期刊文献+

计算机辅助检测系统提高CT肺结节检出方式的研究 被引量:4

Study of Improve the Detection Mode of CT Pulmonary Nodules by Computer Aided Detection
下载PDF
导出
摘要 目的:通过对比研究计算机辅助检测系统(CAD)作为第二阅读者、同步阅读者筛查肺结节的方式,探索到适合临床推广应用的CAD辅助方式。方法:纳入60例MDCT检查肺部有结节的体检者。4位放射科医生阅读图像3次并进行标记,同时采用计时器计算时间。第一次,医生无CAD辅助方式阅片;第二次,CAD辅助医生作为同步阅读者(CR)方式阅片;第三次,CAD辅助医生作为第二阅读者(SR)方式阅片。结节参照标准由3名主任医生共同拟定。分别使用χ2检验、秩和检验分析两种阅读方式灵敏度及阅片时间是否存在差异,P<0.05有统计学差异。结果:根据参照标准共检出253个结节。放射科医生使用CAD作为CR(87.75%,P<0.001)、SR(88.84%,P<0.001)方式检测肺结节灵敏度显著高于无CAD辅助方式阅片(68.58%)。CR和SR方式检测肺结节灵敏度之间没有显著差异(P=0.30)。放射科医生CR(97±38s)方式阅片时间明显少于无CAD辅助方式阅片(128±45s,P<0.001)及SR方式(169±53s,P<0.001)。结论 :CAD作为同步阅读者、第二阅读者方式在MDCT筛查肺结节中均可显著提高放射科医生检测肺结节的灵敏度,且同步阅读者方式工作效率高,可以作为医生检测肺结节的首选辅助方式。 Purpose: By comparing concurrent-reader and second-reader modes of computer-aided detection(CAD) for screening pulmonary nodules, to investigate a possible mode for CAD, which can be widely applied in the clinic. Methods: Sixty subjects diagnosed with lung nodules undergoing the rountine-dose screening CT examination were selected. Four radiologists independently interpreted these datasets three times and marked all detected nodules and recorded the reading time simultaneously. For the first time, these radiologists read these scans without CAD;The second time, CAD was refered as concurrent readers helped them reading scans. The last time, CAD was used as the second reader assisted these radiologists reading scans.The ground truth of nodules in the datasets was determined by three raiologists. χ2 test and rank-sum test were performed to test whether there was significant difference between the sensitivities of two reading modes, and statistical significances were defined as P〈0.05. Results: According to theground truth,these three radiologists found out 253 nodules. The sensitivities of pulmonary nodule detection with CR(87.75%, P0.001) and SR(88.84%, P0.001) were significantly higher than the sensitivity of pulmonary nodule detection without CAD(68.58%). There was no significant diffrernce of sensitivity between CR and SR(P=0.30). The reading time was significantly less in CR mode(97±38 s) than that in independently reading(128± 45 s, P〈0.001) and SR mode(169±53s, P〈0.01). Conclusion: Two reading modes of CAD(CR, SR) can significantly increase the sensitivities of radiologists. The efficiency is higher by CR mode than that by SR mode. CR mode can be used as the first option to detect pulmonary nodules by radiologists.
出处 《中国医学计算机成像杂志》 CSCD 北大核心 2016年第2期116-120,共5页 Chinese Computed Medical Imaging
基金 上海市科学技术委员会资助项目No.13DZ2250300~~
关键词 肺结节 体层摄影术 X线计算机 计算机辅助检测 Pulmonary nodule X-ray computed Computer-aided detection
  • 相关文献

