Comparison of Accuracies for Image-based 1.5T and 3T MRI Using a Clinical Decision Support System Driven by a Support Vector Machine to Detect Seminal Vesicle Invasion of Prostate Cancer

서포트 벡터 머신을 이용한 영상기반의 임상 결정 보조 시스템에 근거한 전립선암의 정낭침습 판단: 1.5T와 3.0T 전립선 자기공명영상에서의 임상 결정 보조 시스템의 정확성 비교

  • Kim, Sang-Youn (Department of Radiology, Seoul National University College of Medicine) ;
  • Lee, Hak-Jong (Department of Radiology, Seoul National University College of Medicine) ;
  • Jung, Dae-Chul (Department of Radiology, Research Institute and Hospital, National Cancer Center) ;
  • Hwang, Sung-Il (Department of Radiology, Seoul National University College of Medicine) ;
  • Sung, Chang-Kyu (Department of Radiology, Seoul National University College of Medicine) ;
  • Cho, Jeong-Yeon (Department of Radiology, Seoul National University College of Medicine) ;
  • Kim, Seung-Hyup (Department of Radiology, Seoul National University College of Medicine)
  • 김상윤 (서울대학교 의과대학 영상의학과) ;
  • 이학종 (서울대학교 의과대학 영상의학과) ;
  • 정대철 (국립암센터 영상의학과) ;
  • 황성일 (서울대학교 의과대학 영상의학과) ;
  • 성창규 (서울대학교 의과대학 영상의학과) ;
  • 조정연 (서울대학교 의과대학 영상의학과) ;
  • 김승협 (서울대학교 의과대학 영상의학과)
  • Received : 2010.01.18
  • Accepted : 2010.03.21
  • Published : 2010.07.01

Abstract

Purpose: The purpose of this study is to develop image-based clinical decision support systems (CDSSs) using support vector machine models (SVMs) for the detection of seminal vesicle invasion (SVI) of prostate cancer and to compare the accuracies of 1.5T and 3.0T MR CDSSs. Materials and Methods: A total of 548 prostate cancer patients who underwent a prostatectomy and preoperative MR using 1.5T or 3.0T were enrolled in this study. Each 1.5T and 3.0T group was subdivided into the training group and test group, arbitrarily. Images were analyzed in consensus by two radiologists. CDSS was constructed with input data that has the appearance of a seminal vesicle, PSA level and age in each training group, and with the output data of the probability for SVI using SVMs. The accuracy of the output data were evaluated with data of each test group. After a histopathologic correlation, the sensitivity, specificity and accuracy for the detection of SVI were compared in both 1.5T and 3.0T. Results: For the diagnosis of SVI, the specificity and the accuracy of the 3.0T model were all statistically superior to those of the 1.5T model (90.4% vs. 73.1%; 88.7% vs. 74.6%) (p<0.05). Conclusion: The image-based CDSS for the detection of SVI was successfully constructed using SVM. According to our CDSSs, the specificity and accuracy of 3.0T were superior to those of 1.5T.

목적: 서포트 벡터 머신을 이용한 영상기반의 임상 결정 보조 시스템을 만들고, 이를 이용하여 정낭침습의 진단에 있어 1.5T와 3.0T 기기 간 보조 시스템의 진단 정확성을 비교하였다.대상과 방법: 전립선암으로 진단받고 1.5T 혹은 3.0T 자기공명영상을 시행하고 나서 전립선절제술을 받은 548명 환자를 대상으로 하였다. 1.5T 및 3.0T 기기로 검사한 집단을 각각 임의로 훈련 대상군과 테스트 대상군으로 분류하였다. 영상소견은 2명의 영상의학전문의가 합의로 결정하였다 서포트 벡터 머신을 이용하여 훈련 대상군의 정낭의 모양, 나이, 전립선 특이 항원 수치를 입력 값으로, 전립선암의 정낭침습 가능성을 출력 값으로 하는 임상 결정 보조 시스템을 만들었다. 이 모델을 각 테스트 대상군에 적용시켜 출력 값의 정확성을 분석하였다. 병리조직학적 소견을 고려하여, 1.5T와 3.0T에서 정낭침습 진단에 있어 민감도, 특이도, 정확도를 비교하였다. 결과: 1.5T 모델의 특이도, 정확도는 73.1%, 74.6%이었고, 3.0T 모델의 특이도, 정확도는 90.4%, 88.7%이었다. 정낭침습 진단에 있어 3.0T 모델의 특이도 및 정확도가 1.5T 모델보다 유의하게 높았다(p < 0.05). 결론: 전립선암의 정낭침습에 대해 서포트 벡터 머신을 이용하여 영상기반의 임상 결정 보조 시스템을 만들 수 있었다. 정낭침습 진단능의 비교에서, 1.5T보다는 3.0T 기기를 이용한 보조 시스템이 더 높은 특이도와 정확도를 보였다.

