European Radiology

, Volume 20, Issue 6, pp 1476–1484

Image-based clinical decision support for transrectal ultrasound in the diagnosis of prostate cancer: comparison of multiple logistic regression, artificial neural network, and support vector machine

  • Hak Jong Lee
  • Sung Il Hwang
  • Seok-min Han
  • Seong Ho Park
  • Seung Hyup Kim
  • Jeong Yeon Cho
  • Chang Gyu Seong
  • Gheeyoung Choe
Urogenital

DOI: 10.1007/s00330-009-1686-x

Cite this article as:
Lee, H.J., Hwang, S.I., Han, S. et al. Eur Radiol (2010) 20: 1476. doi:10.1007/s00330-009-1686-x

Abstract

Purpose

We developed a multiple logistic regression model, an artificial neural network (ANN), and a support vector machine (SVM) model to predict the outcome of a prostate biopsy, and compared the accuracies of each model.

Method

One thousand and seventy-seven consecutive patients who had undergone transrectal ultrasound (TRUS)-guided prostate biopsy were enrolled in the study. Clinical decision models were constructed from the input data of age, digital rectal examination findings, prostate-specific antigen (PSA), PSA density (PSAD), PSAD in transitional zone, and TRUS findings. The patients were divided into the training and test groups in a randomized fashion. Areas under the receiver operating characteristic (ROC) curve (AUC, Az) were calculated to summarize the overall performance of each decision model for the task of prostate cancer prediction.

Results

The Az values of the ROC curves for the use of multiple logistic regression analysis, ANN, and the SVM were 0.768, 0.778, and 0.847, respectively. Pairwise comparison of the ROC curves determined that the performance of the SVM was superior to that of the ANN or the multiple logistic regression model.

Conclusion

Image-based clinical decision support models allow patients to be informed of the actual probability of having a prostate cancer.

Keywords

Support vector machine Artificial neural network Multiple logistic regression Prostate cancer US-transrectal 

Copyright information

© European Society of Radiology 2009

Authors and Affiliations

  • Hak Jong Lee
    • 1
    • 2
    • 3
  • Sung Il Hwang
    • 1
    • 2
    • 3
    • 9
  • Seok-min Han
    • 4
  • Seong Ho Park
    • 5
  • Seung Hyup Kim
    • 6
  • Jeong Yeon Cho
    • 6
  • Chang Gyu Seong
    • 7
  • Gheeyoung Choe
    • 8
  1. 1.Department of RadiologySeoul National University College of Medicine, Seoul National University Bundang HospitalSeongnamKorea
  2. 2.Department of RadiologyInstitute of Radiation Medicine, Seoul National University Medical Research CenterSeoulKorea
  3. 3.Department of RadiologyClinical Research Institute, Seoul National University HospitalSeoulKorea
  4. 4.Multimedia lab, Samsung Advanced Institute of TechnologyKiheungKorea
  5. 5.Department of RadiologyUniversity of Ulsan College of Medicine, Asan Medical CenterSeoulKorea
  6. 6.Department of RadiologySeoul National University College of Medicine, Seoul National University HospitalSeoulKorea
  7. 7.Department of RadiologySeoul National University Boramae HospitalSeoulKorea
  8. 8.Department of PathologySeoul National University College of Medicine, Seoul National University Bundang HospitalSeongnamKorea
  9. 9.Department of RadiologySeoul National University Bundang HospitalSeongnam-siKorea

Personalised recommendations