Fractal texture analysis in computer-aided diagnosis of solitary pulmonary nodules

被引:38
作者
Vittitoe, NF [1 ]
Baker, JA [1 ]
Floyd, CE [1 ]
机构
[1] DUKE UNIV,DEPT BIOMED ENGN,DURHAM,NC 27710
关键词
computers; diagnostic aid; lung; nodules; lung neoplasms; diagnosis; thorax; radiography;
D O I
10.1016/S1076-6332(97)80005-0
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
Rationale and Objectives. The authors investigated the use of fractal texture characterization to improve the accuracy of solitary pulmonary nodule computer-aided diagnosis (CAD) systems. Methods. Thirty chest radiographs were acquired from patients who had no pulmonary nodules. Thirty regions were selected that were considered remotely suspicious-looking for nodules. Artificial nodules of multiple shapes, sizes, and orientations were added at subtle levels of contrast to 30 non-suspicious-looking regions of the radiographs. Fractal dimensions of the 60 ''nodule candidates'' were calculated to quantify the texture of each region. Four radiologists also interpreted the images. Results. The fractal dimension of each possible nodule provided statistically significant (P < .05) differentiation between regions that contained an artificial nodule and those that did not. The area under the receiver operating characteristic curve for the fractal analysis was significantly better (P < .05) than that for the radiologists. Conclusion. Fractal texture characterization provides useful information for the classification of potential solitary pulmonary nodules with CAD algorithms.
引用
收藏
页码:96 / 101
页数:6
相关论文
共 25 条
[1]  
ANGUIANO E, 1993, J MICROSCOPY, V172, P233
[2]   VARIABLE COMPENSATION CHEST RADIOGRAPHY PERFORMED WITH A COMPUTED RADIOGRAPHY SYSTEM - DESIGN CONSIDERATIONS AND INITIAL CLINICAL-EXPERIENCE [J].
DOBBINS, JT ;
RICE, JJ ;
GOODMAN, PC ;
PATZ, EF ;
RAVIN, CE .
RADIOLOGY, 1993, 187 (01) :55-63
[3]   IMPROVING THE DISTINCTION BETWEEN BENIGN AND MALIGNANT BREAST-LESIONS - THE VALUE OF SONOGRAPHIC TEXTURE ANALYSIS [J].
GARRA, BS ;
KRASNER, BH ;
HORII, SC ;
ASCHER, S ;
MUN, SK ;
ZEMAN, RK .
ULTRASONIC IMAGING, 1993, 15 (04) :267-285
[4]   PULMONARY NODULES - COMPUTER-AIDED DETECTION IN DIGITAL CHEST IMAGES [J].
GIGER, ML ;
DOI, K ;
MACMAHON, H ;
METZ, CE ;
YIN, FF .
RADIOGRAPHICS, 1990, 10 (01) :41-51
[5]  
GODWIN JD, 1983, RADIOL CLIN N AM, V21, P709
[6]   NON-SMALL-CELL LUNG-CANCER - RESULTS OF THE NEW-YORK SCREENING-PROGRAM [J].
HEELAN, RT ;
FLEHINGER, BJ ;
MELAMED, MR ;
ZAMAN, MB ;
PERCHICK, WB ;
CARAVELLI, JF ;
MARTINI, N .
RADIOLOGY, 1984, 151 (02) :289-293
[7]  
KUKLINSKI WS, 1989, P SOC PHOTO-OPT INS, V1092, P111
[8]   INFLUENCE OF FILM DENSITY ON RADIOLOGIC DETECTION OF LUNG LESIONS [J].
KUNDEL, HL ;
REVESZ, G .
INVESTIGATIVE RADIOLOGY, 1977, 12 (02) :199-200
[9]   CONTRAST GRADIENT AND THE DETECTION OF LUNG NODULES [J].
KUNDEL, HL ;
REVESZ, G ;
TOTO, L .
INVESTIGATIVE RADIOLOGY, 1979, 14 (01) :18-22
[10]   PERCEPTION ERRORS IN CHEST RADIOGRAPHY [J].
KUNDEL, HL .
SEMINARS IN RESPIRATORY MEDICINE, 1989, 10 (03) :203-210