Добавил:
Опубликованный материал нарушает ваши авторские права? Сообщите нам.
Вуз: Предмет: Файл:

Kluwer - Handbook of Biomedical Image Analysis Vol

.2.pdf
Скачиваний:
106
Добавлен:
10.08.2013
Размер:
25.84 Mб
Скачать

744

Kallergi, Heine, and Tembey

2.What are the basic elements and characteristics of a CADiagnosis scheme?

3.What is the “visual analysis” system of mammographic calcifications and how can it be translated to a computer methodology that helps mammogram interpretation?

4.What property exists between wavelet expansion images that does not exist in an arbitrary filter bank output?

5.What can you say about a time series signal that is nothing but a spike a t = t0 with respect to its Fourier properties?

6.An image with long-range positive correlation will have large Fourier components in what part of the frequency domain?

7.Explain what a band pass filter is and what it may be used for.

8.What is white noise and give an example from common observation?

9.Given a low-frequency signal of interest buried in white noise, what kind of filter would work for lessening the influence of the noise?

10.What are the criteria for database design as needed for the evaluation of CADiagnosis algorithms?

11.What are the validation steps of a CADiagnosis scheme?

12.What is the different between computer ROC and observer ROC? How can we correlate the ROC indices of performance to clinically used indices of sensitivity and specificity?

13.Could segmentation be validated through classification and how?

Computer-Aided Diagnosis of Mammographic Calcification Clusters

745

Bibliography

[1]Huo, Z., Giger, M. L., Vyborny, C. J., and Metz, C. E., Breast cancer: Effectiveness of computer-aided diagnosis-observer study with independent database of mammograms, Radiology, Vol. 224, pp. 560–568, 2002.

[2]Feig, S. A., Clinical evaluation of computer-aided detection in breast cancer screening, Sem. Breast Dis., Vol. 5, No. 4, pp. 223–230, 2002.

[3]de Koning, H. J., Mammographic screening: Evidence from randomized controlled trials, Ann Oncol., Vol. 14, No. 8, pp. 1185–1189, 2003.

[4]Feig, S. A., Decreased breast cancer mortality through mammographic screening: Results of clinical trials, Radiology, Vol. 167, pp. 659–665, 1988.

[5]Clark, R. A., Breast cancer screening: Is it worthwhile? Cancer Control, Vol. 3, pp. 189–194, 1995.

[6]Bird, R. E., Wallace, T., W., and Yankaskas, B. C., Analysis of cancers missed at screening mammography, Radiology, Vol. 184, No. 3, pp. 613– 617, 1992.

[7]Millis, R. R., Davis, R., and Stacey, A. J., The detection and significance of calcifications in the breast: A radiological and pathological study, Br. J. Radiol., Vol. 49, pp. 12–26, 1976.

[8]Reintgen, D., Berman, C., Cox, C., Baekey, P., Nicosia, S., Greenberg, H., Bush, C., Lyman, G. H., and Clark, R. A., The anatomy of missed breast cancer, Surg. Oncol., Vol. 2, pp. 65–75, 1993.

[9]Kopans, D. B., The positive predictive value of mammography, AJR, Vol. 158, No. 3, pp. 521–526, 1992.

[10]Lewin, J. M., Hendrick, R. E., D’Orsi, C. J., Isaacs, P. K., Moss, L. J., Karellas, A., Sisney, G. A., Kuni, C. C., and Cutter, G. R., Comparison of full-field digital mammography with screen-film mammography for cancer detection: Results of 4,945 paired examinations, Radiology, Vol. 218, pp. 873–880, 2001.

746

Kallergi, Heine, and Tembey

[11]Giger, M. L., Computer-aided diagnosis in radiology, Acad. Radiol., Vol. 9, No. 1, pp. 1–3, 2002.

[12]Nishikawa, R., Assessment of the performance of computer-aided detection and computer-aided diagnosis systems, Sem. Breast Dis., Vol. 5, No. 4, pp. 217–222, 2002.

