计算机断层扫描上肺结节评估的计算机辅助诊断方法的混合分布分析

Mixture distribution analysis of a computer assisted diagnostic method for the evaluation of pulmonary nodules on computed tomography scan.

作者信息

Kung Justin W, Matsumoto Sumiaki, Hasegawa Ichiro, Nguyen Binh, Toto Lawrence C, Kundel Harold, Hatabu Hiroto

机构信息

Department of Radiology, University of Pennsylvania, 3600 Science Center, Suite 370, 3600 Market St, Philadelphia, PA 19104, USA.

出版信息

Acad Radiol. 2004 Mar;11(3):281-5. doi: 10.1016/s1076-6332(03)00717-7.

DOI:10.1016/s1076-6332(03)00717-7

PMID:15035518

Abstract

RATIONALE AND OBJECTIVES

To compare the effectiveness of a new computational scheme for pulmonary nodule detection in computed tomography images against human observers.

MATERIALS AND METHODS

The study involved evaluation of 81 potential nodules by four radiologists. Each radiologist separately evaluated the potential nodules and provided a confidence level for the presence of pulmonary nodules. Their performance was compared with that of the new computational scheme by mixture distribution analysis.

RESULTS

Mixture distribution analysis of the results of the four radiologists demonstrated a relative proportion agreement of 0.84. The kappa statistic was used to compare the agreement of the computational scheme with the results of the four radiologists. A kappa value of .65 (se = .11) was shown to be significantly different from chance (P = .99).

CONCLUSION

The new computational scheme correlates well with the radiologists' subjective rankings of pulmonary nodules on computed tomography scans and may prove a useful tool in the evaluation of algorithms for the screening and diagnosis of lung cancer.

摘要