Paper:
Language: English:

A Genetic-Algorithm-Based Temporal Subtraction for Chest Radiographs

Takeshi Inaba^, Lifeng He^, Kenji Suzuki^**, Kazuhito Murakami^*,
and Yuyan Chao^***

^Graduate School of Information Science and Technology Aichi Prefectural University, Nagakute-cho, Aichi 480-1198, Japan
^Department of Radiology, Division of Biological Sciences, The University of Chicago, 5841 South Maryland Avenue, Chicago, IL 60637, USA
^Graduate School of Environmental Management, Nagoya Sangyo University, Owariasahi-city, Aichi 488-8711, Japan

Received: November 25, 2008

Accepted: February 25, 2009

Keywords: temporal-subtraction image, computer aided diagnosis (CAD), genetic algorithm (GA), medical imaging, image registration

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.13, No.3 pp. 289-296, 2009

Abstract

To assess pathological chest change, radiologists compare the same patient's chest radiographs taken at different times. Supporting radiologists' diagnostics, temporal-subtraction images constructed from the previous and current radiographs have enhanced the visualization of pathological change. This paper presents a genetic-algorithm-based temporal subtraction for chest radiographs. First, we extract ribs from previous and current images and use them for global matching of the two images. Then, we divide the lung area in the current image into many subareas. For individual subarea, we use the genetic algorithm for local matching to find its corresponding area in the previous image efficiently. Results demonstrated that pathological change were accurately enhanced in temporal-subtraction images without major misregistration artifacts, accurately visualizing of pathological change and proving useful in improving radiologists, diagnostic performance.

Reference

[1] National Cancer Center: Cancer information service, http://ganjoho.ncc.go.jp/public/index.html

[2] T. Ishida, K. Ashizawa, R.M. Engelmann, S. Katsuragawa, H. MacMahon, and K. Doi, “Application of temporal subtraction for detection of interval changes in chest Radiographs: Improvement of subtraction image using automated initial image matching,” Journal of Dig Imag, Vol.12, No.2, pp. 77-86, 1999.

[3] T. Ishida, S. Katsuragawa, K. Nakamura, H. MacMahon, and K. Doi, “Iterative image warping technique for temporal subtraction of sequential chest radiographs to detect interval change,” Med Phys, Vol.26, No.7, pp. 1320-1329, 1999.

[4] S. G. Armato III, D. J. Doshi, R. Engelmann, C. L. Croteau, and H. MacMahon, “Temporal subtraction in chest radiography: Automated assessment of registration accuracy,” Med Phys, Vol.33, No.5, pp. 1239-1249, 2006.

[5] I. Seiki, H. Masaki, M. Koji, Y. Nobuyuki, N. Eisuke, and O. Masato, “C gengo de manabu jissen gazo shori -Windows, Machintosh, X-Window taiou-,” Ohmsha, 1999 (in Japanese).

[6] K. Suzuki, H. Abe, H. MacMahon, and K. Doi, “Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN),” IEEE Trans Med Imaging, Vol.25, No.4, pp. 406-416, 2006.

[7] H. Masahumi, “Neuro/Fuzzy/Genetic Algorithm,” Sangyo-Tosho, 2003 (in Japanese).

[8] R. Fletcher and M. J. D. Powell, “A Rapidly Convergent Descent Method for Minimization,” Computer Journal, Vol.6, pp. 163-168, 1963.