[13]Floyd, C. E., Lo, J. Y., Yun, A. J., Sullivan, D. C., and Kornguth, P. J., Prediction of breast cancer malignancy using an artificial neural network, Cancer, Vol. 74, No. 11, pp. 2944–2948, 1994.

[14]Jiang, Y., Nishikawa, R. M., Schmidt, R. A., Metz, C. E., Giger, M. L., and Doi, K., Improving breast cancer diagnosis with computer-aided diagnosis, Acad. Radiol., Vol. 6, pp. 22–33, 1999.

[15]Giger, M. L., Huo, Z., Kupinski, M. A., and Vyborny, C. J., Computeraided diagnosis in mammography, In: Handbook of Medical Imaging, Volume 2, Medical Image Processing and Analysis, Sonka, M. and Fitzpatrick, M. J., eds., SPIE Press, Bellingham, WA, pp. 915–1004, 2000.

[16]Li, L., Zheng, Y., Zhang, L., and Clark, R. A., False-positive reduction in CAD mass detection using a competitive strategy, Med. Phys., Vol. 28, No. 2, pp. 250–258, 2001.

[17]Wu, Y., Giger, M. L., Doi, K., Vyborny, C. J., Schmidt, R. A., and Metz, C. E., Artificial neural networks in mammography: Application to decision making in the diagnosis of breast cancer, Radiology, Vol. 187, pp. 81–87, 1993.

[18]Chan, H. P., Sahiner, B., Kam, K. L., Petrick, N., Helvie, M. A., Goodsitt, M. M., and Adler, D. D., Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces, Med. Phys., Vol. 25, No. 10, pp. 2007–2019, 1998.

[19] Jiang, Y., Nishikawa, R. M., Wolverton, D. E., Metz, C. E., Giger, M. L., Schmidt, R. A., Vyborny, C. J., and Doi, K., Malignant and benign clustered microcalcifications: Automated feature analysis and classification, Radiology, Vol. 198, pp. 671–678, 1996.

Computer-Aided Diagnosis of Mammographic Calcification Clusters

747

[20]Kallergi, M., Computer aided diagnosis of mammographic microcalcification clusters, Med. Phys., Vol. 31, pp. 314–326, 2004.

[21]Lanyi, M., Morphologic analysis of microcalcifications: A valuable differential diagnostic system for early detection of breast carcinomas and reduction of superfluous exploratory excisions, In: Early Breast Cancer, Zander, J. and Baltzer, J., eds., Springer-Verlag, Berlin, pp. 113–135, 1985.

[22]Lanyi, M., Diagnosis and Differential Diagnosis of Breast Calcifications, Springer-Verlag, Berlin, 1986.

[23]Hall, F. M., Storella, J. M., Silverstone, D. Z., and Wyshak, G., Nonpalpable breast lesions: Recommendations for biopsy based on suspicion of carcinoma at mammography, Radiology, Vol. 167, pp. 353–358, 1988.

[24]Olson, S. L., Fam, B. W., Winter, P. F., Scholz, F. J., Lee, A. K., and Gordon,

S.E., Breast calcifications: Analysis of imaging properties, Radiology, Vol. 169, pp. 329–332, 1988.

[25]Muir, B. B., Lamb, J., Anderson, T. J., and Kirkpatrick, A. E., Microcalcification and its relationship to cancer of the breast: Experience in a screening clinic, Clin. Radiol., Vol. 34, pp. 193–200, 1983.

[26]D’Orsi, C. J. and Kopans, D. B., Mammographic feature analysis, Sem. Roentgenol., Vol. XXVIII, No. 3, pp. 204–230, 1993.

[27]Liberman, L., Abramson, A. F., Squires, F. B., Glassman, J. R., Morris,

E.A., and Dershaw, D. D., The breast imaging reporting and data system: Positive predictive value of mammographic features and final assessment categories, AJR, Vol. 171, pp. 35–40, 1998.

