Abstract
Computer-aided diagnosis (CAD) for detection of lesions in medical images has been an active area of research. Machine learning plays an essential role in CAD, because representing lesions and organs requires a complex model that has a number of parameters to determine; thus, medical pattern recognition essentially requires “learning from examples” to determine the parameters of the model. Machine learning has been used to classify lesions into certain classes (e.g., abnormal or normal, lesions or non-lesions, and malignant or benign) in CAD. Recently, as available computational power increased dramatically, pixel/voxel-based machine learning (PML) has emerged in medical image processing/analysis, which uses pixel/voxel values in local regions (or patches) in images instead of features calculated from segmented regions as input information; thus, feature calculation or segmentation is not required. Because PML can avoid errors caused by inaccurate feature calculation and segmentation, the performance of PML can potentially be higher than that of common classifiers. In this chapter, MTANNs (a class of PML) in CAD schemes for detection of lung nodules in CT and for detection of polyps in CTC are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Giger ML, Suzuki K (2007) Computer-aided diagnosis (CAD). In: Feng DD (ed) Biomedical information technology. Academic Press, New York, pp 359–374
Doi K (2005) Current status and future potential of computer-aided diagnosis in medical imaging. Br J Radiol 78(1):S3–S19
Li F, Aoyama M, Shiraishi J, Abe H, Li Q et al (2004) Radiologists’ performance for differentiating benign from malignant lung nodules on high-resolution CT using computer-estimated likelihood of malignancy. Am J Roentgenol 183(5):1209–1215
Li F, Arimura H, Suzuki K, Shiraishi J, Li Q et al (2005) Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization. Radiology 237(2):684–690
Dean JC, Ilvento CC (2006) Improved cancer detection using computer-aided detection with diagnostic and screening mammography: prospective study of 104 cancers. Am J Roentgenol 187(1):20–28
Suzuki K, Shiraishi J, Abe H, MacMahon H, Doi K (2005) False-positive reduction in computer-aided diagnostic scheme for detecting nodules in chest radiographs by means of massive training artificial neural network. Acad Radiol 12(2):191–201
van Ginneken B, ter Haar Romeny BM, Viergever MA (2001) Computer-aided diagnosis in chest radiography: a survey. IEEE Trans Med Imaging 20(12):1228–1241
Giger ML, Doi K, MacMahon H (1988) Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields. Med Phys 15(2):158–166
Suzuki K, Armato SG, Li F, Sone S, Doi K (2003) Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose CT. Med Phys 30(7):1602–1617
Arimura H, Katsuragawa S, Suzuki K, Li F, Shiraishi J et al (2004) Computerized scheme for automated detection of lung nodules in low-dose computed tomography images for lung cancer screening. Acad Radiol 11(6):617–629
Armato SG 3rd, Giger ML, Moran CJ, Blackburn JT, Doi K et al (1999) Computerized detection of pulmonary nodules on CT scans. Radiographics 19(5):1303–1311
Armato SG 3rd, Li F, Giger ML, MacMahon H, Sone S et al (2002) Lung cancer: performance of automated lung nodule detection applied to cancers missed in a CT screening program. Radiology 225(3):685–692
Chan HP, Doi K, Galhotra S, Vyborny CJ, MacMahon H et al (1987) Image feature analysis and computer-aided diagnosis in digital radiography. I. Automated detection of microcalcifications in mammography. Med Phys 14(4):538–548
Gilhuijs KG, Giger ML, Bick U (1998) Computerized analysis of breast lesions in three dimensions using dynamic magnetic-resonance imaging. Med Phys 25(9):1647–1654
Horsch K, Giger ML, Vyborny CJ, Venta LA (2004) Performance of computer-aided diagnosis in the interpretation of lesions on breast sonography. Acad Radiol 11(3):272–280
Drukker K, Giger ML, Metz CE (2005) Robustness of computerized lesion detection and classification scheme across different breast US platforms. Radiology 237(3):834–840
