The invention relates to the technical field of
medical systems, in particular to a
typing and grading
system for
chronic venous insufficiency. Comprising a
data acquisition module configured to acquire
patient data of
chronic venous insufficiency, a shared
feature extraction module configured to output a shared
feature vector, an attention
perception module configured to generate a weighted
feature vector, a multi-task classification and classification model output module configured to construct a multi-task classification and classification model based on Softmax, and a classification and classification model output module configured to generate a classification and classification model based on Softmax. The method comprises the steps that a patient to be estimated is trained, pre-
treatment parameters and
individual data corresponding to weighted feature vectors of the patient to be estimated are input, a first task head outputs an anatomical type of
chronic venous insufficiency, and a second task head outputs a CVI grade of chronic venous insufficiency; according to the method, full-process assistance of CVI from
typing and grading to treatment recommendation is realized, dynamic guide updating is combined, accuracy and clinical applicability are considered, and doctors can be effectively assisted to improve diagnosis and treatment efficiency.