The invention belongs to the technical field of intelligent
processing of medical images, and specifically relates to a method of detecting and identifying lesions of a gastrointestinal
endoscope, based on a sliding window. Early screening through
endoscopy is an effective means of reducing the morbidity and mortality of cancers of the
digestive tract. In traditional
diagnostic methods, the diagnosis of a doctor is entirely a subjective judgment process, so that diagnosis is limited and influenced by the experience and
knowledge level of the diagnostic doctor. Therefore, the method of detecting and identifying lesions of a gastrointestinal
endoscope, based on a sliding window includes the steps: applying
deep learning to
lesion detection of a gastrointestinal
endoscope, making a sample based on the frame of a
lesion area marked by a doctor, and training a classifier; and proposing a candidate area in a gastrointestinal endoscope image to be detected, inputting the candidate area into the classifier, and performing post-
processing on the
classification result to achieve the purpose of
lesion detection. The experiment result shows that the method of detecting and identifying lesionsof a gastrointestinal endoscope, based on a sliding window can accurately detect the lesion position of the gastrointestinal endoscope image so as to provide a reference for the doctor, thus showing that the
artificial intelligence-assisted diagnosis and treatment of early
digestive tract cancer has irreplaceable superiority.