Abstract
The use of image-guided radiotherapy (IGRT)/radiosurgery (IGRS) is inevitable for high-precision radiation treatment. This study aimed to predict the contribution of off-axis distance (OAD) factors in vertical (Z), longitudinal (Y), and lateral (X) directions calculated through experimental verification and distance criteria for the pass/fail rating of isocenter calibration. Experimental verification (n = 104) for periodic isocenter calibration between IGRS and linear accelerator (LINAC) was performed using a cube water slab phantom and radiochromic film. The dataset was used to develop a predictive model, basic statistical analysis was performed. In this first radiochromic analysis, the mean and standard deviations were calculated to be OAD (X) 0.43 ± 0.17 mm, OAD (Y) 0.42 ± 0.16 mm, and OAD (Z) 0.47 ± 0.15 mm for 104 experimental cases. In predictive modeling, feature importance analysis on X, Y, and Z revealed that OAD (Z), 0.066 (mean SHAP) was a remarkable factor in determining the passing rate for calibration. The probability of distinguishing the threshold distance for OAD (X, Y, and Z) was also calculated, and the performance metrics of the predictive model were calculated as 0.86 accuracy, 0.94 sensitivity, 0.61 specificity, and 0.84 AUC. Experimental verification of an IGRS system based on an optical camera by applying the predictive modeling technique confirmed that the significant prediction factor was the Z axis for the isocenter calibration of the LINAC and IGRT systems. The error was calculated at a threshold of under 0.5 mm between coordinates in the radiosurgery room.
Similar content being viewed by others
References
L. Leksell, Stereotactic radiosurgery. J. Neurol. Neurosurg. Psychiatry 46, 797–803 (1983)
S.I. Ryu, S.D. Chang, D.H. Kim, M.J. Murphy, Q.-T. Le, D.P. Martin, J.R. Adler Jr., Image-guided hypo-fractionated stereotactic radiosurgery to spinal lesions. Neurosurgery 49, 838–846 (2001)
K.H. Kim, K. Park, H. Kim, B. Jo, S.H. Ahn, C. Kim, M. Kim, T.H. Kim, S.B. Lee, D. Shin, Facial expression monitoring system for predicting patient’s sudden movement during radiotherapy using deep learning. J. Appl. Clin. Med. Phys. 21, 191–199 (2020)
M. Van Herk, Errors and margins in radiotherapy. Proc Semi Radiat Oncol. 14(1), 52–64 (2004)
M. Yang, R. Timmerman, Stereotactic ablative radiotherapy uncertainties: delineation, setup and motion. Proc Semi Radiat Oncol. 28(3), 207–217 (2018)
L. Xing, B. Thorndyke, E. Schreibmann, Y. Yang, T.-F. Li, G.-Y. Kim, G. Luxton, A. Koong, Overview of image-guided radiation therapy. Med. Dosim. 31, 91–112 (2006)
P.R. Poulsen, B. Cho, P.J. Keall, A method to estimate mean position, motion magnitude, motion correlation, and trajectory of a tumor from cone-beam CT projections for image-guided radiotherapy. Intern J Radiat Oncol Biol Phys. 72, 1587–1596 (2008)
T. Ackerly, C. Lancaster, M. Geso, K. Roxby, Clinical accuracy of ExacTrac intracranial frameless stereotactic system. Med. Phys. 38, 5040–5048 (2011)
T. Gevaert, D. Verellen, K. Tournel, N. Linthout, S. Bral, B. Engels, C. Collen, T. Depuydt, M. Duchateau, T. Reynders, Setup accuracy of the Novalis ExacTrac 6DOF system for frameless radiosurgery. Intern J Radia Oncol Biol Phys. 82, 1627–1635 (2012)
V.U. Chow, M.L. Cheung, M.W. Kan, A.T. Chan, Shift detection discrepancy between ExacTrac Dynamic system and cone-beam computed tomography. J. Appl. Clin. Med. Phys. 23, e13567 (2022)
S.A. Oh, J.W. Yea, M.K. Kang, J.W. Park, S.K. Kim, Analysis of the setup uncertainty and margin of the daily exactrac 6D image guide system for patients with brain tumors. PLoS ONE 11, e0151709 (2016)
S.A. Oh, J.W. Park, J.W. Yea, S.K. Kim, Evaluations of the setup discrepancy between BrainLAB 6D ExacTrac and cone-beam computed tomography used with the imaging guidance system Novalis-Tx for intracranial stereotactic radiosurgery. PLoS ONE 12, e0177798 (2017)
X. Duan, Y. Zhou, H. Dai, L. Zhao, J. Qian, D. Yang, L. Zhang, C. Luo, G. Li, Evaluating the positional uncertainty of intrafraction, adjacent fields, and daily setup with the BrainLAB ExacTrac system in patients who are receiving craniospinal irradiation. J. Appl. Clin. Med. Phys. 21, 35–46 (2020)
S.H. Ahn, A.U. Yeo, K.H. Kim, C. Kim, Y. Goh, S. Cho, S.B. Lee, Y.K. Lim, H. Kim, D. Shin, Comparative clinical evaluation of atlas and deep-learning-based auto-segmentation of organ structures in liver cancer. Radiat. Oncol. 14, 1–13 (2019)
K.H. Kim, M.-J. Sohn, S. Lee, H.-W. Koo, S.-W. Yoon, A.K. Madadi, Descriptive time series analysis for downtime prediction using the maintenance data of a medical linear accelerator. Appl. Sci. 12, 5431 (2022)
K.H. Kim, H.-W. Koo, B.-J. Lee, S.-W. Yoon, M.-J. Sohn, Cerebral hemorrhage detection and localization with medical imaging for cerebrovascular disease diagnosis and treatment using explainable deep learning. J. Korean Phys. Soc. 79, 321–327 (2021)
Chen T., Guestrin C., Xgboost: A scalable tree boosting system. In: Proceedings of the Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016; pp. 785–794.
