Pseudo-CT generation by conditional inference random forest for MRI-based radiotherapy treatment planning
| Autor: | N. Perichon, A. Largent, Renaud de Crevoisier, Jason Dowling, Caroline Lafond, Jean-Claude Nunes, Antoine Simon, Chloe Herve, Oscar Acosta, A. Barateau, Hervé Saint-Jalmes, Peter B. Greer |
|---|---|
| Přispěvatelé: | Laboratoire Traitement du Signal et de l'Image (LTSI), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de la Santé et de la Recherche Médicale (INSERM), CRLCC Eugène Marquis (CRLCC), University of Newcastle [Australia] (UoN), Commonwealth Scientific and Industrial Research Organisation [Canberra] (CSIRO), Université de Rennes (UR)-Institut National de la Santé et de la Recherche Médicale (INSERM), University of Newcastle [Callaghan, Australia] (UoN) |
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Random Forest
medicine.diagnostic_test Radiotherapy business.industry Inference Magnetic resonance imaging Magnetic Resonance Imaging 030218 nuclear medicine & medical imaging Random forest 03 medical and health sciences 0302 clinical medicine 030220 oncology & carcinogenesis Histogram medicine Computer vision Pseudo-CT [SDV.IB]Life Sciences [q-bio]/Bioengineering Affine transformation Artificial intelligence business Radiation treatment planning Spatial analysis Treatment planning Mathematics Volume (compression) |
| Zdroj: | 25th European Signal Processing Conference, EUSIPCO 2017 25th European Signal Processing Conference, EUSIPCO 2017, Aug 2017, Kos, Greece. pp.46-50, ⟨10.23919/EUSIPCO.2017.8081166⟩ EUSIPCO |
| DOI: | 10.23919/EUSIPCO.2017.8081166⟩ |
| Popis: | International audience; Dose calculation from MRI is a topical issue. New treatment systems combining a linear accelerator with a MRI have been recently being developed. MRI has good soft tissue contrast without ionizing radiation exposure. However, unlike CT, MRI does not provide electron density information necessary for dose calculation. We propose in this paper a machine learning method to simulate a CT from a target MRI and co-registered CT-MRI training set. Ten prostate MR and CT images have been considered. Firstly, a reference image was randomly selected in the training set. A common space has been built thanks to affine registrations between the training set and the reference image. Multiscale image descriptors such as spatial information, gradients and texture features were extracted from MRI patches at different levels of a Gaussian pyramid and used as voxel-wise characteristics in the learning scheme. A Conditional Inference Random Forest (CIRF) modelled the relation between MRI descriptors and CT patches. For validation, test images were spatially normalized and the same descriptors were computed to generate a new pCT. Leave-one out experiments were performed. We obtained a MAE = 45.79 (pCT vs CT). Dose volume histograms inside PTV and organs at risk are in close agreement. The D98% was 0.45 % (inside PTV) and the 3D gamma pass rate (1mm, 1%) was 99,2%. Our method has better results than direct bulk assignment. And the results suggest that the method may be used for dose calculations in an MR based planning system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|