z-logo
open-access-imgOpen Access
A study of positioning orientation effect on segmentation accuracy using convolutional neural networks for rectal cancer
Author(s) -
Men Kuo,
Boimel Pamela,
JanopaulNaylor James,
Cheng Chingyun,
Zhong Haoyu,
Huang Mi,
Geng Huaizhi,
Fan Yong,
Plastaras John P.,
BenJosef Edgar,
Xiao Ying
Publication year - 2019
Publication title -
journal of applied clinical medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.83
H-Index - 48
ISSN - 1526-9914
DOI - 10.1002/acm2.12494
Subject(s) - segmentation , orientation (vector space) , artificial intelligence , supine position , convolutional neural network , hausdorff distance , computer science , sørensen–dice coefficient , pattern recognition (psychology) , medicine , nuclear medicine , computer vision , image segmentation , mathematics , surgery , geometry
Purpose Convolutional neural networks ( CNN ) have greatly improved medical image segmentation. A robust model requires training data can represent the entire dataset. One of the differing characteristics comes from variability in patient positioning (prone or supine) for radiotherapy. In this study, we investigated the effect of position orientation on segmentation using CNN . Methods Data of 100 patients (50 in supine and 50 in prone) with rectal cancer were collected for this study. We designed three sets of experiments for comparison: (a) segmentation using the model trained with data from the same orientation; (b) segmentation using the model trained with data from the opposite orientation; (c) segmentation using the model trained with data from both orientations. We performed fivefold cross‐validation. The performance was evaluated on segmentation of the clinical target volume ( CTV ), bladder, and femurs with Dice similarity coefficient ( DSC ) and Hausdorff distance ( HD ). Results Compared with models trained on cases positioned in the same orientation, the models trained with cases positioned in the opposite orientation performed significantly worse ( P  <   0.05) on CTV and bladder segmentation, but had comparable accuracy for femurs ( P  >   0.05). The average DSC values were 0.74 vs 0.84, 0.85 vs 0.88, and 0.91 vs 0.91 for CTV , bladder, and femurs, respectively. The corresponding HD values (mm) were 16.6 vs 14.6, 8.4 vs 8.1, and 6.3 vs 6.3, respectively. The models trained with data from both orientations have comparable accuracy ( P  >   0.05), with average DSC of 0.84, 0.88, and 0.91 and HD of 14.4, 8.1, and 6.3, respectively. Conclusions Orientation affects the accuracy for CTV and bladder, but has negligible effect on the femurs. The model trained from data combining both orientations performs as well as a model trained with data from the same orientation for all the organs. These observations can offer guidance on the choice of training data for accurate segmentation.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here