Background. The purpose of this study is to identify a set of features for optimizing the performance of metaphase chromosome detection under high throughput scanning microscopy. In the development of computer-aided detection (CAD) scheme, feature selection is critically important, as it directly determines the accuracy of the scheme. Although many features have been examined previously, selecting optimal features is often application oriented. Methods. In this experiment, 200 bone marrow cells were first acquired by a high throughput scanning microscope. Then 9 different features were applied individually to group captured images into the clinically analyzable and unanalyzable classes. The performance of these different methods was assessed by a receiving operating characteristic (ROC) method. Results. The results show that using the number of labeled regions on each acquired image is suitable for the first on-line CAD scheme. For the second off-line CAD scheme, it would be suggested to combine four feature extraction methods including the number of labeled regions, average regions area, average region pixel value, and the standard deviation of either region distance or circularity. Conclusion. This study demonstrates an effective method of feature selection and comparison to facilitate the optimization of the CAD schemes for high throughput scanning microscope in the future. 1. Introduction Chromosome imaging and karyotyping is an important and widely used clinical method for the diagnosis of genetic related diseases and cancers [1–3]. For this technique, identifying a sufficiently large number of pathologically analyzable metaphase chromosomes is critically important for the final accuracy of cancer diagnosis and residual cancer cell detection. At present, the chromosome identification is a two-step semiautomatic procedure [4]. Commercialized automatic scanners first scan and locate the clinically useful cells under low magnification state (i.e., 10x objective lens). Second, clinicians have to manually move back to these detected locations again for high resolution image acquisition (i.e., under 100x objective lens), which is labor intensive and time consuming. In addition, it also creates substantial interobserver variation due to the bias of cell selection (i.e., the tendency towards selecting cells with good morphology). Therefore, the automatic scanning techniques are proposed and developed in the last 20 years, in an attempt to reduce the clinicians’ workload and improve the diagnostic accuracy and consistency [5]. Recently, a new high
References
[1]
J. H. Tjio and A. Levan, “The chromosome number of man,” Hereditas, vol. 42, pp. 1–6, 1956.
[2]
J. Lejeune, M. Gautier, and R. Turpin, “Etude des chromosomes somatiques de neuf enfants mongoliens,” Comptes Rendus Hebdomadaires des Seances de L'Academie des Sciences, vol. 248, no. 11, pp. 1721–1722, 1959.
[3]
P. C. Nowell and D. A. Hungerford, “Minute chromosome in human chronic granulocytic leukemia,” Science, vol. 132, pp. 1497–1497, 1960.
[4]
B. Kajtár, G. Méhes, T. L？rch et al., “Automated fluorescent in situ hybridization (FISH) analysis of t(9;22)(Q34;Q11) in interphase nuclei,” Cytometry Part A, vol. 69, no. 6, pp. 506–514, 2006.
[5]
X. Wang, B. Zheng, M. Wood, S. Li, W. Chen, and H. Liu, “Development and evaluation of automated systems for detection and classification of banded chromosomes: current status and future perspectives,” Journal of Physics D: Applied Physics, vol. 38, no. 15, pp. 2536–2542, 2005.
[6]
Y. Qiu, X. Wang, X. Chen et al., “Automated detection of analyzable metaphase chromosome cells depicted on scanned digital microscopic images,” in Medical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment, vol. 7627 of Proceedings of SPIE, San Diego, Calif, USA, February 2010.
[7]
M. C. Wood, X. Wang, B. Zheng, S. Li, W. Chen, and H. Liu, “Using contrast transfer function to evaluate the effect of motion blur on microscope image quality,” in Biophotonics and Immune Responses III, vol. 6857 of Proceedings of SPIE, San Jose, Calif, USA, January 2008.
[8]
Y. Qiu, X. Chen, Z. Li et al., “An automatic scanning method for high throughput microscopic system to facilitate medical genetic diagnosis: An Initial Study,” in Biophotonics and Immune Responses VII, vol. 8224 of Proceedings of SPIE, San Francisco, Calif, USA, January 2012.
[9]
X. Wang, S. Li, H. Liu, J. J. Mulvihill, W. Chen, and B. Zheng, “A computer-aided method to expedite the evaluation of prognosis for childhood acute lymphoblastic leukemia,” Technology in Cancer Research and Treatment, vol. 5, no. 4, pp. 429–436, 2006.
[10]
X. Wang, S. Li, H. Liu, M. Wood, W. R. Chen, and B. Zheng, “Automated identification of analyzable metaphase chromosomes depicted on microscopic digital images,” Journal of Biomedical Informatics, vol. 41, no. 2, pp. 264–271, 2008.
[11]
X. Wang, B. Zheng, S. Li, J. J. Mulvihill, and H. Liu, “Development and assessment of an integrated computeraided detection scheme for digital microscopic images of metaphase chromosomes,” Journal of Electronic Imaging, vol. 17, no. 4, Article ID 043008, 2008.
