TY - JOUR
T1 - Markerless Pancreatic Tumor Target Localization Enabled By Deep Learning
AU - Zhao, Wei
AU - Shen, Liyue
AU - Han, Bin
AU - Yang, Yong
AU - Cheng, Kai
AU - Toesca, Diego A.S.
AU - Koong, Albert C.
AU - Chang, Daniel T.
AU - Xing, Lei
N1 - Funding Information:
This work was partially supported by the National Institutes of Health (1R01 CA176553 and R01CA227713) and a Faculty Research Award from Google Inc. We gratefully acknowledge the support of NVIDIA Corporation for the GPU donation. This work was partially supported by the National Institutes of Health (1R01 CA176553 and R01CA227713) and a Faculty Research Award from Google Inc. We gratefully acknowledge the support of NVIDIA Corporation for the GPU donation. We would like to thank Prof. Lei Dong for his useful discussion. This work was partially supported by the National Institutes of Health ( 1R01 CA176553 and R01CA227713) and a Faculty Research Award from Google Inc. We gratefully acknowledge the support of NVIDIA Corporation for the GPU donation.
Publisher Copyright:
© 2019 Elsevier Inc.
PY - 2019/10/1
Y1 - 2019/10/1
N2 - Purpose: Deep learning is an emerging technique that allows us to capture imaging information beyond the visually recognizable level of a human being. Because of the anatomic characteristics and location, on-board target verification for radiation delivery to pancreatic tumors is a challenging task. Our goal was to use a deep neural network to localize the pancreatic tumor target on kV x-ray images acquired using an on-board imager for image guided radiation therapy. Methods and Materials: The network is set up in such a way that the input is either a digitally reconstructed radiograph image or a monoscopic x-ray projection image acquired by the on-board imager from a given direction, and the output is the location of the planning target volume in the projection image. To produce a sufficient number of training x-ray images reflecting the vast number of possible clinical scenarios of anatomy distribution, a series of changes were introduced to the planning computed tomography images, including deformation, rotation, and translation, to simulate inter- and intrafractional variations. After model training, the accuracy of the model was evaluated by retrospectively studying patients who underwent pancreatic cancer radiation therapy. Statistical analysis using mean absolute differences (MADs) and Lin's concordance correlation coefficient were used to assess the accuracy of the predicted target positions. Results: MADs between the model-predicted and the actual positions were found to be less than 2.60 mm in anteroposterior, lateral, and oblique directions for both axes in the detector plane. For comparison studies with and without fiducials, MADs are less than 2.49 mm. For all cases, Lin's concordance correlation coefficients between the predicted and actual positions were found to be better than 93%, demonstrating the success of the proposed deep learning for image guided radiation therapy. Conclusions: We demonstrated that markerless pancreatic tumor target localization is achievable with high accuracy by using a deep learning technique approach.
AB - Purpose: Deep learning is an emerging technique that allows us to capture imaging information beyond the visually recognizable level of a human being. Because of the anatomic characteristics and location, on-board target verification for radiation delivery to pancreatic tumors is a challenging task. Our goal was to use a deep neural network to localize the pancreatic tumor target on kV x-ray images acquired using an on-board imager for image guided radiation therapy. Methods and Materials: The network is set up in such a way that the input is either a digitally reconstructed radiograph image or a monoscopic x-ray projection image acquired by the on-board imager from a given direction, and the output is the location of the planning target volume in the projection image. To produce a sufficient number of training x-ray images reflecting the vast number of possible clinical scenarios of anatomy distribution, a series of changes were introduced to the planning computed tomography images, including deformation, rotation, and translation, to simulate inter- and intrafractional variations. After model training, the accuracy of the model was evaluated by retrospectively studying patients who underwent pancreatic cancer radiation therapy. Statistical analysis using mean absolute differences (MADs) and Lin's concordance correlation coefficient were used to assess the accuracy of the predicted target positions. Results: MADs between the model-predicted and the actual positions were found to be less than 2.60 mm in anteroposterior, lateral, and oblique directions for both axes in the detector plane. For comparison studies with and without fiducials, MADs are less than 2.49 mm. For all cases, Lin's concordance correlation coefficients between the predicted and actual positions were found to be better than 93%, demonstrating the success of the proposed deep learning for image guided radiation therapy. Conclusions: We demonstrated that markerless pancreatic tumor target localization is achievable with high accuracy by using a deep learning technique approach.
UR - http://www.scopus.com/inward/record.url?scp=85068550358&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068550358&partnerID=8YFLogxK
U2 - 10.1016/j.ijrobp.2019.05.071
DO - 10.1016/j.ijrobp.2019.05.071
M3 - Article
C2 - 31201892
AN - SCOPUS:85068550358
SN - 0360-3016
VL - 105
SP - 432
EP - 439
JO - International Journal of Radiation Oncology Biology Physics
JF - International Journal of Radiation Oncology Biology Physics
IS - 2
ER -