Systems and methods for generating augmented segmented image set

A system, comprising:

• a non-transitory storage medium storing a set of instructions;
• a processor in communication with the non-transitory storage medium, wherein when executing the set of instructions, the processor is directed to:
• obtain a first image of an object associated with a treatment plan, the first image including a first anatomical structure of a first object from a treatment planning phase;
• determine first feature data of the first anatomical structure;
• determine one or more first transformations related to the first anatomical structure, wherein a first transformation includes a transformation type and one or more transformation parameters related to the transformation type, and the transformation type includes at least one of a displacement of an anatomical structure, a rotation of the anatomical structure, a deformation of the anatomical structure, an appearance of an extra structure, and a disappearance of partial of the anatomical structure;
• apply the one or more first transformations to the first feature data of the first anatomical structure to generate second feature data of the first anatomical structure;
• and
• generate one or more second images based on the second feature data of the first anatomical structure;
• generate an trained model based on an initial model and a training image set including one or more second images;
• obtain a treatment image of the object before or during or after radiotherapy but after the treatment planning phase;
• generate an image with segmented information based on the trained model and the treatment image.

A method for generating training data, the method comprising:

• obtaining a planning image including a first anatomical structure of a first object;
• determining first feature data of the first anatomical structure;
• determining one or more first transformations related to the first anatomical structure under one or more associated constraints, wherein a first transformation includes a transformation type and one or more transformation parameters related to the transformation type, and the transformation type includes at least one of a displacement of an anatomical structure, a rotation of the anatomical structure, a deformation of the anatomical structure, an appearance of an extra structure, and a disappearance of partial of the anatomical structure;
• applying the one or more first transformations to the first feature data of the first anatomical structure to generate second feature data of the first anatomical structure;
• and
• generating an artificial image based on the second feature data of the first anatomical structure, the artificial image being used as the training data.