IMAGE-ANALYSIS METHODS FOR SOLITARY PULMONARY NODULE CHARACTERIZATION BY COMPUTED-TOMOGRAPHY

被引:41
作者
CAVOURAS, D
PRASSOPOULOS, P
PANTELIDIS, N
机构
[1] Department of Medical Instruments, School of Technological Applications, Technological Educational Institute of Athens, Athens
[2] Department of Diagnostic Radiology, Airforce General and V.A. Hospital, Athens
关键词
IMAGE; ANALYSIS; PROCESSING; THORAX; SOLITARY PULMONARY NODULE; IMAGE ANALYSIS;
D O I
10.1016/0720-048X(92)90079-O
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Computer software was designed for classifying solitary pulmonary nodules (SPNs) into benign and malignant from their CT images, using image analysis methods. The system made use of three features, computed from the CT density matrix of the SPN, and a class-discriminating algorithm. System evaluation was performed on 51 histologically confirmed SPNs of indeterminate CT diagnosis. Overall classification accuracy in distinguishing benign and malignant SPNs was 90.2%, while 83.3% of the benign and 93.9% of the malignant SPNs were correctly classified. The proposed system may be of value to the radiologist in assessing the probability of malignancy in patients with a solitary pulmonary nodule.
引用
收藏
页码:169 / 172
页数:4
相关论文
共 16 条
[1]  
Caskey, Templeton, Zerhouni, Current evaluation of the solitary pulmonary nodule, Radiol Clin North Am, 28, pp. 511-520, (1990)
[2]  
Sagel, Glazer, Lung, pleural, chest wall, Computed body tomography, pp. 295-387, (1989)
[3]  
Cummings, Lillington, Richard, Managing solitary pulmonary nodules: the choice of strategy is a ‘close call’, Am Rev Respir Dis, 134, pp. 453-460, (1986)
[4]  
Siegelman, Zerhouni, Leo, Khouri, Stitik, CT of the solitary pulmonary nodule, AJR, 135, pp. 1-13, (1980)
[5]  
Siegelman, Khouri, Leo, Fishman, Braverman, Zerhouni, Solitary pulmonary nodules: CT assessment, Radiology, 160, pp. 307-312, (1986)
[6]  
Siegelman, Khouri, Scott, Leo, Hamper, Fishman, Zerhouni, Pulmonary hamartoma: CT findings, Radiology, 160, pp. 313-317, (1986)
[7]  
Proto, Thomas, Pulmonary nodules studied by computed tomography, Radiology, 156, pp. 149-153, (1985)
[8]  
Fraser, Sanders, Niklason, Sabbagh, Luna, Alexandra, Robinson, Katzenstein, Barnes, Calcification in pulmonary nodules: detection with dual energy digital radiography, Radiology, 160, pp. 595-601, (1986)
[9]  
Chen, Pavlidis, Segmentation by texture using a cooccurrence matrix and a split-and-merge algorithm, Comput Graph Image Process, 10, pp. 172-182, (1979)
[10]  
Raeth, Schlaps, Limberg, Zuna, Lorenz, Van Kaik, Lorenz, Kommerell, Diagnostic accuracy of computerized B-scan texture analysis and conventional ultrasonography in diffuse parenchymal and malignant liver disease, J Clin Ultrasound, 13, pp. 87-89, (1985)