R. Kumar, A. Indrayan, Receiver operating characteristic (ROC) curve for medical researchers. Indian Pediatr. 48, 277–287 (2011)
H.A. Al-Hallaq, L. Cerviño, A.N. Gutierrez, A. Havnen-Smith, S.A. Higgins, M. Kügele, L. Padilla, T. Pawlicki, N. Remmes, K. Smith, AAPM task group report 302: Surface-guided radiotherapy. Med. Phys. 49, e82–e112 (2022)
V. Da Silva Mendes, M. Reiner, L. Huang, D. Reitz, K. Straub, S. Corradini, M. Niyazi, C. Belka, C. Kurz, G. Landry, ExacTrac Dynamic workflow evaluation: Combined surface optical/thermal imaging and X-ray positioning. J. Appl. Clin. Med. Phys. 23, e13754 (2022)
G. Li, Commissioning and routine quality assurance of the vision RT AlignRT® system (CRC Press, In Surface Guided Radiation Therapy, 2020), pp.157–185
J. Lehmann, T.S. Standen, G. Kaur, J. Wolf, A. Wilfert, J. Simpson, Methodology of thermal drift measurements for surface guided radiation therapy systems and clinical impact assessment illustrated on the C-Rad Catalyst+ HD system. Tech Innov Patient Supp Radia Oncol 21, 58–63 (2022)
A. Rajkomar, J. Dean, I. Kohane, Machine learning in medicine. N. Engl. J. Med. 380, 1347–1358 (2019)
H.O. Alanazi, A.H. Abdullah, K.N. Qureshi, A critical review for developing accurate and dynamic predictive models using machine learning methods in medicine and health care. J. Med. Syst. 41, 1–10 (2017)
J.A. Sidey-Gibbons, C.J. Sidey-Gibbons, Machine learning in medicine: a practical introduction. BMC Med. Res. Methodol. 19, 1–18 (2019)
N. Mirchi, V. Bissonnette, R. Yilmaz, N. Ledwos, A. Winkler-Schwartz, R.F. Del Maestro, The Virtual Operative Assistant: An explainable artificial intelligence tool for simulation-based training in surgery and medicine. PLoS ONE 15, e0229596 (2020)
A.F. Markus, J.A. Kors, P.R. Rijnbeek, The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies. J. Biomed. Inform. 113, 103655 (2021)
D. Bzdok, M. Krzywinski, N. Altman, Machine learning: supervised methods. Nat. Methods 15, 5 (2018)
K.S. Choi, S.H. Choi, B. Jeong, Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network. Neuro Oncol. 21, 1197–1209 (2019)
A. Holzinger, G. Langs, H. Denk, K. Zatloukal, H. Müller, Causability and explainability of artificial intelligence in medicine. Wiley Interdisciplin Rev Data Min Knowled Discov 9, e1312 (2019)
G.S. Handelman, H.K. Kok, R.V. Chandra, A.H. Razavi, S. Huang, M. Brooks, M.J. Lee, H. Asadi, Peering into the black box of artificial intelligence: evaluation metrics of machine learning methods. Am. J. Roentgenol. 212, 38–43 (2019)
Author information
Authors and Affiliations
Contributions
KHK: performed the experiment and analyzed the data including curation and consolidation. KHK: developed the analysis software and performed the analysis including predictive modeling. HK: contributed to the interpretation of the results for the basic statistical analysis. HK: supervised the project. KHK: wrote the manuscript. HK: contributed to the interpretation of the results and contributed to the final version of the manuscript. BL: provided critical feedback and helped shape the research, analysis, and manuscript.
Corresponding author
Ethics declarations
Conflict of interests
The authors declare no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kim, K.H., Lee, BJ. & Koo, HW. Experimental verification of isocenter calibration for image-guided radiosurgery system using predictive modeling. J. Korean Phys. Soc. 82, 1222–1230 (2023). https://doi.org/10.1007/s40042-023-00779-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40042-023-00779-w