Keywords

References

  1. Won YJ, Sung JH, Jung KW, Kong HJ, Park SH, Shin HR, et al. Nationwide cancer incidence in Korea, 2003-2005. Cancer Res Treat 2009;41:122-131 https://doi.org/10.4143/crt.2009.41.3.122
  2. Kang TJ, Song CR, Song GH, Shin GH, Shin DI, Kim CS, et al. The anatomic distribution and pathological characteristics of prostate cancer: a mapping analysis. Korean J Urol 2006;47:578-585 https://doi.org/10.4111/kju.2006.47.6.578
  3. Hull GW, Rabbani F, Abbas F, Wheeler TM, Kattan MW, Scardino PT. Cancer control with radical prostatectomy alone in 1,000 consecutive patients. J Urol 2002;167:528-534 https://doi.org/10.1016/S0022-5347(01)69079-7
  4. Koh H, Kattan MW, Scardino PT, Suyama K, Maru N, Slawin K, et al. A nomogram to predict seminal vesicle invasion by the extent and location of cancer in systematic biopsy results. J Urol 2003;170:1203-1208 https://doi.org/10.1097/01.ju.0000085074.62960.7b
  5. Sala E, Akin O, Moskowitz CS, Eisenberg HF, Kuroiwa K, Ishill NM, et al. Endorectal MR imaging in the evaluation of seminal vesicle invasion: diagnostic accuracy and multivariate feature analysis. Radiology 2006;238:929-937 https://doi.org/10.1148/radiol.2383050657
  6. Jung DC, Lee HJ, Kim SH, Choe GY, Lee SE. Preoperative MR imaging in the evaluation of seminal vesicle invasion in prostate cancer: pattern analysis of seminal vesicle lesions. J Magn Reson Imaging 2008;28:144-150 https://doi.org/10.1002/jmri.21422
  7. Ikonen S, Karkkainen P, Kivisaari L, Salo JO, Taari K, Vehmas T, et al. Endorectal magnetic resonance imaging of prostatic cancer: comparison between fat-suppressed T2-weighted fast spin echo and three-dimensional dual-echo, steady-state sequences. Eur Radiol 2001;11:236-241 https://doi.org/10.1007/s003300000598
  8. Ikonen S, Karkkainen P, Kivisaari L, Salo JO, Taari K, Vehmas T, et al. Magnetic resonance imaging of clinically localized prostatic cancer. J Urol 1998;159:915-919 https://doi.org/10.1016/S0022-5347(01)63770-4
  9. Rorvik J, Halvorsen OJ, Albrektsen G, Ersland L, Daehlin L, Haukaas S. MRI with an endorectal coil for staging of clinically localized prostate cancer prior to radical prostatectomy. Eur Radiol 1999;9:29-34 https://doi.org/10.1007/s003300050622
  10. Schiebler ML, Yankaskas BC, Tempany C, Spritzer CE, Rifkin MD, Pollack HM, et al. MR imaging in adenocarcinoma of the prostate: interobserver variation and efficacy for determining stage C disease. AJR Am J Roentgenol 1992;158:559-562 https://doi.org/10.2214/ajr.158.3.1738994
  11. Park BK, Kim BH, Kim CK, Lee HM, Kwon GY. Comparison of phased-array 3.0-T and endorectal 1.5-T magnetic resonance imaging in the evaluation of local staging accuracy for prostate cancer. J Comput Assist Tomogr 2007;31:534-538 https://doi.org/10.1097/01.rct.0000250108.85799.e1
  12. Sosna J, Pedrosa I, Dewolf WC, Mahallati H, Lenkinski RE, Rofsky NM. MR imaging of the prostate at 3 Tesla: comparison of an external phased-array coil to imaging with an endorectal coil at 1.5 Tesla. Acad Radiol 2004;11:857-862 https://doi.org/10.1016/j.acra.2004.04.013
  13. Torricelli P, Cinquantini F, Ligabue G, Bianchi G, Sighinolfi P, Romagnoli R. Comparative evaluation between external phased array coil at 3T and endorectal coil at 1.5T: preliminary results. J Comput Assist Tomogr 2006;30:355-361 https://doi.org/10.1097/00004728-200605000-00002
