Breast MRI lesion classification: Improved performance of human readers with a backpropagation neural network computer-aided diagnosis (CAD) system

Journal of Magnetic Resonance Imaging

Volumn 25, Issue 1, 2007, Pages 89-95

  Meinel, Lina Arbash ^a   Stolpen, Alan H ^b   Berbaum, Kevin S ^b   Fajardo, Laurie L ^b   Reinhardt, Joseph M ^a  

^a IA United States   (United States)

^b UNIVERSITY OF IOWA HOSPITALS AND CLINICS   (United States)

Author keywords

Breast MRI; Computer aided diagnosis; Kinetics enhancement; Neural networks; Pattern recognition; Shape and texture features

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; BACK PROPAGATION; BREAST LESION; CANCER CLASSIFICATION; CANCER DIAGNOSIS; CANCER STAGING; CLINICAL FEATURE; COMPUTER ASSISTED DIAGNOSIS; CONTROLLED STUDY; DIAGNOSTIC ACCURACY; DIAGNOSTIC IMAGING; DIAGNOSTIC PROCEDURE; HISTOPATHOLOGY; HUMAN; HUMAN EXPERIMENT; IMAGE ANALYSIS; IMAGE ENHANCEMENT; IMAGE PROCESSING; KINETICS; MULTIREADER MULTICASE ANALYSIS; NORMAL HUMAN; NUCLEAR MAGNETIC RESONANCE IMAGING; PATTERN RECOGNITION; PERFORMANCE MEASUREMENT SYSTEM; PRIORITY JOURNAL; RADIODIAGNOSIS; RECEIVER OPERATING CHARACTERISTIC; ROC CURVE; TASK PERFORMANCE;

BREAST NEOPLASMS; CLINICAL COMPETENCE; CONTRAST MEDIA; DIAGNOSIS, COMPUTER-ASSISTED; DIAGNOSIS, DIFFERENTIAL; FEMALE; HUMANS; MAGNETIC RESONANCE IMAGING; MEGLUMINE; NEURAL NETWORKS (COMPUTER); OBSERVER VARIATION; ORGANOMETALLIC COMPOUNDS; ROC CURVE; SOFTWARE;

EID: 33846190665     PISSN: 10531807     EISSN: 15222586     Source Type: Journal    
DOI: 10.1002/jmri.20794     Document Type: Article

References (37)