[28]Kallergi, M., Gavrielides, M. A., He, L., Berman, C. G., Kim, J. J., and Clark, R. A., A simulation model of mammographic calcifications based on the ACR BIRADS, Acad. Radiol., Vol. 5, pp. 670–679, 1998.

[29]Gavrielides, M. A., Kallergi, M., and Clarke, L. P., Automatic shape analysis and classification of mammographic calcifications, In: SPIE, Vol. 3034, pp. 869–876, 1997.

[30]Tolstov, G. P., Fourier Series, Dover Publications, New York, 1962.

748

Kallergi, Heine, and Tembey

[31]Bracewell, R. L., The Fourier Transform and Its Applications, 2nd edn. revised, McGraw-Hill, New York, 1988.

[32]Brigham, E. O., The Fast Fourier Transform and Its Applications, Prentice Hall, Englewood Cliffs, NJ, 1988.

[33]Bracewell, R. L., Two-Dimensional Imaging, Prentice Hall, Englewood Cliffs, NJ, 1995.

[34]Beckmann, P., Probability in Communication Engineering, Harcort, Brace & World, New York, 1967.

[35]Thomas, J. B., An Introduction to Statistical Communication Theory, Wiley, New York, 1969.

[36]Helstrom, C. W., Probability and Stochastic Processes For Engineers, 2nd edn., Macmillan, New York, 1991.

[37]Papoulis, A., Probability, Random Variables, and Stochastic Processes, 3rd edn., McGraw-Hill, Boston, MA, 1991.

[38]Giffin, W. C., Transform Techniques for Probability Modeling, Academic Press, New York, 1975.

[39]Strang, G. and Nguyen, T., Wavelets and Filter Banks, WellesleyCambridge Press, Wellesley, MA, 1996.

[40]Akansu, A. N. and Haddad, R. A., Multiresolution Signal Decomposition Transforms, Subbands, and Wavelets, Academic Press, Boston, MA, 1992.

[41]Vetterli, M. and Kovacevic, J., Wavelets and Subband Coding, Prentice Hall, Englewood Cliffs, NJ, 1995.

[42]Daubechies, I., Ten Lectures on Wavelets, Society for Industrial and Applied Mathematics, Philadelphia, PA, 1992.

[43]Peitgen, H. O., Jurgens, H., and Saupe, D., Chaos and Fractals: New Frontiers of Science, Springer-Verlag, New York, 1992.

[44]Wornell, G. W., Signal Processing with Fractals: A Wavelet Based Approach, Prentice Hall, Upper Saddle River, NJ, 1996.

Computer-Aided Diagnosis of Mammographic Calcification Clusters

749

[45]Turner, M. J., Blackledge, J. M., and Andrews, P. R., Fractal Geometry in Digital Imaging, Academic Press, San Diego, CA, 1998.

[46]Heine, J. J., Deans, S. R., Cullers, D. K., Stauduhar, R., and Clarke, L. P., Multiresolution statistical analysis of high-resolution digital mammograms, IEEE Trans. Med. Imag., Vol. 16, No. 5, pp. 503–604, 1997.

[47]Heine, J. J., Deans, S. R., and Cullers, D. K., Stauduhar, R., and Clarke, L. P., Multiresolution probability analysis of gray scaled images, J. Opt. Soc. Am. A, Vol. 15, pp. 1048–1058, 1998.

[48]Heine, J. J., Deans, S. R., and Clarke, L. P., Multiresolution probability analysis of random fields, J. Opt. Soc. Am. A, Vol. 16, pp. 6–16, 1999.

[49]Mendenhall, W. and Scheaffer, R. L., Mathematical Statistics with Applications, Duxbury Press, North Scituate, MA, 1973.

[50]D’Orsi, C. J. and Kopans, D. B., Mammographic feature analysis, Sem. Roentgenol., Vol. XXVIII, No. 3, pp. 204–230, 1993.

