Back to Search
Start Over
Conditional random fields for phase-based lung feature tracking with ultra-low-dose x-rays.
- Source :
-
Medical physics [Med Phys] 2019 May; Vol. 46 (5), pp. 2337-2346. Date of Electronic Publication: 2019 Mar 12. - Publication Year :
- 2019
-
Abstract
- Purpose: During radiation therapy, a continuous internal tumor monitoring without additional imaging dose is desirable. In this study, a sequential feature-based position estimation with ultra-low-dose (ULD) kV x rays using linear-chain conditional random fields (CRFs) is performed.<br />Methods: Four-dimensional computed tomography (4D-CTs) of eight patients serve as a-priori information from which ULD projections are simulated using a Monte Carlo method. CRFs are trained with Local Energy-based Shape Histogram features extracted from the ULD images to estimate one out of ten breathing phases from the 4D-CT associated with the tumor position.<br />Results: Compared to a mean accuracy for ±1 breathing phase of 0.867 using a support vector machine (SVM), a mean accuracy of 0.958 results for the CRF with ten incident photons per pixel. This corresponds to a position estimation with a discretization error of 2.4-5.3 mm assuming a linear displacement relation between the breathing phases and a systematic error of 2.0-4.4 mm due to motion underestimation of the 4D-CT.<br />Conclusions: The tumor position estimation is comparable to state-of-the-art methods despite its low imaging dose. Training CRFs further allows a prediction of the following phase and offers a precise post-treatment evaluation tool when decoding the full image sequence.<br /> (© 2019 American Association of Physicists in Medicine.)
Details
- Language :
- English
- ISSN :
- 2473-4209
- Volume :
- 46
- Issue :
- 5
- Database :
- MEDLINE
- Journal :
- Medical physics
- Publication Type :
- Academic Journal
- Accession number :
- 30779358
- Full Text :
- https://doi.org/10.1002/mp.13447