Intracranial hemorrhage detection algorithm applied to CT image based on CNN and NLSTM neural network

Abstract

The invention discloses an intracranial hemorrhage detection algorithm applied to a CT image based on a CNN and an NLSTM neural network, and belongs to the field of intelligent medical image processing. A CNN neural network is used to extract picture features of the CT image. Before the CNN features are extracted, the CNN neural network is also trained, and the pre-trained CNN network used in themethod is ResNeXt. The extracted embeding of the image is combined with the sequence information of the patient to serve as the input of the NLSTM neural network, a loss back propagation network is calculated through a cross entropy loss function, and a network structure for testing is finally obtained. The mode of combining the CNN and the RNN neural network is very suitable for processing CT sequence images, and the CNN and the NLSM are novel intracranial hemorrhage detection and classification methods. The intracranial hemorrhage detection algorithm based on the combination of the CNN and the NLSTM is an accurate and efficient automatic hemorrhage detection and classification algorithm, has an extremely important value for clinic, and has a wide application scene.

Description

technical field [0001] The invention belongs to the field of intelligent medical image processing, and in particular relates to an intracranial hemorrhage detection algorithm applied to CT images based on CNN and NLSTM neural networks. Background technique [0002] Deep learning is one of the latest trends in machine learning and artificial intelligence research. It is also one of the most popular scientific research trends today. Deep learning methods have revolutionized computer vision and machine learning. In recent years, deep learning methods have received extensive attention in medical image processing. For some specific tasks, deep learning methods have been shown to match or exceed the performance of medical experts. [0003] Intracranial hemorrhage (ICH) refers to hemorrhage caused by rupture of blood vessels in the brain. As a result, brain cells that receive blood from blood vessels are destroyed, and at the same time, the surrounding nerve tissue is compressed...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that current CT image evaluation of intracranial hemorrhage is time-consuming and highly dependent on the professionalism of doctors, and to provide a detection and classification algorithm for intracranial hemorrhage based on CNN and NLSTM neural network applied to CT images

Images