[12]
K. R. Castleman, “The PSI automatic metaphase finder,” Journal of Radiation Research, vol. 33, pp. 124–128, 1992.
[13]
F. A. Cosío, L. Vega, A. H. Becerra, R. P. Meléndez, and G. Corkidi, “Automatic identification of metaphase spreads and nuclei using neural networks,” Medical and Biological Engineering and Computing, vol. 39, no. 3, pp. 391–396, 2001.
[14]
R. J. Stanley, J. M. Keller, P. Gader, and C. W. Caldwell, “Data-driven homologue matching for chromosome identification,” IEEE Transactions on Medical Imaging, vol. 17, no. 3, pp. 451–462, 1998.
[15]
S. Y. Ryu, J. M. Cho, and S. H. Woo, “A study for the feature selection to identify GIEMSA-stained human chromosomes based on artificial neural network,” in Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 691–692, October 2001.
[16]
J. M. Cho, “Chromosome classification using backpropagation neural networks,” IEEE Engineering in Medicine and Biology Magazine, vol. 19, no. 1, pp. 28–33, 2000.
[17]
J. Piper and E. Granum, “On fully automatic feature measurement for banded chromosome classification,” Cytometry, vol. 10, no. 3, pp. 242–255, 1989.
[18]
C. U. García, A. B. Rubio, F. A. Pérez, and F. S. Hernández, “A curvature-based multiresolution automatic karyotyping system,” Machine Vision and Applications, vol. 14, no. 3, pp. 145–156, 2003.
[19]
E. Poletti, F. Zappelli, A. Ruggeri, and E. Grisan, “A review of thresholding strategies applied to human chromosome segmentation,” Computer Methods and Programs in Biomedicine, vol. 108, no. 2, pp. 679–688, 2012.
[20]
E. Grisan, E. Poletti, and A. Ruggeri, “Automatic segmentation and disentangling of chromosomes in Q-band prometaphase images,” IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 4, pp. 575–581, 2009.
[21]
R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice Hall, Upper Saddle River, NJ, USA, 2002.
[22]
B. Zheng, A. Lu, L. A. Hardesty et al., “A method to improve visual similarity of breast masses for an interactive computer-aided diagnosis environment,” Medical Physics, vol. 33, no. 1, pp. 111–117, 2006.
[23]
X. Wang, X. Chen, Y. Li et al., “Fluorescence in situ hybridization (FISH) signal analysis using automated generated projection images,” Analytical Cellular Pathology, vol. 35, no. 5-6, pp. 395–405, 2012.
[24]
X. Wang, B. Zheng, S. Li, J. J. Mulvihill, M. C. Wood, and H. Liu, “Automated classification of metaphase chromosomes: optimization of an adaptive computerized scheme,” Journal of Biomedical Informatics, vol. 42, no. 1, pp. 22–31, 2009.
[25]
X. Wang, B. Zheng, S. Li, J. J. Mulvihill, and H. Liu, “A rule-based computer scheme for centromere identification and polarity assignment of metaphase chromosomes,” Computer Methods and Programs in Biomedicine, vol. 89, no. 1, pp. 33–42, 2008.
[26]
C. E. Metz, B. A. Herman, and J. H. Shen, “Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data,” Statistics in Medicine, vol. 17, pp. 1033–1053, 1998.
[27]
S. H. Park, J. M. Goo, and C.-H. Jo, “Receiver operating characteristic (ROC) curve: practical review for radiologists,” Korean Journal of Radiology, vol. 5, no. 1, pp. 11–18, 2004.
[28]
D. P. Chakraborty, “Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data,” Medical Physics, vol. 16, no. 4, pp. 561–568, 1989.
[29]
C. E. Metz, B. A. Herman, and C. A. Roe, “Statistical comparison of two ROC-curve estimates obtained from partially-paired datasets,” Medical Decision Making, vol. 18, no. 1, pp. 110–121, 1998.
[30]
C. Metz, P. L. Wang, and H. Kronman, “A new approach for testing the significance of differences between ROC curves measured from correlated data,” in Information Processing in Medical Imaging, F. Deconinck, Ed., pp. 432–445, Springer, Dordrecht, The Netherlands, 1984.
[31]
T. M. Mitchell, Machine Learning, McGraw-Hill, Boston, Mass, USA, 1997.
[32]
B. Lerner, “Bayesian fluorescence in situ hybridisation signal classification,” Artificial Intelligence in Medicine, vol. 30, no. 3, pp. 301–316, 2004.
[33]
A. David and B. Lerner, “Support vector machine-based image classification for genetic syndrome diagnosis,” Pattern Recognition Letters, vol. 26, no. 8, pp. 1029–1038, 2005.
[34]
B. Vigdor and B. Lerner, “Accurate and fast off and online fuzzy ARTMAP-based image classification with application to genetic abnormality diagnosis,” IEEE Transactions on Neural Networks, vol. 17, no. 5, pp. 1288–1300, 2006.
[35]
D. Lederman, B. Zheng, X. Wang, X. H. Wang, and D. Gur, “Improving breast cancer risk stratification using resonance-frequency electrical impedance spectroscopy through fusion of multiple classifiers,” Annals of Biomedical Engineering, vol. 39, no. 3, pp. 931–945, 2011.
