The invention discloses a mare
follicle development noninvasive real-time monitoring method and
system based on multi-parameter fusion, and relates to the crossing field of
animal breeding technology and
medical imaging technology. The method comprises the following steps: transmitting ultrasonic
waves to mare ovarian tissues through a monitoring
assembly, receiving reflection echoes, generating two-dimensional / three-dimensional ultrasonic image data of ovarian follicles and
endometrium, and collecting temperature data and
light intensity time sequence data; the received ultrasonic image data, temperature data and
light intensity time sequence data are preprocessed respectively, and
follicle parameters, endometrial parameters,
pelvic cavity temperature parameters and ovarian
peripheral tissue
blood flow related parameters are obtained; and constructing a multi-parameter fusion model, inputting the obtained
follicle parameters, endometrial parameters,
pelvic cavity temperature parameters and
blood flow related parameters into the model, carrying out
feature fusion by adopting a
deep learning architecture, and outputting a mare follicle development stage
evaluation result and an
ovulation time prediction value. According to the invention, injury, infection and stress risks caused by invasive operation can be avoided, and long-term multi-time monitoring can be realized.