论著摘要 |【AI-CT】一种从脑CT图像中自动检测脑血管意外事故的智能支持系统(双语版)

2018-01-17 11:22:09 admin 0
标签:  神经网络 CT 脑血管 大脑 多目标遗传算法 人工神经网络

An intelligent support system for automatic detection of cerebral vascular accidents from brain CT images.

发表日期: 2017.05.20   来源:Comput Methods Programs Biomed. 2017 Jul;146:109-123.

作者:

Hajimani E1, Ruano MG2, Ruano AE3.

作者介绍:

1. Faculty of Science and Technology, University of Algarve, Faro, Portugal. Electronic address: a48669@ualg.pt.

2. Faculty of Science and Technology, University of Algarve, Faro, Portugal and CISUC, University of Coimbra, Portugal. Electronic address: mruano@ualg.pt.

3. Faculty of Science and Technology, University of Algarve, Faro, Portugal and IDMEC, Instituto Superior Técnico, University of Lisbon, Portugal. Electronic address: aruano@ualg.pt.

摘要

Abstact

目的

本文提出了一种基于径向基函数神经网络(RBFNN)的检测系统,通过分析计算机断层扫描(CT)图像来自动识别脑血管意外事故(CVA)。

Objective

This paper presents a Radial Basis Functions Neural Network (RBFNN) based detection system, for automatic identification of Cerebral Vascular Accidents (CVA) through analysis of Computed Tomographic (CT) images.

方法

为了神经网络分类器的设计,使用一个多目标遗传算法(MOGA)框架来确定分类器的体系结构与其相应的参数和输入特征,分类精度最大化,同时保证泛化。该方法考虑了大量的输入特征,包括一阶和二阶像素强度统计,以及关于理想的中矢状线的对称/不对称信息。

Methods

For the design of a neural network classifier, a Multi Objective Genetic Algorithm (MOGA) framework is used to determine the architecture of the classifier, its corresponding parameters and input features by maximizing the classification precision, while ensuring generalization. This approach considers a large number of input features, comprising first and second order pixel intensity statistics, as well as symmetry/asymmetry information with respect to the ideal mid-sagittal line.

结果

在神经放射学家标记的一组150个CT切片(1,867,602个像素)中,通过由MOGA生成的非主导模型的集合,在像素水平获得了98%的特异性和98%的灵敏度的值。 这种方法也与其他三种已发表的解决方案相比,在特异性(86%比84%),显著病变符合度(89%比77%)和分类准确率(96%比88%)上均有优势。

Results

Values of specificity of 98% and sensitivity of 98% were obtained, at pixel level, by an ensemble of non-dominated models generated by MOGA, in a set of 150 CT slices (1,867,602pixels), marked by a NeuroRadiologist. This approach also compares favorably at a lesion level with three other published solutions, in terms of specificity (86% compared with 84%), degree of coincidence of marked lesions (89% compared with 77%) and classification accuracy rate (96% compared with 88%).

关键词:

脑血管意外;智能支持系统;多目标遗传算法;神经网络;对称特征

Keywords:

Cerebral vascular Accident; Intelligent support systems; Multi-objective genetic algorithm; Neural networks; Symmetry features

阅读原文:PMID: 28688480  DOI: 10.1016/j.cmpb.2017.05.005


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片