Feasibility of anatomical feature points for the estimation of prostate locations in the Bayesian delineation frameworks for prostate cancer radiotherapy
This study aimed to investigate the feasibility of anatomical feature points for the estimation of prostate locations in the Bayesian delineation frameworks for prostate cancer radiotherapy. The relationships between the reference centroids of prostate regions (CPRs) (prostate locations) and anatomical feature points were explored, and the most feasible anatomical feature points were selected based on the smallest location estimation errors of CPRs and the largest Dice’s similarity coefficient (DSC) between the reference and extracted prostates. The reference CPRs were calculated according to reference prostate contours determined by radiation oncologists. Five anatomical feature points were manually determined on a prostate, bladder, and rectum in a sagittal plane of a planning computed tomography image for each case. The CPRs were estimated using three machine learning architectures [artificial neural network, random forest, and support vector machine (SVM)], which learned the relationships between the reference CPRs and anatomical feature points. The CPRs were applied for placing a prostate probabilistic atlas at the coordinates and extracting prostate regions using a Bayesian delineation framework. The average estimation errors without and with SVM using three feature points, which indicated the best performance, were 5.6 ± 3.7 mm and 1.8 ± 1.0 mm, respectively (the smallest error) (p < 0.001). The average DSCs without and with SVM using the three feature points were 0.69 ± 0.13 and 0.82 ± 0.055, respectively (the highest DSC) (p < 0.001). The anatomical feature points may be feasible for the estimation of prostate locations, which can be applied to the general Bayesian delineation frameworks for prostate cancer radiotherapy.
KeywordsAnatomical feature points Prostate location Machine learning Probabilistic atlas Bayesian inference Prostate cancer radiotherapy
Compliance with ethical standards
Conflict of interest
The authors declare no conflict of interest.
This study was approved by the Institutional Review Board of the Kyushu University Hospital.
This article does not include other studies using animal models.
- 10.Acosta O, Dowling J, Drean G, Simon A, De Crevoisier R, Haigron P. Multi-atlas-based segmentation of pelvic structures from ct scans for planning in prostate cancer radiotherapy. Abdomen Thorac Imaging An Eng Clin Perspect. 2014;623–56.Google Scholar
- 15.Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation. Parallel Distrib Process Explor Microstruct Cogn. 1986;318–62.Google Scholar
- 16.Meinshausen N. Quantile regression forests. J Mach Learn Res. 2006;7:983–99.Google Scholar
- 18.fitnet (Function fitting neural network). Mathworks. MATLAB. https://jp.mathworks.com/help/nnet/ref/fitnet.html. Accessed 20 Jul 2018.
- 19.TreeBagger (Create bag of decision trees). Mathworks. MATLAB. https://jp.mathworks.com/help/stats/treebagger.html. Accessed 20 Jul 2018.
- 20.fitrsvm (Fit a support vector machine regression model). Mathworks. MATLAB. https://jp.mathworks.com/help/stats/fitrsvm.html. Accessed 20 Jul 2018.
- 22.Lebesque JV, Bruce AM, Guus Kroes AP, Touw A, Shouman T, van Herk M. Variation in volumes, dose-volume histograms, and estimated normal tissue complication probabilities of rectum and bladder during conformal radiotherapy of T3 prostate cancer. Int J Radiat Oncol Biol Phys. 1995;33:1109–19.CrossRefGoogle Scholar
- 23.Hair JF, Black WC, Babin BJ, Anderson RE. Multivariate data analysis. New York: Pearson; 2010.Google Scholar
- 24.Bishop CM. Pattern recognition and machine learning. Pattern recognition. New York: Springer; 2006.Google Scholar