参考文献14

  • 1Doi K,Heber MM,Shigehiko K, et al.Computer-aided diagnosis in radiology: potential and pitfalls. European Journal of Radiology,1997,31: 97-109.
  • 2White CS, Pugatch R, Koonce T ,et al.Lung nodule CAD software asa second reader: a multicenter study.Acad Radiol, 2008,15:326-333.
  • 3Sahiner B, Chan HP, Hadjiiski LM, et al. Effect of CAD on radiologists' detection of lung nodules on thoracic CT scans: analysis of an observer performance study by nodule size. Academic Radiology ,2009,16:1518-1530.
  • 4Bae KT, Kim JS, Na YH, et al.Pulmonary nodules: automated detection on CT images with morphologic matching algorithm-- preliminaryresults.Radiology,2005,236:286-293.
  • 5蔡强,吴宁,周丽娜,唐威,黄遥,王建卫.计算机辅助检测系统在低剂量CT筛查者非钙化肺结节中的应用研究[J].中华放射学杂志,2014,48(1):63-66. 被引量:24
  • 6Sumiaki M ,Yoshiharu O,Takatoshi A. Computer-aided detection of lung nodules on multideteetor CT inconcurrent-reader and second- reader modes: A comparative study.European Journal of Radiology, 82 2013,1332-1337.
  • 7Beyer F,Zierott L,Fallenberg EM. Comparison of sensitivity and reading time for the use of computer-aided detection (CAD) of pulmonary nodules at MDCT as concurrent or second reader.Eur Radiol, 2007,17:2941-2947.
  • 8Hirose T,Nitta N,Shiraishi J, et al.Evaluation computer-aided diagnosis(CAD) software for the detection of lung nodules on multidetector row computed tomography(MDCT):JAFROC study for the improvement inradiologists'diagnostiy accuracy. Academic Radiology,2008,15:1505-1512.
  • 9Das M,Mtihlenbruch G,Mahnken AH,et al.Small pulmonary nodules: effect of two computer-aided detection system sonradiologis performance. Radiology ,2006, 241:564-571.
  • 10Foti G, Faccioli N,D'Onofrio M, et al.Evaluation of a method of computer-aided detection (CAD) of pulmonary nodules at computed tomography.Radiologia Medica,20 l 0,115:950-961.

二级参考文献13

  • 1Rubin GD,Lyo JK,Paik DS. Pulmonary nodules on multidetector row CT scans:performance comparison of radiologists and computer-aided detection[J].{H}RADIOLOGY,2005.274-283.
  • 2Brown MS,Goldin JG,Suh RD. Lung micronodules:automated method for detection at thin-section CT:initial experience[J].{H}RADIOLOGY,2003.256-262.
  • 3Goo JM,Lee JW,Lee H J. Automated lung nodule detection at low-dose CT:preliminary experience[J].{H}KOREAN JOURNAL OF RADIOLOGY,2003.211-216.
  • 4Teague SD,Trilikis G,Dharaiya E. Lung nodule computer-aided detection as a second reader:influence on radiology residents[J].{H}Journal of Computer Assisted Tomography,2010.35-39.
  • 5Gruden JF,Ouanounou S,Tigges S. Incremental benefit of maximum-intensity-projection images on observer detection of small pulmonary nodules revealed by multidetector CT[J].{H}AJR American Journal of Roentgenology,2002.149-157.
  • 6Yuan R,Vos PM,Cooperberg PL. Computer-aided detection in screening CT for pulmonary nodules[J].{H}AJR American Journal of Roentgenology,2006.1280-1287.
  • 7Yanagawa M,Honda O,Yoshida S. Commercially available computer-aided detection system for pulmonary nodules on thinsection images using 64 detectors row CT:preliminary study of 48 cases[J].{H}ACADEMIC RADIOLOGY,2009.924-933.
  • 8Song KD,Chung M J,Kim HC. Usefulness of the CAD system for detecting pulmonary nodule in real clinical practice[J].{H}KOREAN JOURNAL OF RADIOLOGY,2011.163-168.
  • 9Goo JM. A computer-aided diagnosis for evaluating lung nodules on chest CT:the current status and perspective[J].{H}KOREAN JOURNAL OF RADIOLOGY,2011.145-155.
  • 10Bcigclman-Aubry C,Raffy P,Yang W. Computer-aided detection of solid lung nodules on follow-up MSCT screening:evaluation of detection,tracking,and reading time[J].{H}AJR American Journal of Roentgenology,2007.948-955.

共引文献23

同被引文献29

引证文献4

二级引证文献25

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