摘要
肝穿刺病理学检查主要在医学中用于各种肝脏疾病的鉴别与诊断,了解肝脏病变的程度和活动性,发现早期、静止期或尚在代偿期的肝硬化,判别临床治疗。卷积神经网络作为深度学习的一个重要组成部分,在图像识别方面有很多重要应用。针对肝穿刺图像分类中病理图像分类问题,提出一种基于卷积神经网络的分类方法。设计并训练卷积神经网络,得到用于分类的模型。实验结果表明,该方法可以有效地对其进行分类,提高识别准确率。
Liver biopsy is mainly used for the identification and diagnosis of various liver diseases in medicine. It was used to diag-nose the degree and activity of liver lesions, and to detect early, static or compensatory cirrhosis of the liver, and to identify clinicaltreatment. As an important part of deep learning, convolution neural network has many important applications in image recognition.A method based on convolution neural network was proposed to classify the pathological images in liver biopsy image classification.The experimental results show that this method can effectively classify and improve the recognition accuracy.
作者
王岩
WANG Yan （Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China）
出处
《电脑知识与技术》
2018年第9期203-205,共3页
Computer Knowledge and Technology
关键词
肝穿刺图像
卷积神经网络
深度学习
图像识别
人工智能
liver biopsy image
convolution neural network
deep learning
image recognition
artificial intelligence