Yoshida H, Nappi J (2001) Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps. IEEE Trans Med Imaging 20(12):1261–1274
Suzuki K, Yoshida H, Nappi J, Dachman AH (2006) Massive-training artificial neural network (MTANN) for reduction of false positives in computer-aided detection of polyps: suppression of rectal tubes. Med Phys 33(10):3814–3824
Suzuki K, Yoshida H, Nappi J, Armato SG 3rd, Dachman AH (2008) Mixture of expert 3D massive-training ANNs for reduction of multiple types of false positives in CAD for detection of polyps in CT colonography. Med Phys 35(2):694–703
Lostumbo A, Wanamaker C, Tsai J, Suzuki K, Dachman AH (2010) Comparison of 2D and 3D views for evaluation of flat lesions in CT colonography. Acad Radiol 17(1):39–47
Fukunaga K (1990) Introduction to statistical pattern recognition, 2nd edn. Academic Press, San Diego
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536
Vapnik N (1995) The nature of statistical learning theory. Springer, Berlin
Shiraishi J, Li Q, Suzuki K, Engelmann R, Doi K (2006) Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification. Med Phys 33(7):2642–2653
Armato SG 3rd, Giger ML, MacMahon H (2001) Automated detection of lung nodules in CT scans: preliminary results. Med Phys 28(8):1552–1561
Aoyama M, Li Q, Katsuragawa S, MacMahon H, Doi K (2002) Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images. Med Phys 29(5):701–708
Aoyama M, Li Q, Katsuragawa S, Li F, Sone S et al (2003) Computerized scheme for determination of the likelihood measure of malignancy for pulmonary nodules on low-dose CT images. Med Phys 30(3):387–394
Jerebko K, Summers RM, Malley JD, Franaszek M, Johnson CD (2003) Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees. Med Phys 30(1):52–60
Suzuki K, Horiba I, Sugie N (2002) Efficient approximation of neural filters for removing quantum noise from images. IEEE Trans Signal Process 50(7):1787–1799
Suzuki K, Horiba I, Sugie N (2003) Neural edge enhancer for supervised edge enhancement from noisy images. IEEE Trans Pattern Anal Mach Intell 25(12):1582–1596
Suzuki K, Horiba I, Sugie N, Nanki M (2004) Extraction of left ventricular contours from left ventriculograms by means of a neural edge detector. IEEE Trans Med Imaging 23(3):330–339
Suzuki K, Li F, Sone S, Doi K (2005) Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network. IEEE Trans Med Imaging 24(9):1138–1150
Suzuki K, Abe H, MacMahon H, Doi K (2006) Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN). IEEE Trans Med Imaging 25(4):406–416
Suzuki K, Rockey DC, Dachman AH (2010) CT colonography: Advanced computer-aided detection scheme utilizing MTANNs for detection of “missed” polyps in a multicenter clinical trial. Med Phys 30:2–21
Suzuki K, Zhang J, Xu J (2010) Massive-training artificial neural network coupled with Laplacian-eigenfunction-based dimensionality reduction for computer-aided detection of polyps in CT colonography. IEEE Trans Med Imaging 29(11):1907–1917
Xu J, Suzuki K (2011) Massive-training support vector regression and Gaussian process for false-positive reduction in computer-aided detection of polyps in CT colonography. Med Phys 38(4):1888–1902
Suzuki K, Horiba I, Sugie N, Nanki M (2002) Neural filter with selection of input features and its application to image quality improvement of medical image sequences. IEICE Trans Inf Syst E85-D(10):1710–1718
Lo SB, Lou SA, Lin JS, Freedman MT, Chien MV et al (1995) Artificial convolution neural network techniques and applications for lung nodule detection. IEEE Trans Med Imaging 14(4):711–718
Lo SCB, Chan HP, Lin JS, Li H, Freedman MT et al (1995) Artificial convolution neural network for medical image pattern recognition. Neural Netw 8(7–8):1201–1214
Lin JS, Lo SB, Hasegawa A, Freedman MT, Mun SK (1996) Reduction of false positives in lung nodule detection using a two-level neural classification. IEEE Trans Med Imaging 15(2):206–217
Lo SC, Li H, Wang Y, Kinnard L, Freedman MT (2002) A multiple circular path convolution neural network system for detection of mammographic masses. IEEE Trans Med Imaging 21(2):150–158
