This invention relates to the field of
ultrasound imaging diagnostic technology, and discloses a method and
system for diagnosing
adenomyosis based on multi-parameter
ultrasound imaging of the
cervix. The method utilizes a transvaginal probe to acquire two-dimensional
grayscale, shear wave elasticity, and ultra-micro
blood flow images of the
cervix. An anatomical coordinate
system is established based on the longitudinal axis of the
cervical canal in the
grayscale image, and multiple independent quantitative analysis sub-regions covering the internal os and mid-segment of the
cervix are identified as measurement target areas within the cervical
parenchyma. Young's modulus, reflecting tissue stiffness, and resistance index, reflecting microcirculatory resistance, are extracted from the elasticity and
blood flow images, respectively. The extracted parameters are input into a multivariate
logistic regression diagnostic model, and the probability value of
disease risk is calculated based on weighted coefficients, outputting a classification conclusion. This invention overcomes the limitations of morphological diagnosis through a standardized target area localization strategy and multi-
modal parameter joint modeling, achieving objective quantitative diagnosis of
adenomyosis and improving the accuracy and
repeatability of detection.