The invention discloses a blood vessel guided wave elastic imaging method and system based on machine learning. The blood vessel guided wave elastic imaging method comprises the steps that numerical simulation is conducted on propagation of shear waves in a thin layer system of a blood vessel through finite element software, and a finite element analysis result is obtained; motion speed distribution of nodes in the whole field is obtained according to the finite element analysis result, the motion speeds of the nodes on the center line of a thin layer are extracted, and a frequency dispersioncurve is obtained to serve as an input signal of a neural network; and a training set and a test set of the neutral network are obtained according to the frequency dispersion curve, training is conducted through a neutral network method till the error on the training set is less than a preset value, and a blood vessel guided wave elastic imaged picture is obtained through the final neutral network. According to the blood vessel guided wave elastic imaging method, the measuring precision of blood vessel mechanical properties can be improved, good extensibility is achieved, in-vivo noninvasive rapid measurement of the blood vessel elastic property is achieved, operation is easy and convenient, and the measurement error is small.