Three-Dimensional SVM with Latent Variable: Application for Detection of Lung Lesions in CT Images

被引:0
|
作者
Qingzhu Wang
Wenchao Zhu
Bin Wang
机构
[1] Northeast Dianli University,School of Information Engineering
[2] Jilin Tumor Hospital,undefined
来源
Journal of Medical Systems | 2015年 / 39卷
关键词
Computer-aided detection; Lung CT; Higher-order tensor; Gaussian kernel; Structure support vector machine;
D O I
暂无
中图分类号
学科分类号
摘要
The study aims to improve the performance of current computer-aided schemes for the detection of lung lesions, especially the low-contrast in gray density or irregular in shape. The relative position between suspected lesion and whole lung is, for the first time, added as a latent feature to enrich current Three-dimensional (3D) features such as shape, texture. Subsequently, 3D matrix patterns-based Support Vector Machine (SVM) with the latent variable, referred to as L-SVM3Dmatrix, was constructed accordingly. A CT image database containing 750 abnormal cases with 1050 lesions was used to train and evaluate several similar computer-aided detection (CAD) schemes: traditional features-based SVM (SVMfeature), 3D matrix patterns-based SVM (SVM3Dmatrix) and L-SVM3Dmatrix. The classifier performances were evaluated by computing the area under the ROC curve (AUC), using a 5-fold cross-validation. The L-SVM3Dmatrix sensitivity was 93.0 with 1.23 % percentage of False Positive (FP), the SVM3Dmatrix sensitivity was 88.4 with 1.49 % percentage of FP, and the SVMfeature sensitivity was 87.2 with 1.78 % percentage of FP. The L-SVM3Dmatrix outperformed other current lung CAD schemes, especially regarding the difficult lesions.
引用
收藏
相关论文
共 50 条
  • [31] Three-dimensional reconstruction of endosonographic images of gastric lesions: Preliminary experience
    Tsutsui, A
    Okamura, S
    Muguruma, N
    Tsujigami, K
    Ichikawa, S
    Ito, S
    Umino, K
    JOURNAL OF CLINICAL ULTRASOUND, 2005, 33 (03) : 112 - 118
  • [32] Detection algorithm for suspected lesions in CT images of lung cancer CAD
    Wei, Ying
    Yu, Qian
    Jia, Tong
    Zhao, Dazhe
    Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2009, 30 (01): : 1 - 6
  • [33] A fast method for three-dimensional obstacles detection from images - application to efficient walkers design
    Pissaloux, EE
    CLIMBING AND WALKING ROBOTS, 2002, : 287 - 290
  • [34] Automatic detection of device setup errors in radiotherapy by matching three-dimensional CT data and portal images
    Tschirley, R
    Beier, J
    Wust, P
    CARS '99: COMPUTER ASSISTED RADIOLOGY AND SURGERY, 1999, 1191 : 270 - 274
  • [35] Detection and upconversion of three-dimensional MMW/THz images to the visible
    Avihai Aharon(Akram)
    Daniel Rozban
    Avi Klein
    Amir Abramovich
    Yitzhak Yitzhaky
    Natan S.Kopeika
    Photonics Research, 2016, (06) : 306 - 312
  • [36] Detection and upconversion of three-dimensional MMW/THz images to the visible
    Avihai AharonAkram
    Daniel Rozban
    Avi Klein
    Amir Abramovich
    Yitzhak Yitzhaky
    Natan SKopeika
    Photonics Research, 2016, 4 (06) : 306 - 312
  • [37] Detection and upconversion of three-dimensional MMW/THz images to the visible
    Aharon , Avihai
    Rozban, Daniel
    Klein, Avi
    Abramovich, Amir
    Yitzhaky, Yitzhak
    Kopeika, Natan S.
    PHOTONICS RESEARCH, 2016, 4 (06) : 306 - 312
  • [38] Three-Dimensional Respiratory Deformation Processing for CT Vessel Images Using Angiographic Images
    Suganuma, Shohei
    Takano, Yuya
    Ohnishi, Takashi
    Kato, Hideyuki
    Ooka, Yoshihiko
    Haneishi, Hideaki
    ABDOMINAL IMAGING: COMPUTATIONAL AND CLINICAL APPLICATIONS, 2014, 8676 : 257 - 266
  • [39] Clinical fusion of three-dimensional images using bremsstrahlung SPECT and CT
    Parsai, EI
    Ayyangar, KM
    Dobelbower, RR
    Siegel, JA
    JOURNAL OF NUCLEAR MEDICINE, 1997, 38 (02) : 319 - 324
  • [40] Fully Automatic Segmentation and Three-Dimensional Reconstruction of the Liver in CT Images
    Wang, ZhenZhou
    Zhang, Cunshan
    Jiao, Ticao
    Gao, MingLiang
    Zou, Guofeng
    JOURNAL OF HEALTHCARE ENGINEERING, 2018, 2018