Sahiner B, Chan HP, Petrick N, Wei D, Helvie MA et al (1996) Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images. IEEE Trans Med Imaging 15(5):598–610
Lawrence S, Giles CL, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8(1):98–113
Neubauer C (1998) Evaluation of convolutional neural networks for visual recognition. IEEE Trans Neural Netw 9(4):685–696
Wei D, Nishikawa RM, Doi K (1996) Application of texture analysis and shift-invariant artificial neural network to microcalcification cluster detection. Radiology 201:696–696
Zhang W, Doi K, Giger ML, Nishikawa RM, Schmidt RA (1996) An improved shift-invariant artificial neural network for computerized detection of clustered microcalcifications in digital mammograms. Med Phys 23(4):595–601
Zhang W, Doi K, Giger ML, Wu Y, Nishikawa RM et al (1994) Computerized detection of clustered microcalcifications in digital mammograms using a shift-invariant artificial neural network. Med Phys 21(4):517–524
Suzuki K, Armato SG 3rd, Li F, Sone S, Doi K (2003) Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography. Med Phys 30(7):1602–1617
Oda S, Awai K, Suzuki K, Yanaga Y, Funama Y et al (2009) Performance of radiologists in detection of small pulmonary nodules on chest radiographs: effect of rib suppression with a massive-training artificial neural network. Am J Roentgenol 193(5):W397–402
Suzuki K (2009) A supervised ‘lesion-enhancement’ filter by use of a massive-training artificial neural network (MTANN) in computer-aided diagnosis (CAD). Phys Med Biol 54(18):S31–45
Xu JW, Suzuki K (2010 ) False-positive reduction in computer-aided detection of polyps in CT colonography: a massive-training support vector regression approach. In: MICCAI workshop on computational challenges and clinical opportunities in virtual colonoscopy and abdominal imaging, Beijing, China pp. 55–60
Mosier CI (1951) Problems and designs of cross-validation. Educ Psychol Meas 11:5–11
Jemal A, Murray T, Ward E, Samuels A, Tiwari RC et al (2005) Cancer statistics, 2005. CA Cancer J Clin 55(1):10–30
Cancer Facts and Figures (2005) American Cancer Society, Atlanta
Flehinger BJ, Kimmel M, Melamed MR (1992) The effect of surgical treatment on survival from early lung cancer. Implications for screening. Chest 101(4):1013–1018
Sobue T, Suzuki T, Matsuda M, Kuroishi T, Ikeda S et al (1992) Survival for clinical stage I lung cancer not surgically treated. Comparison between screen-detected and symptom-detected cases. The Japanese Lung Cancer Screening Research Group. Cancer 69(3):685–692
Miettinen S (2000) Screening for lung cancer. Radiol Clin North Am 38(3):479–486
Heelan RT, Flehinger BJ, Melamed MR, Zaman MB, Perchick WB et al (1984) Non-small-cell lung cancer: results of the New York screening program. Radiology 151(2):289–293
Frost JK, Ball WC Jr, Levin ML, Tockman MS, Baker RR et al (1984) Early lung cancer detection: results of the initial (prevalence) radiologic and cytologic screening in the Johns Hopkins study. Am Rev Respir Dis 130(4):549–554
Flehinger BJ, Melamed MR, Zaman MB, Heelan RT, Perchick WB et al (1984) Early lung cancer detection: results of the initial (prevalence) radiologic and cytologic screening in the Memorial Sloan-Kettering study. Am Rev Respir Dis 130(4):555–560
Fontana RS, Sanderson DR, Taylor WF, Woolner LB, Miller WE et al (1984) Early lung cancer detection: results of the initial (prevalence) radiologic and cytologic screening in the Mayo Clinic study. Am Rev Respir Dis 130(4):561–565
Kubik A, Polak J (1986) Lung cancer detection. Results of a randomized prospective study in Czechoslovakia. Cancer 57(12):2427–2437
Henschke CI, McCauley DI, Yankelevitz DF, Naidich DP, McGuinness G et al (1999) Early Lung Cancer Action Project: overall design and findings from baseline screening. Lancet 354(9173):99–105
Miettinen S, Henschke CI (2001) CT screening for lung cancer: coping with nihilistic recommendations. Radiology 221(3):592–596
Henschke CI, Naidich DP, Yankelevitz DF, McGuinness G, McCauley DI et al (2001) Early lung cancer action project: initial findings on repeat screenings. Cancer 92(1):153–159
