Lung nodule detection in low-dose and thin-slice computed tomography

被引：75
作者：
Retico, A. [1 ]
Delogu, P. [1 ,2 ]
Fantacci, M. E. [1 ,2 ]
Gori, I. [1 ,3 ]
Martinez, A. Preite [4 ]
机构：
[1] Ist Nazl Fis Nucl, Sez Pisa, I-56127 Pisa, Italy
[2] Univ Pisa, Dipartimento Fis, I-56127 Pisa, Italy
[3] Bracco Imaging SpA, I-20134 Milan, Italy
[4] Ctr Studi & Ric Enrico Fermi, I-00184 Rome, Italy
来源：
COMPUTERS IN BIOLOGY AND MEDICINE | 2008年 / 38卷 / 04期
关键词：
computer-aided detection (CAD); low-dose computed tomography (LDCT); thin-slice CT; image processing;
D O I：
10.1016/j.compbiomed.2008.02.001
中图分类号：
Q [生物科学];
学科分类号：
07 ; 0710 ; 09 ;
摘要：
A computer-aided detection (CAD) system for the identification of small pulmonary nodules in low-dose and thin-slice CT scans has been developed. The automated procedure for selecting the nodule candidates is mainly based on a filter enhancing spherical-shaped objects. A neural approach based on the classification of each single voxel of a nodule candidate has been purposely developed and implemented to reduce the amount of false-positive findings per scan. The CAD system has been trained to be sensitive to small internal and sub-pleural pulmonary nodules collected in a database of low-dose and thin-slice CT scans. The system performance has been evaluated on a data set of 39 CT containing 75 internal and 27 sub-pleural nodules. The FROC curve obtained on this data set shows high values of sensitivity to lung nodules (80-85% range) at an acceptable level of false positive findings per patient (10-13 FP/scan). (c) 2008 Elsevier Ltd. All rights reserved.
引用
收藏
页码：525 / 534
页数：10
相关论文
共 29 条
[1]  
[Anonymous], MED IMAGING TELEMEDI
[2]   Lung cancer mortality in European women: recent trends and perspectives [J].
Bosetti, C ;
Levi, F ;
Lucchini, F ;
Negri, E ;
La Vecchia, C .
ANNALS OF ONCOLOGY, 2005, 16 (10) :1597-1604
[3]   Computer-aided detect ion of lung nodules on thin collimation MDCT: impact on radiologists' performance [J].
Brochu, B. ;
Beigelman-Aubry, C. ;
Goldmard, J-L ;
Raffy, P. ;
Grenier, P. A. ;
Lucidarme, O. .
JOURNAL DE RADIOLOGIE, 2007, 88 (04) :573-578
[4]   Computer-aided lung nodule detection in CT: Results of large-scale observer test [J].
Brown, MS ;
Goldin, JG ;
Rogers, S ;
Kim, HJ ;
Suh, RD ;
McNitt-Gray, MF ;
Shah, SK ;
Truong, D ;
Brown, K ;
Sayre, JW ;
Gjertson, DW ;
Batra, P ;
Aberle, DR .
ACADEMIC RADIOLOGY, 2005, 12 (06) :681-686
[5]   FREE-RESPONSE METHODOLOGY - ALTERNATE ANALYSIS AND A NEW OBSERVER-PERFORMANCE EXPERIMENT [J].
CHAKRABORTY, DP ;
WINTER, LHL .
RADIOLOGY, 1990, 174 (03) :873-881
[6]   Lung cancer mortality at ages 35-54 in the European Union: ecological study of evolving tobacco epidemics [J].
Didkowska, J ;
Manczuk, M ;
McNeill, A ;
Powles, J ;
Zatonski, W .
BMJ-BRITISH MEDICAL JOURNAL, 2005, 331 (7510) :189-191
[7]   Detection of pulmonary nodules at spiral CT: comparison of maximum intensity projection sliding slabs and single-image reporting [J].
Diederich, S ;
Lentschig, MG ;
Overbeck, TR ;
Wormanns, D ;
Heindel, W .
EUROPEAN RADIOLOGY, 2001, 11 (08) :1345-1350
[8]   Approximate statistical tests for comparing supervised classification learning algorithms [J].
Dietterich, TG .
NEURAL COMPUTATION, 1998, 10 (07) :1895-1923
[9]   Lung nodule detection on thoracic computed tomography images: Preliminary evaluation of a computer-aided diagnosis system [J].
Gurcan, MN ;
Sahiner, B ;
Petrick, N ;
Chan, HP ;
Kazerooni, EA ;
Cascade, PN ;
Hadjiiski, L .
MEDICAL PHYSICS, 2002, 29 (11) :2552-2558
[10]   Early Lung Cancer Action Project: overall design and findings from baseline screening [J].
Henschke, CI ;
McCauley, DI ;
Yankelevitz, DF ;
Naidich, DP ;
McGuinness, G ;
Miettinen, OS ;
Libby, DM ;
Pasmantier, MW ;
Koizumi, J ;
Altorki, NK ;
Smith, JP .
LANCET, 1999, 354 (9173) :99-105
123