Evaluation of the dose distribution behind the prostheses in prostate cancer patients with hip prostheses using film dosimetry and specially designed phantom

2012 ◽  
Vol 27 (4) ◽  
pp. 172-180
Keyword(s):  
Prostate Cancer ◽  
Cancer Patients ◽  
Dose Distribution ◽  
Film Dosimetry ◽  
Hip Prostheses

scholarly journals A convolutional neural network approach for IMRT dose distribution prediction in prostate cancer patients

2019 ◽  
Vol 60 (5) ◽  
pp. 685-693 ◽  
Author(s):  
Tomohiro Kajikawa ◽  
Noriyuki Kadoya ◽  
Kengo Ito ◽  
Yoshiki Takayama ◽  
Takahito Chiba ◽  
...  
Keyword(s):  
Neural Network ◽  
Prostate Cancer ◽  
Convolutional Neural Network ◽  
Cancer Patients ◽  
Dose Distribution ◽  
Organs At Risk ◽  
Model Performance ◽  
Estimation Algorithm ◽  
Neural Network Approach ◽  
Dose Distributions

Abstract The purpose of the study was to compare a 3D convolutional neural network (CNN) with the conventional machine learning method for predicting intensity-modulated radiation therapy (IMRT) dose distribution using only contours in prostate cancer. In this study, which included 95 IMRT-treated prostate cancer patients with available dose distributions and contours for planning target volume (PTVs) and organs at risk (OARs), a supervised-learning approach was used for training, where the dose for a voxel set in the dataset was defined as the label. The adaptive moment estimation algorithm was employed for optimizing a 3D U-net similar network. Eighty cases were used for the training and validation set in 5-fold cross-validation, and the remaining 15 cases were used as the test set. The predicted dose distributions were compared with the clinical dose distributions, and the model performance was evaluated by comparison with RapidPlan™. Dose–volume histogram (DVH) parameters were calculated for each contour as evaluation indexes. The mean absolute errors (MAE) with one standard deviation (1SD) between the clinical and CNN-predicted doses were 1.10% ± 0.64%, 2.50% ± 1.17%, 2.04% ± 1.40%, and 2.08% ± 1.99% for D2, D98 in PTV-1 and V65 in rectum and V65 in bladder, respectively, whereas the MAEs with 1SD between the clinical and the RapidPlan™-generated doses were 1.01% ± 0.66%, 2.15% ± 1.25%, 5.34% ± 2.13% and 3.04% ± 1.79%, respectively. Our CNN model could predict dose distributions that were superior or comparable with that generated by RapidPlan™, suggesting the potential of CNN in dose distribution prediction.

EP-1404 CT ARTIFACTS EFFECT IN SIB-IMRT CONTOURING AND PLANNING FOR PROSTATE CANCER PATIENTS WITH BILATERAL HIP PROSTHESES

2012 ◽  
Vol 103 ◽  
pp. S533-S534
Author(s):  
J. Saez ◽  
X. Maldonado Pijoan ◽  
J. Rovira ◽  
M. Hermida Lopez ◽  
I. Toribio ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Cancer Patients ◽  
Hip Prostheses

scholarly journals Prediction of the cumulated dose for external beam irradiation of prostate cancer patients with 3D-CRT technique

Nukleonika ◽  
2016 ◽  
Vol 61 (1) ◽  
pp. 15-18
Author(s):  
Marta Giżyńska ◽  
Dorota Blatkiewicz ◽  
Beata Czyżew ◽  
Maciej Gałecki ◽  
Małgorzata Gil-Ulkowska ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Cancer Patients ◽  
Cumulative Dose ◽  
Dose Distribution ◽  
Setup Error ◽  
Dose Distributions ◽  
External Beam Irradiation ◽  
Original Plan ◽  
The Mean ◽  
3D Crt

Abstract Nowadays in radiotherapy, much effort is taken to minimize the irradiated volume and consequently minimize doses to healthy tissues. In our work, we tested the hypothesis that the mean dose distribution calculated from a few first fractions can serve as prediction of the cumulated dose distribution, representing the whole treatment. We made our tests for 25 prostate cancer patients treated with three orthogonal fields technique. We did a comparison of dose distribution calculated as a sum of dose distribution from each fraction with a dose distribution calculated with isocenter shifted for a mean setup error from a few first fractions. The cumulative dose distribution and predicted dose distributions are similar in terms of gamma (3 mm 3%) analysis, under condition that we know setup error from seven first fractions. We showed that the dose distribution calculated for the original plan with the isocenter shifted to the point, defined as the original isocenter corrected of the mean setup error estimated from the first seven fractions supports our hypothesis, i.e. can serve as a prediction for cumulative dose distribution.

Sign in / Sign up

Export Citation Format

Share Document