Extracting lung contour deformation features with deep learning for internal target motion tracking: a preliminary study
Open Access
- 22 September 2023
- journal article
- research article
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 68 (19) , 195009
Abstract
Objective . To propose lung contour deformation features (LCDFs) as a surrogate to estimate the thoracic internal target motion, and to report their performance by correlating with the changing body using a cascade ensemble model (CEM). LCDFs, correlated to the respiration driver, are employed without patient-specific motion data sampling and additional training before treatment. Approach . LCDFs are extracted by matching lung contours via an encoder–decoder deep learning model. CEM estimates LCDFs from the currently captured body, and then uses the estimated LCDFs to track internal target motion. The accuracy of the proposed LCDFs and CEM were evaluated using 48 targets’ motion data, and compared with other published methods. Main results . LCDFs estimated the internal targets with a localization error of 2.6 ± 1.0 mm (average ± standard deviation). CEM reached a localization error of 4.7 ± 0.9 mm and a real-time performance of 256.9 ± 6.0 ms. With no internal anatomy knowledge, they achieved a small accuracy difference (of 0.34∼1.10 mm for LCDFs and of 0.43∼1.75 mm for CEM at the 95% confidence level) with a patient-specific lung biomechanical model and the deformable image registration models. Significance . The results demonstrated the effectiveness of LCDFs and CEM on tracking target motion. LCDFs and CEM are non-invasive, and require no patient-specific training before treatment. They show potential for broad applications.Keywords
Funding Information
- National Natural Science Foundation of China (82001928)
- Zhejiang Provincial Natural Science Foundation of China (LQ20H180016)
This publication has 36 references indexed in Scilit:
- Prediction of Lung Motion From Four-Dimensional Computer Tomography (4DCT) Images Using Bayesian Registration and Trajectory ModellingIEEE Access, 2017
- Dynamic tumor tracking using the Elekta Agility MLCMedical Physics, 2014
- Guidelines for respiratory motion management in radiation therapyJournal of Radiation Research, 2012
- Toward efficient biomechanical-based deformable image registration of lungs for image-guided radiotherapyPhysics in Medicine & Biology, 2011
- Geometric accuracy of a novel gimbals based radiation therapy tumor tracking systemRadiotherapy and Oncology, 2011
- A robotic approach to 4D real-time tumor tracking for radiotherapyPhysics in Medicine & Biology, 2011
- A framework for evaluation of deformable image registration spatial accuracy using large landmark point setsPhysics in Medicine & Biology, 2009
- The management of respiratory motion in radiation oncology report of AAPM Task Group 76a)Medical Physics, 2006
- A dosimetric analysis of respiration-gated radiotherapy in patients with stage III lung cancerRadiation Oncology, 2006
- Dosimetric evaluation of lung tumor immobilization using breath hold at deep inspirationInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2001