Illustrative medical imaging for functional prognosis estimation

A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed by a computing device, causes the computing device to implement a medical record to illustrative medical image translation engine, wherein the computer readable program causes the computing device to:

• train the medical record to illustrative medical translation engine using dual neural machine translation to form a generative adversarial network (GAN);
• receive, by the medical record to illustrative medical image translation engine, a medical record batch from storage for a patient;
• generate, by the medical record to illustrative medical image translation engine, one or more predicted prognosis records based on the medical record batch using a neural network;
• convert, by the medical record to illustrative medical image translation engine, the one or more predicted prognosis records to an illustrative sequence of medical images using a first agent, wherein the illustrative sequence of medical images comprises a leaking swimming pool model of relapsing-remitting multiple sclerosis flare-ups;
• generate, by the medical record to illustrative medical image translation engine, a presentation of disease progression using the illustrative sequence of medical images;
• and
• output, by the medical record to illustrative medical image translation engine, the presentation to a user.

An apparatus comprising:

• at least one processor, and
• a memory coupled to the at least one processor, wherein the memory comprises instructions, which when executed by the at least one processor, cause the at least one processor to implement a medical record to illustrative medical image translation engine, wherein the instructions cause the at least one processor to:
• train the medical record to illustrative medical translation engine using dual neural machine translation to form a generative adversarial network (GAN);
• receive, by the medical record to illustrative medical image translation engine, a medical record batch from storage for a patient;
• generate, by the medical record to illustrative medical image translation engine, one or more predicted prognosis records based on the medical record batch using a neural network;
• convert, by the medical record to illustrative medical image translation engine, the one or more predicted prognosis records to an illustrative sequence of medical images using a first agent, wherein the illustrative sequence of medical images comprises a leaking swimming pool model of relapsing-remitting multiple sclerosis flare-ups;
• generate, by the medical record to illustrative medical image translation engine, a presentation of disease progression using the illustrative sequence of medical images;
• and
• output, by the medical record to illustrative medical image translation engine, the presentation to a user.