Cerebrovascular image segmentation method based on multi-scale attention network

• Main Authors: ZHOU QIANWEI, ZHANG ZEHAN, LOU HAIYAN, XU XINLI, JIANG WEIWEI, YANG ZHIQIANG, GUAN QIU, HU HAIGEN, LI ZHICHENG
• Format: Patent
• Language: Chinese; English
• Published: 08.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a cerebrovascular medical image segmentation method based on a multi-scale attention network, and the method comprises the steps: firstly carrying out the preprocessing of an original cerebrovascular MRA image, and then training a multi-scale attention UNet network; the coding part on the network model extracts the features of the cerebrovascular image through a multi-scale attention module, and the learning ability of effective features is improved; in the decoding part, multi-scale features are fused through step-by-step connection, so that the accuracy of model segmentation is improved; and finally, inputting to-be-segmented test data into the trained model to obtain a segmentation result, and performing three-dimensional reconstruction. According to the method, the complex characteristics of the brain blood vessels in the brain image are considered, the network model is pointedly put forward to carry out segmentation and three-dimensional reconstruction on the brain blood vessel im