期刊文献+

计算机辅助检测系统对数字化胸片中肺结节诊断的应用价值 被引量:7

The practice value of computer aided detection system on the diagnosis of pulmonary nodules in digital chest radiograph
原文传递
导出
摘要 目的评价计算机辅助检测(computer aided detection,CAD)系统对肺内单发结节的诊断价值。方法选取150例直径约9~30mm肺部单发结节的病例为试验组,所有肺结节病灶均经病理证实。另从健康体检人群中数字法随机抽取150例年龄、性别构成与受检组相仿的病例作为对照组。2组胸部X线片均经CT证实,并由多名放射学专家共同诊断。所有胸部X线片均通过数字化X线摄影(digital radiography,DR)获得。由5名高年资影像诊断医生和5名低年资影像诊断医生作为观测者,分别对不用和用CAD系统输出图像的胸部X线片进行诊断。观察者积分用受试者操作特性曲线(receiver operating characteristic curve,ROC曲线)分析来衡量。结果高年资影像诊断医生评价的平均ROC曲线下面积从不用CAD系统输出图像(0.821±0.001)与用CAD系统输出图像(0.834±0.016)进行比较,两者差异有统计学意义(P<0.05),低年资影像诊断医生评价的平均ROC曲线下面积从不用CAD系统输出图像(0.711±0.022)与用CAD系统输出图像(0.831±0.022)进行比较,两者差异有统计学意义(P<0.05)。结论运用DR所配置的CAD系统能帮助影像诊断医生提高对肺结节性病灶的检出率。 Objective To determine the effect of computer aided detection system on the diagnosis of pulmonary nodules. Methods For examined patients, 150 cases with solitary lung nodules up to 9 - 30 mm in diameter were used. All nodules had been verified by means of biopsy. For healthy patients, 150 cases were selected as control group on the basis of confirmation on the chest CT. All chest radiograph in the two groups were obtained with a digital radiography system. Five experienced chest radiologists and five residents detected the chest radiograph with or without CAD output images. The scales of performance was evaluated with receiver operating characteristic curve analysis. Results For the experienced chest radiologists, the average area under the curve value increased significantly from (0. 821 ±0. 001 ) to(0. 834 ± 0.016) with CAD output images. For the residents, the average area under the curve value increased significantly from (0. 711 ± 0. 022) to (0. 831 ± 0. 022) with CAD output images. Conclusion This CAD system for digital radiograph can assist radiologist and has the potential to improve the detection of lung nodules.
出处 《中华放射学杂志》 CAS CSCD 北大核心 2005年第10期1092-1094,共3页 Chinese Journal of Radiology
  • 相关文献

参考文献8

  • 1MacMahon H, Engelmann R , Behlen FM , et al. Computer-aided diagnosis of pulmonary nodules: rusults of a large-scale observer test.Radiology, 1999, 213:723-726.
  • 2Kakeda S, Moriya J, Sato H, et al. Improved detection of lung nodules on chest radiographs using a commercial computer-aided diagnosis system. AJR , 2004 ,182:505-510.
  • 3段刚,陈卫国,王江云,黄信华,王勇,卢伟.数字化放射成像与普通X线诊断肺内单发结节的ROC曲线评价[J].第一军医大学学报,2003,23(6):621-623. 被引量:10
  • 4孙军,陈峰,郑凯尔.ROC曲线分析在放射学中的应用[J].中华放射学杂志,2001,35(8):574-577. 被引量:107
  • 5袁聿德 冯树理.X线诊断影像质量评价进展[J].中华放射学杂志,1997,31:80-82.
  • 6Obuchowski NA. Receiver operating characteristic curves and their use in radiology. Radiology , 2003,229:3-8.
  • 7Shiraishi J, Abe H , Engelmann R , et al . Computer-aided diagnosis to distinguish benign from malignant solitary pulmonary nodules on radiographs: ROC analysis of radiologists′ performance--initial experience. Radiology, 2003,227:469-474.
  • 8Johkoh T , Kozuka T , Tomiyama N, et al .Temporal subtraction for detection of solitary pulmonary nodules on chest radiographs: evaluation of a commercially available computer-aided diagnosis system. Radiology , 2002,223 :806-811.

二级参考文献15

  • 1[1]Paurazas SB, Geist JR, Pink FE, et al. Comparison of diagnostic accuracy of digital imaging by using CCD and CMOS-APS sensors with E-speed film in the detection of periapical bone lesions [J]. Oral Surg Oral Med Oral Pathol Oral Radiol Endod, 2000, 89(3): 356-62.
  • 2[2]Hanley JA, Mencil BJ. The meaning and use of the area under a recei ver operating characteristic (ROC) curve [J]. Radiology, 1982, 143 (1): 29-36.
  • 3[3]Johkoh T, Kozuka T, Tomiyama. Temporal subtraction for detection of solitary pulmonary nodules on chest radiographs: evaluation acommercially available computer-aided diagnosis system [J]. Radiology, 2002, 223(3): 806-11.
  • 4[4]Kullendorff B, Petersson K, Rohlin M. Direct digital radiography for the detection ofperiapical bone lesions: a clinical study[J]. Endod Dent Traumatol, 1997, 13(4): 183-9.
  • 5[7]Lawrence R, Goodman MD, Foley WD, et al. Digital and conven tional chest images: observer performance with film digital radiography system[J]. Radiology, 1986, 158(1): 27-33.
  • 6[8]Austin JH, Romney BM, Goldsmith LS. Missed bronchogenic carci noma: radiographic findings in 27 patients with a potentially respec table lesion evident in retrospect [J]. Radiology, 1992, 182 (1): 115-22.
  • 7[9]Kundel HL, Revesz G. Lesion conspicuity, structured noise, and filmreader error[J]. AJR Am J Roentgenol, 1976, 126(6): 1233-8.
  • 8[10]Sherrier RH, Chiles C, Johnson GA, et ad. Differentiation of benign from malignant pulmonary nodules with digitized chest radiographs [J]. Radiology, 1987, 162(3): 645-9.
  • 9Ward J,Radiology,2000年,214卷,159页
  • 10高培毅,中华放射学杂志,2000年,34卷,240页

共引文献116

同被引文献84

引证文献7

二级引证文献21

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部