Swensen SJ, Jett JR, Hartman TE, Midthun DE, Sloan JA et al (2003) Lung cancer screening with CT: Mayo Clinic experience. Radiology 226(3):756–761
Kaneko M, Eguchi K, Ohmatsu H, Kakinuma R, Naruke T et al (1996) Peripheral lung cancer: screening and detection with low-dose spiral CT versus radiography. Radiology 201(3):798–802
Sone S, Takashima S, Li F, Yang Z, Honda T et al (1998) Mass screening for lung cancer with mobile spiral computed tomography scanner. Lancet 351(9111):1242–1245
Sone S, Li F, Yang ZG, Honda T, Maruyama Y et al (2001) Results of three-year mass screening programme for lung cancer using mobile low-dose spiral computed tomography scanner. Br J Cancer 84(1):25–32
Nawa T, Nakagawa T, Kusano S, Kawasaki Y, Sugawara Y et al (1996) Lung cancer screening using low-dose spiral CT: results of baseline and 1-year follow-up studies. Chest 122(1):15–20
Gurney JW (1996) Missed lung cancer at CT: imaging findings in nine patients. Radiology 199(1):117–122
Li F, Sone S, Abe H, MacMahon H, Armato SG 3rd et al (2002) Lung cancers missed at low-dose helical CT screening in a general population: comparison of clinical, histopathologic, and imaging findings. Radiology 225(3):673–683
Kobayashi T, Xu XW, MacMahon H, Metz CE, Doi K (1996) Effect of a computer-aided diagnosis scheme on radiologists’ performance in detection of lung nodules on radiographs. Radiology 199(3):843–848
Otsu N (1979) A threshold selection method from gray level histograms. IEEE Trans Syst Man Cybern 9(1):62–66
Funahashi K (1989) On the approximate realization of continuous mappings by neural networks. Neural Netw 2:183–192
Suzuki K, Horiba I, Sugie N (2001) A simple neural network pruning algorithm with application to filter synthesis. Neural Process Lett 13(1):43–53
Suzuki K (2004) Determining the receptive field of a neural filter. J Neural Eng 1(4):228–237
Suzuki K, Doi K (2005) How can a massive training artificial neural network (MTANN) be trained with a small number of cases in the distinction between nodules and vessels in thoracic CT? Acad Radiol 12(10):1333–1341
Egan JP, Greenberg GZ, Schulman AI (1961) Operating characteristics, signal detectability, and the method of free response. J Acoust Soc Am 33:993–1007
Li Q, Sone S, Doi K (2003) Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. Med Phys 30(8):2040–2051
Winawer SJ, Fletcher RH, Miller L, Godlee F, Stolar MH et al (1997) Colorectal cancer screening: clinical guidelines and rationale. Gastroenterology 112(2):594–642
Dachman H (2003) Atlas of virtual colonoscopy. Springer, New York
Macari M, Bini EJ (2005) CT colonography: where have we been and where are we going? Radiology 237(3):819–833
Fletcher JG, Booya F, Johnson CD, Ahlquist D (2005) CT colonography: unraveling the twists and turns. Curr Opin Gastroenterol 21(1):90–98
Yoshida H, Dachman AH (2005) CAD techniques, challenges, and controversies in computed tomographic colonography. Abdom Imaging 30(1):26–41
Johnson CD, Dachman AH (2000) CT colonography: the next colon screening examination? Radiology 216(2):331–341
Nappi J, Yoshida H (2003) Feature-guided analysis for reduction of false positives in CAD of polyps for computed tomographic colonography. Med Phys 30(7):1592–1601
Frimmel H, Nappi J, Yoshida H (2004) Fast and robust computation of colon centerline in CT colonography. Med Phys 31(11):3046–3056
Yoshida H, Masutani Y, MacEneaney P, Rubin DT, Dachman AH (2002) Computerized detection of colonic polyps at CT colonography on the basis of volumetric features: pilot study. Radiology 222(2):327–336
Kupinski MA, Edwards DC, Giger ML, Metz CE (2001) Ideal observer approximation using Bayesian classification neural networks. IEEE Trans Med Imaging 20(9):886–899
Nappi J, Yoshida H (2002) Automated detection of polyps with CT colonography: evaluation of volumetric features for reduction of false-positive findings. Acad Radiol 9(4):386–397
Suzuki K, Armato SG, Li F, Sone S, Doi K (2003) Effect of a small number of training cases on the performance of massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose CT. In: Proceedings of SPIE Medical Imaging (SPIE MI), San Diego, CA, pp 1355–1366
