Enhancement of multimodality texture-based prediction models via optimization of PET and MR image acquisition protocols: a proof of concept. (27th October 2017)

• Record Type: Journal Article
• Authors: Vallières, Martin; Laberge, Sébastien; Diamant, André; El Naqa, Issam
• Is Part Of: Physics in medicine & biology. Volume 62:Number 22(2017:Nov.)
• Page Start: 8536
• Page End: 8565
• Publication Date: 2017-10-27
• Subjects: tumour outcome prediction -- radiomics -- textures -- PET simulations -- MRI simulations; Biophysics -- Periodicals; Medical physics -- Periodicals; 610.153
• DOI: 10.1088/1361-6560/aa8a49
• Languages: English
• ISSNs: 0031-9155

Abstract

Abstract: 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 1 -weighted and T 2 -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 0.84 ± 0.01 in bootstrap testing experiments. In comparison, the model performance significantly increased using an optimal set of image acquisition parameters ( p = 0.04 ), with an average AUC of 0.89 ± 0.01 . 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.