Marking systems, methods, devices, and storage media for intestinal valve imaging

A system, comprising:

• at least one storage device including a set of instructions;
• at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to cause the system to perform operations including:
• obtaining multiple intestinal images of an examined object;
• performing intestinal valve segmentation on at least a portion of the multiple intestinal images to determine at least one independent intestinal valve;
• and
• marking the at least one independent intestinal valve in the at least a portion of the multiple intestinal images, wherein
• the at least one independent intestinal valve includes one or more independent intestinal valves including no lesion and one or more independent intestinal valves including lesion,
• each of the one or more independent intestinal valves including no lesion is marked by a first mark, and
• each of the one or more independent intestinal valves including lesion is marked by a second mark, the first mark and the second mark having different forms.

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

• obtaining multiple intestinal images of an examined object;
• performing intestinal valve segmentation on at least a portion of the multiple intestinal images to determine at least one independent intestinal valve;
• and
• marking the at least one independent intestinal valve in the at least a portion of the multiple intestinal images by:
• for each of the at least one independent intestinal valve, determining a specific intestinal image in which the independent intestinal valve first appears;
• and
• numbering the at least one independent intestinal valve in an order according to a sequential order of the specific intestinal image in which each independent intestinal valve first appears.

A non-transitory computer readable medium, comprising at least one set of instructions, wherein when executed by at least one processor of a computing device, the at least one set of instructions causes the at least one processor to effectuate a method comprising:

• obtaining multiple intestinal images of an examined object;
• performing intestinal valve segmentation on at least a portion of the multiple intestinal images by a segmentation model to determine at least one independent intestinal valve, wherein the segmentation model includes a machine learning model that segments the at least a portion of the multiple intestinal images to determine edges of the at least one independent intestinal valve;
• and
• marking the at least one independent intestinal valve in the at least a portion of the multiple intestinal images, wherein
• the segmentation model is determined by training a preliminary segmentation model based on a plurality of training samples,
• for each of the plurality of training samples
• the training sample includes a sample intestinal image,
• a label of the training sample includes a sample initial segmented image corresponding to the sample intestinal image, and
• edges of sample intestinal valves in the sample initial segmented image are thickened.