Automatic segmentation and recognition of lungs and lesion from CT scans of thorax

被引：42

作者：

Kakar, Manish ^{[1
]}

Olsen, Dag Rune ^{[1
,2
,3
]}

机构：

[1] Radiumhosp, Rikshosp, Med Ctr, Inst Canc Res,Dept Radiat Biol, Oslo, Norway

[2] Radiumhosp, Rikshosp, Med Ctr, Inst Canc Res,Dept Med Phys, Oslo, Norway

[3] Univ Oslo, Dept Phys, Oslo, Norway

来源：

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS | 2009年 / 33卷 / 01期

关键词：

Texture analysis; Gabor filters; Segmentation; Genetic Algorithm; SVM; Tracking; HIGH-RESOLUTION CT; PULMONARY NODULES; DISEASE; SYSTEM; IMAGES; MOTION; MRI;

D O I：

10.1016/j.compmedimag.2008.10.009

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

In this study, a fully automated texture-based segmentation and recognition system for lesion and lungs from CT of thorax is presented. For the segmentation part. we have extracted texture features by Gabor filtering the images, and. then combined these features to segment the target volume by using Fuzzy C Means (FCM) clustering. Since clustering is sensitive to initialization of cluster prototypes, optimal initialization of the cluster prototypes was done by using a Genetic Algorithm. For the recognition stage, we have used cortex like mechanism for extracting statistical features in addition to shape-based features. The segmented regions showed a high degree of imbalance between positive and negative samples, so we employed over and under sampling for balancing the data. Finally, the balanced and normalized data was subjected to Support Vector Machine (SimpleSVM) for training and testing. Results reveal an accuracy of delineation to be 94.06%, 94.32% and 89.04% for left lung, right lung and lesion, respectively. Average sensitivity of the SVM classifier was seen to be 89.48%. (C) 2008 Elsevier Ltd. All rights reserved.

引用

页码：72 / 82

页数：11

共 48 条

[1] Feature normalization and likelihood-based similarity measures for image retrieval [J].

Aksoy, S ;

Haralick, RM .

PATTERN RECOGNITION LETTERS, 2001, 22 (05) :563-582

[2] Automated detection of lung nodules in CT scans: Preliminary results [J].

Armato, SG ;

Giger, ML ;

MacMahon, H .

MEDICAL PHYSICS, 2001, 28 (08) :1552-1561

[3]

BACK T, 1994, P INF PROC MAN UNC K, V2, P659

[4]

Baker J. E., 1987, Genetic Algorithms and their Applications: Proceedings of the Second International Conference on Genetic Algorithms, P14

[5]

Bezdek J., 1999, FUZZY MODELS ALGORIT

[6] REVIEW OF MR IMAGE SEGMENTATION TECHNIQUES USING PATTERN-RECOGNITION [J].

BEZDEK, JC ;

HALL, LO ;

CLARKE, LP .

MEDICAL PHYSICS, 1993, 20 (04) :1033-1048

[7] A tutorial on Support Vector Machines for pattern recognition [J].

Burges, CJC .

DATA MINING AND KNOWLEDGE DISCOVERY, 1998, 2 (02) :121-167

[8] SMOTE: Synthetic minority over-sampling technique [J].

Chawla, Nitesh V. ;

Bowyer, Kevin W. ;

Hall, Lawrence O. ;

Kegelmeyer, W. Philip .

2002, American Association for Artificial Intelligence (16)

[9]

COHEN I, 1992, CVGIP IMAGE UNDERST, V56, P135

[10] Usual interstitial pneumonia - Quantitative assessment of high-resolution computed tomography findings by computer-assisted texture-based image analysis [J].

Delorme, S ;

KellerReichenbecher, MA ;

Zuna, I ;

Schlegel, W ;

vanKaick, G .

INVESTIGATIVE RADIOLOGY, 1997, 32 (09) :566-574

← 1 2 3 4 5 →