Detection of Lung Nodules in Thoracic MDCT Images Based on Temporal Changes from Previous and Current Images

Shinya Maeda; Yasuyuki Tomiyama; Hyoungseop Kim; Noriaki Miyake; Yoshinori Itai; Joo Kooi Tan; Seiji Ishikawa; Akiyoshi Yamamoto

doi:10.20965/jaciii.2011.p0707

single-jc.php

« previous

JACIII Vol.15 No.6 pp. 707-713

doi: 10.20965/jaciii.2011.p0707

(2011)

Paper:

Views over last 60 days: 573

Detection of Lung Nodules in Thoracic MDCT Images Based on Temporal Changes from Previous and Current Images

Shinya Maeda, Yasuyuki Tomiyama, Hyoungseop Kim,
Noriaki Miyake, Yoshinori Itai, Joo Kooi Tan, Seiji Ishikawa,
and Akiyoshi Yamamoto

Department of Control Engineering, Kyushu Institute of Technology, 1-1 Sensui, Tobata, Kitakyushu 804-8550, Japan

Received:

December 7, 2010

Accepted:

April 22, 2011

Published:

August 20, 2011

Keywords:

temporal subtraction method, lung nodule detection, computer aided diagnosis, medical imaging, MDCT

Abstract

Temporal subtraction enhances temporal change by subtracting images captured at different times. Medical images captured currently (current images) and in previous examination (previous images) are subtracted to enhance new lesions and temporal change in existing lesion shadows. Temporal subtraction using chest MultiDetector-Row Computed Tomography (MDCT) images and currently being developed is to be applied to nodule detection in pulmonary regions. Nodule detection using conventional temporal subtraction, however, yields many false-positive results for those 20 mm or less in diameter, requiring improvement. We discuss improvements in nodule detection accuracy using temporal subtraction, first extracting rough nodules from temporal subtraction images as candidate shadows. Features are then acquired from current, previous, and temporal subtraction images. We use intensity features in previous images and shape features in the current images and in features used in conventional methods. Using acquired features, we build a neural network classifier, then extract final pulmonary candidates in unknown shadows.

Cite this article as:

S. Maeda, Y. Tomiyama, H. Kim, N. Miyake, Y. Itai, J. Tan, S. Ishikawa, and A. Yamamoto, “Detection of Lung Nodules in Thoracic MDCT Images Based on Temporal Changes from Previous and Current Images,” J. Adv. Comput. Intell. Intell. Inform., Vol.15 No.6, pp. 707-713, 2011.

Data files:

References

[1] K. Doi, “Current status and future potential of computer-aided diagnosis in medical imaging,” British J. Rad., Vol.78, pp. S3-S19, 2005.
[2] J. Y. Wei, Y. Hagihara, A. Shimidzu et al., “Optimal image feature set for detecting lung nodules on chest X-ray image,” Proc. of the CARS, pp. 706-711, 2002.
[3] Y. Lee, T. Hara, H. Fujita et al., “Automatic detection of pulmonary nodules in helical CT images based on an improved templatematching technique,” IEEE Trans. Med. Imaging, Vol.20, pp. 595-604, 2001.
[4] X. Zhang, G. McLennan, E. A. Hoffman et al., “Automated detection of small-size pulmonary nodules on helical CT images,” Proc. of Int. Conf. on Information Proc. in Medical Imaging., pp. 664-676, 2005.
[5] S. Kakeda, K. Kamada, and Y. Hatakeyama, “Effect of temporal subtraction on interpretation time and diagnostic accuracy of chest radiography,” American J. of Roenteenology, Vol.187, No.5, pp. 1253-1259, 2006.
[6] Y. Itai, H. Kim, S. Ishikawa et al., “3D elastic matching for temporal subtraction employing thorax MDCT image,” Proc. of the World Congress on Medical Physics and Biomedical Engineering., pp. 2181-2191, 2006.
[7] Y. Itai, H. Kim, S. Ishikawa et al., “Development of a voxel matching technique for substantial reduction of subtraction artifacts in temporal subtraction images obtained from thoracic MDCT,” J. of Digital Imaging, Vol.23, No.1, pp. 32-38, 2010.
[8] N. Miyake, H. Kim, Y. Itai et al., “Automatic detection of lung nodules in temporal subtraction image by use of shape and density features,” Int. Conf. on Innovative Computing, Information and Control, CD-ROM (4 pages), 2009.
[9] Q. Li, S. Sone, and K. Doi, “Selective enhancement filters for nodules, vessels and airway walls in two- and three-dimensional CT scans,” Med. Phys., Vol.30, pp. 2040-2051, 2003.
[10] H. Kobatake, W. Jun, and Y. Hagihara, “Nonlinear adaptive filters based on gradient vector orientation,” Prog. of Int. Simp. on Nonlinear Theory and its Applications, pp. 533-556, 1999.
[11] J.Wang, R. Englman, and Q. Li, “Segmentation of pulmonary nodules in three-dimentional CT images by use of a spiral-scanning technique,” Med, Phys., Vol.34, No.12, pp. 4678-4689, 2007.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] K. Doi, “Current status and future potential of computer-aided diagnosis in medical imaging,” British J. Rad., Vol.78, pp. S3-S19, 2005.

