Systems and methods for image generation

A method implemented on a computing device having at least one processor and at least one storage device, the method comprising:

• obtaining a first image of a subject of a first modality, the first image including a first region and a second region, the first region including a representation of a first portion of the subject, and the second region including a representation of a second portion of the subject;
• obtaining a second image of the subject of a second modality, the second image including a third region, the third region including a representation of the first portion of the subject, and the second image lacking a representation of the second portion of the subject;
• obtaining a trained machine learning model;
• and
• generating, based on the first image and the second image, a synthesized second image using the trained machine learning model, wherein the synthesized second image includes a fourth region and the third region, the fourth region including a representation of the second portion of the subject, and the third region including a representation includes the first portion of the subject.

A system, comprising:

• at least one storage device storing executable instructions, and
• at least one processor in communication with the at least one storage device, when executing the executable instructions, causing the system to perform operations including:
• obtaining multiple groups of training samples, each group of the multiple groups of training samples corresponding to an object;
• and
• generating a trained machine learning model by training a machine learning model using the multiple groups of training samples,
• wherein for each group of the multiple groups of training samples includes a reference image and a pair of a first image and a second image of different modalities, the first image and the second image serve as an input of the machine learning model and the reference image serves as a desired output of the machine learning model during a training process of the machine learning model, the first image including a complete representation of the object, and the second image including a partial representation of the object, and the reference image including a complete representation of the object corresponding to the second image.