Rockey DC, Paulson E, Niedzwiecki D, Davis W, Bosworth HB et al (2005) Analysis of air contrast barium enema, computed tomographic colonography, and colonoscopy: prospective comparison. Lancet 365(9456):305–311
Doshi T, Rusinak D, Halvorsen RA, Rockey DC, Suzuki K et al (2007) CT colonography: false-negative interpretations. Radiology 244(1):165–173
Edwards DC, Kupinski MA, Metz CE, Nishikawa RM (2002) Maximum likelihood fitting of FROC curves under an initial-detection-and-candidate-analysis model. Med Phys 29(12):2861–2870
Rembacken BJ, Fujii T, Cairns A, Dixon MF, Yoshida S et al (2000) Flat and depressed colonic neoplasms: a prospective study of 1000 colonoscopies in the UK. Lancet 355(9211):1211–1214
Soetikno RM, Kaltenbach T, Rouse RV, Park W, Maheshwari A et al (2008) Prevalence of nonpolypoid (flat and depressed) colorectal neoplasms in asymptomatic and symptomatic adults. JAMA 299(9):1027–1035
Soetikno R, Friedland S, Kaltenbach T, Chayama K, Tanaka S (2006) Nonpolypoid (flat and depressed) colorectal neoplasms. Gastroenterology 130(2):566–576; quiz 588–589
Kudo S, Kashida H, Tamura T (2000) Early colorectal cancer: flat or depressed type. J Gastroenterol Hepatol 15(Suppl):D66–70
Kudo S, Kashida H, Tamura T, Kogure E, Imai Y et al (2000) Colonoscopic diagnosis and management of nonpolypoid early colorectal cancer. World J Surg 24(9):1081–1090
Ross S, Waxman I (2006) Flat and depressed neoplasms of the colon in Western populations. Am J Gastroenterol 101(1):172–180
Fujii T, Rembacken BJ, Dixon MF, Yoshida S, Axon AT (1998) Flat adenomas in the United Kingdom: are treatable cancers being missed? Endoscopy 30(5):437–443
Johnson CD, Chen MH, Toledano AY, Heiken JP, Dachman A et al (2008) Accuracy of CT colonography for detection of large adenomas and cancers. N Engl J Med 359(12):1207–1217
Fidler JL, Johnson CD, MacCarty RL, Welch TJ, Hara AK et al (2002) Detection of flat lesions in the colon with CT colonography. Abdom Imaging 27(3):292–300
Fidler J, Johnson C (2008) Flat polyps of the colon: accuracy of detection by CT colonography and histologic significance. Abdom Imaging
Taylor SA, Suzuki N, Beddoe G, Halligan S (2008) Flat neoplasia of the colon: CT colonography with CAD. Abdom Imaging 34(2):173–181
Lostumbo A, Suzuki K, Dachman AH (2009) Flat lesions in CT colonography. Abdom Imaging 34(2):173–181
Acknowledgments
This work would not have been possible without the help of countless individuals. The author acknowledges the invaluable assistance of all colleagues and support staff. The author is grateful to all members in the Suzuki Laboratory in the Department of Radiology at the University of Chicago, especially Ivan Sheu, Mark L Epstein, Jianwu Xu, and Sheng Chen, for their contributions to the studies, to colleagues and collaborators, especially Abraham H Dachman, Heber MacMahon, Kunio Doi, Samuel G Armato III, Feng Li, Shusuke Sone, Hiroyuki Abe, Qiang Li, Junji Shiraishi, Don C Rockey, Hiroyuki Yoshida, and Janne Nappi for their valuable suggestions, and to Ms. E. F. Lanzl for improving the chapter. The author is also grateful to his wife, Harumi Suzuki, for her assistance with the chapter and studies, and his daughters, Mineru Suzuki and Juno Suzuki, for cheering him up. This work was partly supported by Grant Number R01CA120549 from the National Cancer Institute/National Institutes of Health and by NIH S10 RR021039 and P30 CA14599.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Suzuki, K. (2014). Pixel-based Machine Learning in Computer-Aided Diagnosis of Lung and Colon Cancer. In: Dua, S., Acharya, U., Dua, P. (eds) Machine Learning in Healthcare Informatics. Intelligent Systems Reference Library, vol 56. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40017-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-40017-9_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40016-2
Online ISBN: 978-3-642-40017-9
eBook Packages: EngineeringEngineering (R0)