[2] [2] J. Y. Wei, Y. Hagihara, A. Shimidzu et al., “Optimal image feature set for detecting lung nodules on chest X-ray image,” Proc. of the CARS, pp. 706-711, 2002.

[3] [3] Y. Lee, T. Hara, H. Fujita et al., “Automatic detection of pulmonary nodules in helical CT images based on an improved templatematching technique,” IEEE Trans. Med. Imaging, Vol.20, pp. 595-604, 2001.

[4] [4] X. Zhang, G. McLennan, E. A. Hoffman et al., “Automated detection of small-size pulmonary nodules on helical CT images,” Proc. of Int. Conf. on Information Proc. in Medical Imaging., pp. 664-676, 2005.

[5] [5] S. Kakeda, K. Kamada, and Y. Hatakeyama, “Effect of temporal subtraction on interpretation time and diagnostic accuracy of chest radiography,” American J. of Roenteenology, Vol.187, No.5, pp. 1253-1259, 2006.

[6] [6] Y. Itai, H. Kim, S. Ishikawa et al., “3D elastic matching for temporal subtraction employing thorax MDCT image,” Proc. of the World Congress on Medical Physics and Biomedical Engineering., pp. 2181-2191, 2006.

[7] [7] Y. Itai, H. Kim, S. Ishikawa et al., “Development of a voxel matching technique for substantial reduction of subtraction artifacts in temporal subtraction images obtained from thoracic MDCT,” J. of Digital Imaging, Vol.23, No.1, pp. 32-38, 2010.

[8] [8] N. Miyake, H. Kim, Y. Itai et al., “Automatic detection of lung nodules in temporal subtraction image by use of shape and density features,” Int. Conf. on Innovative Computing, Information and Control, CD-ROM (4 pages), 2009.

[9] [9] Q. Li, S. Sone, and K. Doi, “Selective enhancement filters for nodules, vessels and airway walls in two- and three-dimensional CT scans,” Med. Phys., Vol.30, pp. 2040-2051, 2003.

[10] [10] H. Kobatake, W. Jun, and Y. Hagihara, “Nonlinear adaptive filters based on gradient vector orientation,” Prog. of Int. Simp. on Nonlinear Theory and its Applications, pp. 533-556, 1999.

[11] [11] J.Wang, R. Englman, and Q. Li, “Segmentation of pulmonary nodules in three-dimentional CT images by use of a spiral-scanning technique,” Med, Phys., Vol.34, No.12, pp. 4678-4689, 2007.

Detection of Lung Nodules in Thoracic MDCT Images Based on Temporal Changes from Previous and Current Images

Shinya Maeda, Yasuyuki Tomiyama, Hyoungseop Kim, Noriaki Miyake, Yoshinori Itai, Joo Kooi Tan, Seiji Ishikawa, and Akiyoshi Yamamoto

Shinya Maeda, Yasuyuki Tomiyama, Hyoungseop Kim,
Noriaki Miyake, Yoshinori Itai, Joo Kooi Tan, Seiji Ishikawa,
and Akiyoshi Yamamoto