Blood vessel narrow area detection method and system based on ICG fluorescence image

The invention discloses a blood vessel narrow area detection method and system based on an ICG fluorescence image, and belongs to the technical field of image processing. According to a dense U-Net deep neural network model, and the dense U-Net deep neural network model contains a convolution LSTM module, a label of a single image and time sequence information contained in front and back frames of an image adjacent to the image can be extracted so as to adapt to the characteristic that fluorescence development in the task has flowability, and the requirement for labeling work is small. Dense U-Net deep neural network model training is carried out based on the labeled fluorescence image, the shape and position of the blood vessel are determined, the position of the blood vessel narrow area is determined according to the shape of the blood vessel, and the recognition accuracy is improved. The dense connection structure added in the dense U-Net deep neural network model can make the utilization of multi-scale fe