At present, heart disease not only has a significant impact on the quality of human life but also poses a greater impact on people’s health. Therefore, it is very important to be able to diagnose heart disease as early as possible and give corresponding treatment. Heart image
segmentation is the primary operation of intelligent heart disease diagnosis. The quality of segmentation directly determines the effect of intelligent diagnosis. Because the running time of image segmentation is often longer, coupled with the characteristics of cardiac MR imaging technology
and the structural characteristics of the cardiac target itself, the rapid segmentation of cardiac MRI images still has challenges. Aiming at the long running time of traditional methods and low segmentation accuracy, a medical image segmentation (MIS) method based on particle swarm optimization
(PSO) optimized support vector machine (SVM) is proposed, referred to as PSO-SVM. First, the current iteration number and population number in PSO are added to the control strategy of inertial weight λ to improve the performance of PSO inertial weight λ. Find the
optimal penalty coefficient C and γ in the gaussian kernel function by PSO. Then use the SVM method to establish the best classification model and test the data. Compared with traditional methods, this method not only shortens the running time, but also improves the segmentation
accuracy. At the same time, comparing the influence of traditional inertial weights on segmentation results, the improved method reduces the average convergence algebra and shortens the optimization time.
A Multi-Task Cross-Task Learning Architecture for Ad Hoc Uncertainty Estimation in 3D Cardiac MRI Image Segmentation