The ultrasonic volume biological parameter measurement method and measurement system can reflect development situations of a fetus and related tissues on the whole, are less influenced by fetal position or fetus posture, and can make up for the deficiency of single-aspect evaluation of a conventional biological parameter measurement method.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method and system for measuring biological parameters of ultrasonic volume. Background technique [0002] Ultrasonic prenatal diagnosis is safe and non-destructive, and is widely used in the assessment of fetal growth status. At the same time, it also plays an important role in reducing the rate of congenital deformities, maternal mortality and fetal mortality, and plays a decisive role in improving the quality of my country's population. In the process of prenatal ultrasound diagnosis, the measurement of biological parameters is mainly used to predict gestational age, body weight and evaluate fetal development status, which is one of the most important and basic tasks in prenatal ultrasound. The most basic fetal biological parameters mainly include head circumference, biparietal diameter, abdominal circumference, and femur length. After obtaining these biologi...

AI Technical Summary

Problems solved by technology

Two-dimensional ultrasound is the most commonly used imaging mode in ultrasonic diagnosis. However, due to the large influence of human factors, prenatal diagnosis based on two-dimensional ultrasound inevitably presents differences between examiners and multiple measurements by the same examiner. lead to bias in prenatal diagnosis

The manual segmentation method is time-consuming and labor-intensive, and there are large user differences, so it is difficult to promote in clinical diagnosis

However, the existing semi-automatic segmentation methods usually use segmentation methods based on shape models or traditional machine learning methods. The main problem of these methods is that when faced with complex segmentation problems, the robustness and accuracy of segmentation cannot meet clinical requirements. Requires more intervention by clinical specialists

Images