Texture-based radiomic models constructed from medical images have the potential to support cancer treatment management via personalized assessment of tumour aggressiveness. While the identification of stable texture features under varying imaging settings is crucial for the translation of radiomics analysis into routine clinical practice, we hypothesize in this work that a complementary optimization of image acquisition parameters prior to texture feature extraction could enhance the predictive performance of texture-based radiomic models. As a proof of concept, we evaluated the possibility of enhancing a model constructed for the early prediction of lung metastases in soft-tissue sarcomas by optimizing PET and MR image acquisition protocols via computerized simulations of image acquisitions with varying parameters. Simulated PET images from 30 STS patients were acquired by varying the extent of axial data combined per slice ('span'). Simulated T -weighted and T-weighted MR images were acquired by varying the repetition time and echo time in a spin-echo pulse sequence, respectively. We analyzed the impact of the variations of PET and MR image acquisition parameters on individual textures, and we investigated how these variations could enhance the global response and the predictive properties of a texture-based model. Our results suggest that it is feasible to identify an optimal set of image acquisition parameters to improve prediction performance. The model constructed with textures extracted from simulated images acquired with a standard clinical set of acquisition parameters reached an average AUC of [Formula: see text] in bootstrap testing experiments. In comparison, the model performance significantly increased using an optimal set of image acquisition parameters ([Formula: see text]), with an average AUC of [Formula: see text]. Ultimately, specific acquisition protocols optimized to generate superior radiomics measurements for a given clinical problem could be developed and standardized via dedicated computer simulations and thereafter validated using clinical scanners.
Purpose: We hypothesize that MRI texture‐based tumor outcome prediction models could be optimized via numerical simulations of image acquisitions. These simulations require knowledge of T1 and T2 relaxation times as inputs. The goal of this study is to evaluate the feasibility of using machine learning techniques to infer T1 and T2 tumor maps with accurate texture preservation for simulation inputs from clinical sequences. Methods: Clinical T1‐weighted (T1w) and T2‐weighted fat‐saturated (T2FS) scans, and measured T1 and T2 maps from eight patients with soft‐tissue sarcomas were used in this study. Measured T1 and T2 maps were computed using pulse sequences with variable flip angles and echo times, respectively. General regression neural networks (GRNNs) were trained on these data to infer T1 and T2 relaxation times from T1w and T2FS images. Four texture features were extracted to evaluate texture preservation: GLCM/Entropy, GLRLM/Gray‐Level Variance (GLV), GLSZM/Zone Size Variance (ZSV) and NGTDM/Complexity. The GRNN ability to estimate T1 and T2 relaxation times was assessed using leave‐one‐out cross‐validation. Results: The average T1 and T2 relaxation times within the tumor region of all patients were (1515 ± 542) ms and (226 ± 151) ms in the measured cases, and (1546 ± 546) ms and (249 ± 145) ms in the estimated cases, respectively. The average root‐mean‐square errors between measured and estimated relaxation times were 573 ms for T1 and 160 ms for T2. The average absolute percentage differences between measured and estimated GLCM/Entropy, GLRLM/GLV, GLSZM/ZSV and NGTDM/Complexity features were 5.1%, 0.02%, 0.0% and 16.2% for T1 maps, and 7.7%, 0.04%, 0.0% and 10.9% for T2 maps, respectively. Conclusion: From a texture preservation perspective, this work demonstrates the feasibility to create MRI numerical models using GRNNs from T1w and T2FS clinical scans. Further work is required to obtain higher accuracy for T1 and T2 absolute relaxation times. This work was supported by the Natural Sciences and Engineering Research Council (NSERC) of Canada under the scholarship CGSD3‐426742‐2012, as well as it was supported by the Canadian Institutes of Health Research (CIHR) under grant MOP‐136774.
Purpose: To develop a convenient simulation platform to facilitate PET/MR image analysis with the prospect of gaining a better understanding of the influence of acquisition parameters on PET/MRI textural features. The simulation platform is demonstrated by showing textural variations of a representative case study using different image acquisition parameters. Methods: The simulation platform is composed of MRI simulators JEMRIS and SIMRI to achieve simulations of customized MRI sequences on sample tumor models. The PET simulator GATE is used to get 2D and 3D Monte Carlo acquisitions of voxelized PET sources using a phantom geometry and a customized scanner architecture. The platform incorporates a series of graphical user interfaces written in Matlab. Two GUIs are used to facilitate communication with the simulation executables installed on a computer cluster. A third GUI is used to collect and display the clinical and simulated images, as well as fused PET/MRI images, and perform computation of textural features. To illustrate the capabilities of this platform, one FDG‐PET and T1‐weighted (T1w) digitized tumor models were generated from clinical images of a soft‐tissue sarcoma patient. Numerically simulated MR images were produced using 3 different echo times (TE) and 5 different repetition times (TR). PET 2D images were simulated using an OSEM algorithm with 1 to 32 iterations and a post‐reconstruction Gaussian filter of 0, 2, 4 or 6 mm width. Results: STAMP was successfully used to produce numerically simulated FDG‐PET and MRI images, and to calculate their corresponding textures. Three typical textures (GLCM‐Contrast, GLSZM‐ZSV and NGTDM‐Coarseness) were found to vary by a range of 45% on average compared to reference scanning conditions in the case of FDG‐PET, and by a range of 40% in the case of T1w MRI. Conclusion: We have successfully developed a Matlab‐based simulation platform to facilitate PET/MRI texture image analysis for outcome prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.