skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: MO-G-BRF-02: Enhancement of Texture-Based Metastasis Prediction Models Via the Optimization of PET/MRI Acquisition Protocols

Abstract

Purpose: We have previously identified a prediction model of lung metastases at diagnosis of soft-tissue sarcomas (STS) that is composed of two textural features extracted from FDG-PET and T1-weighted (T1w) MRI scans. The goal of this study is to evaluate whether the optimization in FDGPET and MRI acquisition parameters would enhance the prediction performance of texture-based models. Methods: Ten FDG-PET and T1w- MRI digitized tumor models were generated from imaging data of STS patients who underwent pre-treatment clinical scans between 2005 and 2011. Five of ten patients eventually developed lung metastases. Numerically simulated MR images were produced using echo times (TE) of 2 and 4 times the nominal clinical parameter (TEc), and repetition times (TR) of 0.5, 0.67, 1.5 and 2 times the nominal clinical parameter (TRc) found in the DICOM headers (TEc range: 9–13 ms, TRc range: 410-667 ms). PET 2D images were simulated using Monte-Carlo and were reconstructed using an ordered-subsets expectation maximization (OSEM) algorithm with 1 to 32 iterations and a post-reconstruction Gaussian filter of 0, 2, 4 or 6 mm width. For all possible combinations of PET and MRI acquisition parameters, the prediction model was constructed using logistic regression with new coefficients, and its associated predictionmore » performance for lung metastases was evaluated using the area under the ROC curve (AUC). Results: The prediction performance over all simulations yielded AUCs ranging from 0.7 to 1. Notably, TR values below or equal to TRc and higher PET post-reconstruction filter widths yielded higher prediction performance. The best results were obtained with a combination of 4*TEc, TRc, 30 OSEM iterations and 2mm filter width. Conclusion: This work indicates that texture-based metastasis prediction models could be improved using optimized choices of FDG-PET and MRI acquisition protocols. This principle could be generalized to other texture-based models.« less

Authors:
; ; ;  [1]
  1. McGill University, Montreal, QC (Canada)
Publication Date:
OSTI Identifier:
22409614
Resource Type:
Journal Article
Journal Name:
Medical Physics
Additional Journal Information:
Journal Volume: 41; Journal Issue: 6; Other Information: (c) 2014 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA); Journal ID: ISSN 0094-2405
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; ALGORITHMS; DIAGNOSIS; FORECASTING; LUNGS; METASTASES; MONTE CARLO METHOD; NMR IMAGING; OPTIMIZATION; PATIENTS; POSITRON COMPUTED TOMOGRAPHY; SARCOMAS; TEXTURE

Citation Formats

Vallieres, M, Laberge, S, Levesque I, R, and El Naqa, I. MO-G-BRF-02: Enhancement of Texture-Based Metastasis Prediction Models Via the Optimization of PET/MRI Acquisition Protocols. United States: N. p., 2014. Web. doi:10.1118/1.4889195.
Vallieres, M, Laberge, S, Levesque I, R, & El Naqa, I. MO-G-BRF-02: Enhancement of Texture-Based Metastasis Prediction Models Via the Optimization of PET/MRI Acquisition Protocols. United States. https://doi.org/10.1118/1.4889195
Vallieres, M, Laberge, S, Levesque I, R, and El Naqa, I. 2014. "MO-G-BRF-02: Enhancement of Texture-Based Metastasis Prediction Models Via the Optimization of PET/MRI Acquisition Protocols". United States. https://doi.org/10.1118/1.4889195.
@article{osti_22409614,
title = {MO-G-BRF-02: Enhancement of Texture-Based Metastasis Prediction Models Via the Optimization of PET/MRI Acquisition Protocols},
author = {Vallieres, M and Laberge, S and Levesque I, R and El Naqa, I},
abstractNote = {Purpose: We have previously identified a prediction model of lung metastases at diagnosis of soft-tissue sarcomas (STS) that is composed of two textural features extracted from FDG-PET and T1-weighted (T1w) MRI scans. The goal of this study is to evaluate whether the optimization in FDGPET and MRI acquisition parameters would enhance the prediction performance of texture-based models. Methods: Ten FDG-PET and T1w- MRI digitized tumor models were generated from imaging data of STS patients who underwent pre-treatment clinical scans between 2005 and 2011. Five of ten patients eventually developed lung metastases. Numerically simulated MR images were produced using echo times (TE) of 2 and 4 times the nominal clinical parameter (TEc), and repetition times (TR) of 0.5, 0.67, 1.5 and 2 times the nominal clinical parameter (TRc) found in the DICOM headers (TEc range: 9–13 ms, TRc range: 410-667 ms). PET 2D images were simulated using Monte-Carlo and were reconstructed using an ordered-subsets expectation maximization (OSEM) algorithm with 1 to 32 iterations and a post-reconstruction Gaussian filter of 0, 2, 4 or 6 mm width. For all possible combinations of PET and MRI acquisition parameters, the prediction model was constructed using logistic regression with new coefficients, and its associated prediction performance for lung metastases was evaluated using the area under the ROC curve (AUC). Results: The prediction performance over all simulations yielded AUCs ranging from 0.7 to 1. Notably, TR values below or equal to TRc and higher PET post-reconstruction filter widths yielded higher prediction performance. The best results were obtained with a combination of 4*TEc, TRc, 30 OSEM iterations and 2mm filter width. Conclusion: This work indicates that texture-based metastasis prediction models could be improved using optimized choices of FDG-PET and MRI acquisition protocols. This principle could be generalized to other texture-based models.},
doi = {10.1118/1.4889195},
url = {https://www.osti.gov/biblio/22409614}, journal = {Medical Physics},
issn = {0094-2405},
number = 6,
volume = 41,
place = {United States},
year = {Sun Jun 15 00:00:00 EDT 2014},
month = {Sun Jun 15 00:00:00 EDT 2014}
}