  14. Suzuki H, Komiya A, Kamiya N, Imamoto T, Kawamura K, Miura J, et al. Development of a nomogram to predict probability of positive initial prostate biopsy among Japanese patients. Urology 2006;67:131-136 https://doi.org/10.1016/j.urology.2005.07.040
  15. Snow PB, Smith DS, Catalona WJ. Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study. J Urol 1994;152:1923-1926 https://doi.org/10.1016/S0022-5347(17)32416-3
  16. Stephan C, Cammann H, Semjonow A, Diamandis EP, Wymenga LF, Lein M, et al. Multicenter evaluation of an artificial neural network to increase the prostate cancer detection rate and reduce unnecessary biopsies. Clin Chem 2002;48:1279-1287
  17. Walz J, Graefen M, Chun FK, Erbersdobler A, Haese A, Steuber T, et al. High incidence of prostate cancer detected by saturation biopsy after previous negative biopsy series. Eur Urol 2006;50:498-505 https://doi.org/10.1016/j.eururo.2006.03.026
  18. Nam RK, Toi A, Klotz LH, Trachtenberg J, Jewett MA, Appu S, et al. Assessing individual risk for prostate cancer. J Clin Oncol 2007;25:3582-3588 https://doi.org/10.1200/JCO.2007.10.6450
  19. Bianco FJ Jr. Nomograms and medicine. Eur Urol 2006;50:884-886 https://doi.org/10.1016/j.eururo.2006.07.043
  20. Cortes C, Vapnik V. Support-vector networks. Machine Learning 1995;20:273-297
  21. Vapnik V. The nature of statistical learning theory. Berlin: Springer, 2000:123-160
  22. Comak E, Arslan A, Turkoglu I. A decision support system based on support vector machines for diagnosis of the heart valve diseases. Comput Biol Med 2007;37:21-27 https://doi.org/10.1016/j.compbiomed.2005.11.002
  23. Blute ML, Bergstralh EJ, Iocca A, Scherer B, Zincke H. Use of Gleason score, prostate specific antigen, seminal vesicle and margin status to predict biochemical failure after radical prostatectomy. J Urol 2001;165:119-125 https://doi.org/10.1097/00005392-200101000-00030
  24. Epstein JI, Partin AW, Potter SR, Walsh PC. Adenocarcinoma of the prostate invading the seminal vesicle: prognostic stratification based on pathologic parameters. Urology 2000;56:283-288 https://doi.org/10.1016/S0090-4295(00)00640-3
  25. Salomon L, Anastasiadis AG, Johnson CW, McKiernan JM, Goluboff ET, Abbou CC, et al. Seminal vesicle involvement after radical prostatectomy: predicting risk factors for progression. Urology 2003;62:304-309 https://doi.org/10.1016/S0090-4295(03)00373-X
  26. Vapnik V. Statistical learning theory, wiley series on adaptive and learning systems for signal processing, communications and control. New York: John Wiley & Sons, 1998
  27. Duda RO, Peter EH, David GS. Pattern classification. 2nd ed. New York: Wiley-Interscience publication, 2001
  28. Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods. Cambridge: Cambridge University Press, 2000:93-122
  29. Byvatov E, Fechner U, Sadowski J, Schneider G. Comparison of support vector machine and artificial neural network systems for drug/nondrug classification. J Chem Inf Comput Sci 2003;43:1882-1889 https://doi.org/10.1021/ci0341161
  30. Hearst M. Trends and controversies-support vector machines. IEEE Intelligent Systems 1998;13:18-28
  31. Beyersdorff D, Taymoorian K, Knosel T, Schnorr D, Felix R, Hamm B, et al. MRI of prostate cancer at 1.5 and 3.0T: comparison of image quality in tumor detection and staging. AJR Am J Roentgenol 2005;185:1214-1220 https://doi.org/10.2214/AJR.04.1584