1. Imaginis. Breast cancer: statistics on incidence, survival, and screening. 2002. Available at: http://www.imaginis.com/breast-health/statistics. asp.htm. Last accessed: October 7, 2006.
2. Starita A, LaManna S, Majidi D, Caramella D, Cilotti A. Magnetic resonance in mammography: a quantitative evaluation tool of contrast-enhanced magnetic resonance of the breast. In: First International Conference on Advances in Medical Signal and Information Processing, 2000. IEEE Conference Publication No. 476. Piscataway, NJ: Institute of Electrical and Electronics Engineers. p 200-205.
3. Verma B, Zakos J. A computer-aided diagnosis system for digital mammograms based on fuzzy-neural and feature extraction techniques. IEEE Trans Inf Technol Biomed 2001;5:46-54.
4. Lihua L, Clark R. Computer-aided diagnosis of masses with full-field digital mammography. Acad Radiol 2002;9:4-12.
5. Gulsrud TO, Husoy J. Optimal filter-based detection of microcalcifications. IEEE Trans Biomed Eng 2001;48:1272-1281.
6. Qian W, Li I. Image feature extraction for mass detection in digital mammography. Med Phys 1999;26:402-408.
7. Li H, Liu R, Lo S. Fractal modeling and segmentation for the enhancement of microcalcifications in digital mammograms. IEEE Trans Med Imaging 1997;16:785-798.
8. Chan H, Sahiner B. Computerized analysis of mammographic microcalcifications in morphological and texture feature space. Med Phys 1998;25:2007-2019.
9. Polakowski W, Cournoyer D. Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivation-based feature saliency. IEEE Trans Med Imaging 1997;16:811-819.
10. Liu S, Babbs CF, Delp EJ. Multiresolution detection of spiculated lesions in digital mammograms. IEEE Trans Image Process 2001;10:874-884.
11. Dhawan B, Alam P. Artificial-neural-network-based classification of mammographic microcalcifications using image structure features. In: Proceedings of the Biomedical Imaging and Biomedical Visualization Conference of SPIE, Vol. 1905. Bellingham, WA: International Society for Optical Engineering; 1993. p 820-831.
12. Yu S, Guan L, Brown S. Automatic detection of clustered microcalcifications in digital mammograms based on wavelet and neural network classification. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 3338. Bellingham, WA: International Society for Optical Engineering; 1998. p 1540-1546.
13. Li L, Clark R, Thomas J. Computer-aided diagnosis of masses with full-field digital mammography. Acad Radiol 2002;9:4-12.
14. Wu Y, Giger M, Doi K, Metz C, Nishikawa R. Application of artificial neural networks in mammography for diagnosis of breast cancer. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 1778. Bellingham, WA: International Society for Optical Engineering; 1992. p 19-27.
15. Christoyianni I, Dermatas E, Kokkinakis G. Neural classification of abnormal tissues in digital mammography using statistical features of the texture. In: Proceedings of the 6th International Conference on Electronics, Circuits and Systems of IEEE, England, 1999;117-120.
16. Land W, Masters T, Lo J. Application of adaptive boosting to EP-derived multilayer feed-forward neural networks (MLFN) to improve benign/malignant breast cancer classification. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 4322. Bellingham, WA: International Society for Optical Engineering; 2001. p 1717-1724.
17. Wu C. Image feature analysis for classification of microcalcifications in digital mammography: Neural network and genetic algorithms. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 3034. Bellingham, WA: International Society for Optical Engineering; 1997. p 499-507.
18. Huo Z, Giger ML, Vyborny C, Wolverton D, Schmidt R, Doi K. Automated computerized classification of malignant and benign mass lesions on digitized mammograms. Acad Radiol 1998;5:155-168.
19. Shih-Chung BL, Li H, Wang Y, Freedman M. A multiple circular path convolution neural network system for detection of mammographic masses. IEEE Trans Med Imaging 2002;21:150-158.
20. Yang ZR, Harrison RG. Detecting false benign in breast cancer diagnosis. IEEE Trans Neural Netw 2000;3:655-658.
21. Mudigonda NR, Rangayyan RM, Desautels JE. Detection of breast masses in mammograms by density slicing and texture flow-field analysis. IEEE Trans Med Imaging 2001;20:1215-1227.
22. Li L, Chu Y, Salem AF, Clark RA. Image segmentation and 3D visualization for MRI mammography. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 4684. Bellingham, WA: International Society for Optical Engineering; 2002. p 1780-1789.
23. Penn AI, Umar N, Thompson SF, Schnall MD, Wang F. Preliminary performance analysis of breast MRI CAD system. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 4322. Bellingham, WA: International Society for Optical Engineering; 2001. p 1944-1953.
24. Pohle R, Toennies KD. Segmentation of medical images using adaptive region growing. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 4322. Bellingham, WA: International Society for Optical Engineering; 2001. p 1337-1346.
25. Aykac D, Hoffman EA, McLennan G, Reinhardt JM. Segmentation and analysis of the human airway tree from three-dimensional x-ray CT images. IEEE Trans Med Imaging 2003;22:940-950.
26. Arbach L, Bennett DL, Reinhardt JM, Fallouh G. Distinguishing between malignant and non-malignant breast masses from mammograms using A1 techniques. Basel Al-Assad J Eng Sci 2002;16:103-121.
27. Nunes L, Schnall MD, Orel SG. Update of breast MR imaging architectural interpretation model. Radiology 2001;219:484-494.
28. Arbach L, Bennett DL, Reinhardt JM, Fallouh G. Classification of mammographic masses: comparison between backpropagation neural network BNN and human readers. In: Proceedings of the Medical Imaging Conference of SPIE, Vol. 5032. Bellingham, WA: International Society for Optical Engineering: 2003. p 810-818.
29. Rauber TW. TOOLDIAG: pattern recognition toolbox. Available at: http://www.inf.ufes.br/~thomas/home/tooldiag.html. Last accessed: October 26, 2006.
30. Duda R, Hart P, Stork D. Pattern classification, 2nd edition. New York: Wiley & Sons, 2000. 654 p.
31. Lera G, Pinzolas M. Neighborhood based Levenberg-Marquardt algorithm for neural network training. IEEE Trans Med Imaging 2002;13:1200-1203.
32. Nunes L, Schnall MD. Diagnostic performance characteristics of architectural features revealed by high spatial-resolution MR imaging of the breast. AJR Am J Roentgenol 1997;169:409-415.
33. Bruce LM, Adhami RR. Classifying mammographic mass shapes using the wavelet transform modulus-maxima method. IEEE Trans Med Imaging 1999;18:1170-1177.
34. Dorfman DD, Berbaum KS, Metz CE. Receiver operating characteristic rating analysis: generalization to the population of readers and patients with the jackknife method. Invest Radiol 1992;27:723-731.
35. Quenouille M. Approximate tests of correlation in time series. J R Stat Soc Ser B Methodol 1949;11:68-84.
36. Quenouille M. Notes on bias in estimation. Biometrika 1956;43:353-360.
37. Tukey J. Bias and confidence in not quite large samples. Ann Math Stat 1958;29:614-618.