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

页码：525 / 534

页数：10