[51]Heine, J. J., Multiresolution statistical analysis of direct x-ray detection digital mammograms, Final report, Department of Defense, CDMRD, 2002.

[52]Heine, J. J., Deans, S. R., Velthuizen, R. P., and Clarke, L. P., On the statistical nature Of mammograms, Med. Phys., Vol. 26, pp. 2254–2265, 1999.

[53]Burgess, A. E., Jacobson, F. L., and Judy, P. F., Human observer detection experiments with mammograms and power-law noise, Med. Phys., Vol. 28, No. 4, pp. 419–437, 2001.

[54]Heine, J. J., Deans, S. R., Gangadharan, D., and Clarke, L. P., Multiresolution analysis of two dimensional 1/f processes: Approximations, Opt. Eng., Vol. 38, pp. 1505–1516, 1999.

[55]Freedman, M., Pe, E., Zuurbier, R., Katial, R., Jafroudi, H., Nelson, M., Lo, S. C. B., and Mun, S. K., Image processing in digital mammography, SPIE, Vol. 2164, pp. 537–554, 1994.

750

Kallergi, Heine, and Tembey

[56]Woods, K., Automated Image Analysis Techniques for Digital Mammography, Ph.D. Dissertation, Department of Computer Science and Engineering, College of Engineering, University of South Florida, 1994.

[57]Shen, L., Rangayyan, R. M., and Desautels, J. E. L., Application of shape analysis to mammographic calcifications, IEEE Trans. Med. Imag., Vol. 13, No. 2, pp. 263–274, 1994.

[58]Jemal, A., Thomas, A., Murray, T., and Thun, M., Cancer statistics 2002, CA Cancer J. Clin., Vol. 52, pp. 23–47, 2002.

[59]Tembey, M., Computer Aided Diagnosis for Mammographic Microcalcification Clusters, MS Thesis, Computer Science Department, College of Engineering, University of South Florida, Tampa, FL, 2003.

[60]Burke, H. B., Goodman, P. H., Rosen, D. B., Henson, D. E., Weinstein, J. N., Harrell, F. E., Marks, J. R., Winchester, D. P., and Bostwick, D. G., Artificial neural networks improve the accuracy of cancer survival prediction, Cancer, Vol. 79, pp. 857–862, 1997.

[61]Efron, B., The Jacknife, the Bootstrap, and Other Resampling Plans, Society for Industrial and Applied Mathematics, Philadelphia, PA, 1982.

[62]Tourassi, G. D. and Floyd, C. E., The effect of data sampling on the performance evaluation of artificial neural networks in medical diagnosis, Med. Decis. Making, Vol. 17, pp. 186–192, 1997.

[63]Harrell, F. E., Lee, K. L., and Mark, D. B., Tutorial in biostatistics, multivariate prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors, Stat. Med., Vol. 15, pp. 361–387, 1996.

[64]Chen, D. R., Kuo, W. J., Chang, R. F., Moon, W. K., and Lee, C. C., Use of the bootstrap technique with small training sets for computer-aided diagnosis in breast ultrasound, Ultrasound Med. Biol., Vol. 28, No. 7, pp. 897–902, 2002.

[65]Nishikawa, R., Assessment of the performance of computer-aided detection and computer-aided diagnosis systems, Sem. Breast Dis., Vol. 5, No. 4, pp. 217–222, 2002.

Computer-Aided Diagnosis of Mammographic Calcification Clusters

751

[66]Bowyer, K. W., Validation of medical image analysis techniques, In: Handbook of Medical Imaging, Volume 2, Medical Image Processing and Analysis, Sonka, M. and Fitzpatrick, J. M., eds., SPIE Press, Bellingham, WA, pp. 567–607, 2000.

[67]University of Chicago. Kurt Rossmann Laboratories for Radiologic Image Research. http://home.uchicago.edu/njunji/KRL HP/roc soft.htm. Accessed September 2, 2004.

