论著摘要 |【CT】经影像组学对肺结节的计算机检测(双语版)

2017-09-03 09:53:37 admin 30

Computerized detection of lung nodules through radiomics.

发表日期: 2017.8.3   来源:Med Phys.

作者:Ma J1Zhou Z2Ren Y1Xiong J1Fu L1Wang Q1Zhao J1.

作者介绍

    1.School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.

    2.Department of Radiology, School of Medicine, Ren Ji Hospital, Shanghai Jiao Tong University, Shanghai, 200127, China.

目的

肺癌是癌症死亡的一大主要原因,IV期肺癌患者的5年生存率仅为2%。然而,I期肺癌患者的5年生存率显著增加至50%。因此,螺旋计算机断层扫描(CT)扫描是早期诊断高危肺癌患者所必需的。在这项研究中,提出了一种基于影像组学的计算机辅助检测(CAD)系统,该系统可以自动检测肺结节,减少放射科医师的工作量和人为错误

Lung cancer is a major cause of cancer deaths, and the 5-year survival rate of stage IV lung cancer patients is only 2%. However, the 5-year survival rate of stage I lung cancer patients significantly increases to 50%. As such, spiral computed tomography (CT) scans are necessary to diagnose high-risk lung cancer patients in early stages. In this study, a computer-aided detection (CAD) system with radiomicswas proposed. This system could automatically detect pulmonary nodules and reduce radiologists' workloads and human errors.

方法

在提出的方案中,使用结节增强滤波器分割结节候选物并提取影像组学特征,并应用少数样本合成过采样技术平衡样本,采用随机森林法区分真实结节和假阳性检测。影像组学方法可以量化与肺结节高度相关的肿瘤内异质性和多发性信息。



In the proposed scheme, a nodular enhancement filter was used to segment nodule candidates and extract radiomic features. A synthetic minority over-sampling technique was also applied to balance the samples, and a random forest method was utilized to distinguish between real nodules and false positive detections. The radiomics approach quantified intratumor heterogeneity and multifrequency information, which are highly correlated with lung nodules.

结果

提出的方法用于评估来自知名肺图像数据库联盟的1004CT病例,通过随机选择502例训练过的和502例其他的检测病例,灵敏度88.9%,每次CT扫描检测4次假阳性。



The proposed method was used to evaluate 1004 CT cases from the well-known Lung Image Database Consortium, and 88.9% sensitivity with four false positive detections per CT scan was obtained by randomly selecting 502 cases for training and 502 other cases for testing.

结论

所提出的方案在LIDC数据库中产生了高性能。因此提出的方案对于常规诊断和肺癌筛查中使用的各种CT配置可能是有效的。



The proposed scheme yielded a high performance on the LIDC database. Therefore, the proposed scheme is possibly effective for various CT configurations used in routine diagnosis and lung cancer screening.

关键词

计算机辅助检测,肺结节检测, 影像组学,随机森林法,少数样本合成过采样技术

CAD ; lung nodule detection; radiomics; random forest; synthetic minority over-sampling


阅读原文:10.1002/mp.12331

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
  • 人工智能诊断云平台