Xiaokun Liang1, Maxime Bassenne2, Dimitre H Hristov3, Md Tauhidul Islam4, Wei Zhao5, Mengyu Jia6, Zhicheng Zhang7, Michael Gensheimer8, Beth Beadle9, Quynh Le10, Lei Xing11. 1. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: xiaokun@stanford.edu. 2. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: bassenne@stanford.edu. 3. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: dhristov@stanford.edu. 4. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: tauhid@stanford.edu. 5. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: zhaow85@stanford.edu. 6. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: jeremy18@stanford.edu. 7. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: zzc623@stanford.edu. 8. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: mgens@stanford.edu. 9. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: bbeadle@stanford.edu. 10. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: qle@stanford.edu. 11. Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA. Electronic address: lei@stanford.edu.
Abstract
PURPOSE: To develop a deep unsupervised learning method with control volume (CV) mapping from patient positioning daily CT (dCT) to planning computed tomography (pCT) for precise patient positioning. METHODS: We propose an unsupervised learning framework, which maps CVs from dCT to pCT to automatically generate the couch shifts, including translation and rotation dimensions. The network inputs are dCT, pCT and CV positions in the pCT. The output is the transformation parameter of the dCT used to setup the head and neck cancer (HNC) patients. The network is trained to maximize image similarity between the CV in the pCT and the CV in the dCT. A total of 554 CT scans from 158 HNC patients were used for the evaluation of the proposed model. At different points in time, each patient had many CT scans. Couch shifts are calculated for the testing by averaging the translation and rotation from the CVs. The ground-truth of the shifts come from bone landmarks determined by an experienced radiation oncologist. RESULTS: The system positioning errors of translation and rotation are less than 0.47 mm and 0.17°, respectively. The random positioning errors of translation and rotation are less than 1.13 mm and 0.29°, respectively. The proposed method enhanced the proportion of cases registered within a preset tolerance (2.0 mm/1.0°) from 66.67% to 90.91% as compared to standard registrations. CONCLUSIONS: We proposed a deep unsupervised learning architecture for patient positioning with inclusion of CVs mapping, which weights the CVs regions differently to mitigate any potential adverse influence of image artifacts on the registration. Our experimental results show that the proposed method achieved efficient and effective HNC patient positioning.
PURPOSE: To develop a deep unsupervised learning method with control volume (CV) mapping from patient positioning daily CT (dCT) to planning computed tomography (pCT) for precise patient positioning. METHODS: We propose an unsupervised learning framework, which maps CVs from dCT to pCT to automatically generate the couch shifts, including translation and rotation dimensions. The network inputs are dCT, pCT and CV positions in the pCT. The output is the transformation parameter of the dCT used to setup the head and neck cancer (HNC) patients. The network is trained to maximize image similarity between the CV in the pCT and the CV in the dCT. A total of 554 CT scans from 158 HNC patients were used for the evaluation of the proposed model. At different points in time, each patient had many CT scans. Couch shifts are calculated for the testing by averaging the translation and rotation from the CVs. The ground-truth of the shifts come from bone landmarks determined by an experienced radiation oncologist. RESULTS: The system positioning errors of translation and rotation are less than 0.47 mm and 0.17°, respectively. The random positioning errors of translation and rotation are less than 1.13 mm and 0.29°, respectively. The proposed method enhanced the proportion of cases registered within a preset tolerance (2.0 mm/1.0°) from 66.67% to 90.91% as compared to standard registrations. CONCLUSIONS: We proposed a deep unsupervised learning architecture for patient positioning with inclusion of CVs mapping, which weights the CVs regions differently to mitigate any potential adverse influence of image artifacts on the registration. Our experimental results show that the proposed method achieved efficient and effective HNC patient positioning.
Authors: Guha Balakrishnan; Amy Zhao; Mert R Sabuncu; John Guttag; Adrian V Dalca Journal: IEEE Trans Med Imaging Date: 2019-02-04 Impact factor: 10.048
Authors: Wei Zhao; Bin Han; Yong Yang; Mark Buyyounouski; Steven L Hancock; Hilary Bagshaw; Lei Xing Journal: Radiother Oncol Date: 2019-07-11 Impact factor: 6.280
Authors: Peter H Ahn; Andrew I Ahn; C Joe Lee; Jin Shen; Ekeni Miller; Alex Lukaj; Elissa Milan; Ravindra Yaparpalvi; Shalom Kalnicki; Madhur K Garg Journal: Int J Radiat Oncol Biol Phys Date: 2009-02-01 Impact factor: 7.038
Authors: X Sharon Qi; Angie Y Hu; Steve P Lee; Percy Lee; John DeMarco; X Allen Li; Michael L Steinberg; Patrick Kupelian; Daniel Low Journal: Int J Radiat Oncol Biol Phys Date: 2013-03-06 Impact factor: 7.038
Authors: Travers Ching; Daniel S Himmelstein; Brett K Beaulieu-Jones; Alexandr A Kalinin; Brian T Do; Gregory P Way; Enrico Ferrero; Paul-Michael Agapow; Michael Zietz; Michael M Hoffman; Wei Xie; Gail L Rosen; Benjamin J Lengerich; Johnny Israeli; Jack Lanchantin; Stephen Woloszynek; Anne E Carpenter; Avanti Shrikumar; Jinbo Xu; Evan M Cofer; Christopher A Lavender; Srinivas C Turaga; Amr M Alexandari; Zhiyong Lu; David J Harris; Dave DeCaprio; Yanjun Qi; Anshul Kundaje; Yifan Peng; Laura K Wiley; Marwin H S Segler; Simina M Boca; S Joshua Swamidass; Austin Huang; Anthony Gitter; Casey S Greene Journal: J R Soc Interface Date: 2018-04 Impact factor: 4.293