The present invention belongs to the field of intelligent
medical treatment, and specifically relates to a method, device, and program product for constructing an enophthalmos
lesion volume assessment model. The method comprises: obtaining an image set of an enophthalmos patient; annotating the image set to obtain the orbital tissue area boundaries of the healthy side and the affected side, wherein the orbital tissue includes the eyeball, orbital fat, and any one or more of the following:
extraocular muscles,
optic nerve,
cornea, and
lacrimal gland; extracting the orbital tissue volumes of the healthy side and the affected side based on the orbital tissue area boundaries, and calculating the orbital
tissue volume changes of the affected and healthy sides; using the image set as a training
data set, and the orbital
tissue volume changes as a prediction target input into a neural
network model, and obtaining an enophthalmos
lesion volume assessment model after training. The present application takes into account the changes in the finely divided orbital
tissue volume, and at the same time integrates the
relative volume changes, so as to more accurately quantify the amount of enophthalmos lesions and achieve better correction effects after
surgery.