Coronary intimal boundary segmentation method based on adjacent frame consistency

The invention discloses a coronary intimal boundary segmentation method based on adjacent frame consistency. The method comprises the following steps: acquiring an OCT image to be detected and inputting the OCT image to a deep learning network; a cavity convolution module based on multi-scale dense link extracts image features and establishes a corresponding relation between the optical coherence tomography image and the coronary intima; calculating the consistency of adjacent frames in the optical coherence tomography image based on an adjacent frame information supplement module, and obtaining an adjacent frame supplement relation; and outputting an intimal boundary segmentation boundary result according to the corresponding relationship between the optical coherence tomography image and the coronary intima and the adjacent frame supplementary relationship. By using the method, the coronary intima boundary can be quickly and accurately segmented. The coronary intimal boundary segmentation method based on ad