[68]Dorfman, D. D., Berbaum, K. S., and Lenth R. V., Multireader, multicase receiver operating characteristic methodology: A bootstrap analysis, Acad. Radiol., Vol 2, pp. 626–633, 1995.

[69]Nishikawa, R. M., Giger, M. L., Doi, K., Metz, C. E., Yin, F. F., Vyborny, C. J., and Schmidt R. A., Effect of case selection on the performance of computer-aided detection schemes, Med. Phys., Vol. 21, No. 2,

pp.265–269, 1994.

[70]Kallergi, M., Carney, G., and Gaviria, J., Evaluating the performance of detection algorithms in digital mammography, Med. Phys., Vol. 26, No. 2, pp. 267–275, 1999.

[71]D’Orsi, C. J. and Kopans, D. B., Mammographic feature analysis, Sem. Roentgenol., Vol. XXVIII, No. 3, pp. 204–230, 1993.

[72]Kallergi, M., Gavrielides, M. A., Gross, W. W., and Clarke, L. P., Evaluation of a CCD-based film digitizer for digital mammography, SPIE, Vol. 3032,

pp.282–291, 1997.

[73]Velthuizen, R. P. and Clarke, L. P., Digitized mammogram standardization for display and CAD, SPIE, Vol. 3335, pp. 179–187, 1998.

Chapter 14

Computer-Supported Segmentation

of Radiological Data

Philippe Cattin,1 Matthias Harders,1 Johannes Hug,1

Raimundo Sierra,1 and Gabor Szekely1

14.1 Introduction

Segmentation is in many cases the bottleneck when trying to use radiological image data in many clinically important applications as radiological diagnosis, monitoring, radiotherapy, and surgical planning. The availability of efficient segmentation methods is a critical issue especially in the case of large 3-D medical datasets as obtained today by the routine use of 3-D imaging methods like magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US).

Although manual image segmentation is often regarded as a gold standard, its usage is not acceptable in some clinical situations. In some applications such as computer-assisted neurosurgery or radiotherapy planning, e.g., a large number of organs have to be identified in the radiological datasets. While a careful and time-consuming analysis may be acceptable for outlining complex pathological objects, no real justification for such a procedure can be found for the delineation of normal, healthy organs at risk. Delineation of organ boundaries is also necessary in various types of clinical studies, where the correlation between morphological changes and therapeutical actions or clinical diagnosis has to be analyzed. In order to get statistically significant results, a large number of datasets has to be segmented. For such applications manual segmentation

1 Computer Vision Laboratory, ETH-Zurich, Switzerland

753

754

Cattin et al.

becomes questionable not only because of the amount of work, but also with regard to the poor reproducibility of the results.

Because of the above reasons, computer-assisted segmentation is a very important problem to be solved in medical image analysis. During the past decades a huge body of literature has emerged, addressing all facets of the related scientific and algorithmic problems. A reasonably comprehensive review of all relevant efforts is clearly beyond the scope of this chapter. Instead, we just tried to analyze the underlying problems and principles and concisely summarize the most important research results, which have been achieved by several generations of PhD students at the Computer Vision Laboratory of the Swiss Federal Institute of Technology during the past 20 years.

14.2 Intensity-Based Automatic Segmentation

Early approaches for automatic segmentation fundamentally use the assumption that radiological images are basically “self-contained,” i.e., they contain most of the information which is necessary for the identification of anatomical objects. In some limited applications such techniques can be very successful, as the automatic segmentation of dual-echo MR images [1]. This example will be used here as an illustration as it addresses most aspects of intensity-based medical image segmentation. The method uses two spatially perfectly matched echos of a spin-echo MR acquisition as illustrated by Figs. 14.1(a) and 14.1(c).

Figure 14.1: Spin-echo MR image pair (an early echo is shown on the left, a late echo on the right). In the middle the two-dimensional intensity distribution (i.e., the frequency of the occurrence of intensities I1 and I2 in the left and right images) is given.