You Position: Home > Paper
Feasibility of computer-aided nodule detection system in digital chest radiographs
( views:232, downloads:128 )
- Author:
- No author available
- Journal Title:
- CHINESE JOURNAL OF RADIOLOGY
- Issue:
- 11
- DOI:
- 10.3760/j.issn:1005-1201.2007.11.005
- Key Word:
- 硬币病变,肺;X线摄影术;图像处理,计算机辅助
Abstract： 目的 评价计算机辅助检测(computer-aided detection,CAD)系统在数字化胸片肺结节检出中的应用价值及其对放射科医师的辅助作用.方法 选取数字化胸片328例.由2名专家组医师应用IQQATM-Chest系统阅读具有结节样阴影的胸片,2人意见达成一致后标记结节的位置和大小并保存标记结果 ,将标记结果 作为金标准来评估CAD系统检测肺结节的能力.由8名不同年资的放射科医师首先独立阅读具有结节样阴影的数字X线摄影(DR)胸片并保存诊断结果 ,然后再应用CAD系统阅读胸片,将最终结果 存入CAD系统.应用受试者操作特征曲线(ROC)和配对t检验来分析放射科医师应用CAD系统前后在肺结节检测能力上的差异.结果 在100例DR胸片中,金标准结节151个,CAD系统肺结节检测敏感性为78.1%(118.0/151),低年资放射科医师不用和应用CAD系统时,肺结节的检测敏感性分别为62.4%(94.2/151)和77.4%(116.8/151),ROC曲线下面积分别为0.769和0.836,二者之间的差异具有统计学意义(P＜0.01);高年资放射科医师不用和应用CAD系统时,肺结节的检测敏感性分别为73.8%(111.5/151)和76.2%(115.0/151),ROC曲线下面积分别为0.820和0.827,二者之间的差异无统计学意义(P＞0.05).结论 CAD系统能够辅助放射科医师提高肺小结节的检测敏感性,对低年资医师的帮助更大.
- [1]孙军,陈峰,郑凯尔.ROC曲线分析在放射学中的应用[J].2001,(8).
- [2]Doi K,Engelmann R,Suzuki K,etc.Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification.[J].2006,33(7).
- [3]Loog M,Schilham AM,van Ginneken B.A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database.[J].2006,10(2).
- [4]MacMahon H,Engelmann R,Doi K,etc.Computer-aided diagnosis to distinguish benign from malignant solitary pulmonary nodules on radiographs: ROC analysis of radiologists' performance--initial experience.[J].2003,227(2).
- [5]Obuchowski NA.Receiver operating characteristic curves and their use in radiology.[J].2003,229(1).
- [6]Ishida T,MacMahon H,Li Q,etc.Computer-aided diagnosis in chest radiography: results of large-scale observer tests at the 1996-2001 RSNA scientific assemblies.[J].2003,23(1).
- [7]Jemal A,Tiwari RC,Ghafoor A,etc.Cancer statistics, 2005.[J].2005,55(1).
- [8]MacMahon H,Engelmann R,Doi K,etc.Computer-aided diagnosis for the detection and classification of lung cancers on chest radiographs ROC analysis of radiologists' performance.[J].2006,13(8).
- [9]Li F,Doi K,Shiraishi J.Computer-aided diagnosis for improved detection of lung nodules by use of posterior-anterior and lateral chest radiographs.[J].2007,14(1).
- [10]Junji, Shiraishi,Hiroyuki, Abe,Roger, Engelmann,etc.Effect of high sensitivity in a computerized scheme for detecting extremely subtle solitary pulmonary nodules in chest radiographs: observer performance study.[J].2003,10.