This invention discloses an
esophageal cancer lesion image assessment
system, comprising a basic
image processing module for generating initial
lesion area focus data from input esophageal images; a doctor interaction acquisition module for collecting doctor's correction operations on the initial
lesion area focus data; a
preference learning module for learning individual preference parameters corresponding to the doctor based on the correction operations; and a personalized output module for calibrating the initial lesion area focus data based on the individual preference parameters and outputting personalized lesion area focus data. This
esophageal cancer lesion image assessment
system improves the assessment process for
esophageal cancer lesions, reducing repetitive correction operations for doctors in handling consecutive cases, decreasing the additional
workload as the number of cases increases, and making the initial output more aligned with the doctor's interpretation methods, thereby improving the
overall efficiency of the assessment task.