Learning to Read Chest X-Ray Images from 16000+Examples Using CNN

被引：43

作者：

Dong, Yuxi ^{[1
]}

Pan, Yuchao ^{[1
]}

Zhang, Jun ^{[2
]}

Xu, Wei ^{[1
]}

机构：

[1] Tsinghua Univ, Inst Interdisciplinary Informat Sci, Beijing, Peoples R China

[2] Fourth Peoples Hosp Shaanxi, Radiol Dept, Xian, Shaanxi, Peoples R China

来源：

2017 IEEE/ACM SECOND INTERNATIONAL CONFERENCE ON CONNECTED HEALTH - APPLICATIONS, SYSTEMS AND ENGINEERING TECHNOLOGIES (CHASE) | 2017年

基金：

中国国家自然科学基金;

关键词：

DIAGNOSIS;

D O I：

10.1109/CHASE.2017.59

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Chest radiography (chest X-ray) is a low-cost yet effective and widely used medical imaging procedures. The lacking of qualified radiologist seriously limits the applicability of the technique. We explore the possibility of designing a computer-aided diagnosis for chest X-rays using deep convolutional neural networks. Using a real-world dataset of 16,000 chest X-rays with natural language diagnosis reports, we can train a multi-class classification model from images and preform accurate diagnosis, without any prior domain knowledge.

引用

页码：51 / 57

页数：7