Association of Radiomics and Metabolic Tumor Volumes in Radiation Treatment of Glioblastoma Multiforme

Abstract

Purpose To build a framework for investigation of the associations between imaging, clinical target volumes (CTVs), and metabolic tumor volumes (MTVs) features for better understanding of the underlying information in the CTVs and dependencies between these volumes. High-throughput extraction of imaging and metabolomic quantitative features from magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging of glioblastoma multiforme (GBM) results in tens of variables per patient. In radiation therapy of GBM the relevant metabolic tumor volumes (MTVs) are related to aberrant levels of N-acetyl aspartate (NAA) and choline (Cho). The corresponding clinical target volumes (CTVs) for radiation therapy are based on contrast-enhanced T1-weighted (CE-T1w) and T2-weighted (T2w)/fluid-attenuated inversion recovery MRI. Methods and Materials Necrotic portions, enhancing lesion, and edema were manually contoured on CE-T1w/T2w images for 17 GBM patients. Clinical target volumes and MTVs for NAA (MTVNAA) and Cho (MTVCho) were constructed. Imaging and metabolic features related to size, shape, and signal intensities of the volumes were extracted. Tumors were also scored categorically for 10 semantic imaging traits by a neuroradiologist. All features were investigated for redundancy. Two-way correlations between imaging and CTVs/MTVs features were visualized as heatmaps. Associations between MTVNAA and MTVCho and imaging features were studied using Spearman correlation. Results Forty-eight imaging features were extracted per patient. Half of the imaging traits were replaced with automatically extracted continuous variables. Twenty features were extracted from CTVs and MTVs. A series of semantic imaging traits were replaced with automatically extracted continuous variables. There were multiple (22) significant correlations of imaging measures with CTVs/MTVNAA, whereas there were only 6 with CTVs/MTVCho. Conclusions A framework for investigation of codependencies between MRI and magnetic resonance spectroscopic imaging radiomic features and CTVs/MTVs has been established. The MTV for NAA was found to be closely associated with MRI volumes, whereas very few imaging features were related to MTVCho, indicating that Cho provides additional information to imaging.

Radiomics Nomogram Building From Multiparametric MRI to Predict Grade in Patients With Glioma: A Cohort Study

“…CET 1 WI images are often used to determine the boundaries of gross tumors and to assess the extent of tumors as a means of assessing their invasiveness . T 2 WI sequences are sensitive to water tissue content and can be used to estimate cellular density and to detect the presence of edema . The ADC was used to describe diffusion processes that reflect various biomedical mechanisms and to estimate cellular density and the presence of edema .…”

“…37 T 2 WI sequences are sensitive to water tissue content and can be used to estimate cellular density and to detect the presence of edema. 38 The ADC was used to describe diffusion processes that reflect various biomedical mechanisms and to estimate cellular density and the presence of edema. 39 In our study, we illustrate that features extracted from the CET 1 WI sequence have a better performance than T 2 WI and ADC, which demonstrated that CET 1 WI is more useful than ADC maps in glioma grading.…”

Radiomics signature: A potential biomarker for the prediction of MGMT promoter methylation in glioblastoma

“…The images from different sequences represent different tissue characteristics within the tumor. For example, enhanced T 1 WI could show the perfusion and extravasation characteristics of the contrast agent, while T 2 MRI sequences present edema as well as cell density, to a certain extent . T 1 WI spatial habitat diversity features have previously been demonstrated to be associated with clinical characteristics of epidermal growth factor receptor .…”

“…For example, enhanced T 1 WI could show the perfusion and extravasation characteristics of the contrast agent, while T 2 MRI sequences present edema as well as cell density, to a certain extent. 39 T 1 WI spatial habitat diversity features have previously been demonstrated to be associated with clinical characteristics of epidermal growth factor receptor. 40 This may also explain why more enhanced T 1 WI features were selected than the other two sequences in the combination radiomic features.…”

Artificial intelligence in radiation oncology treatment planning: a brief overview

“…Radiomics features are a promising additional data type for oncologic outcome prediction and tumor control probability models (76). Multiple manuscripts have been published using radiomics to predict radiation response, in some cases with prediction power outperforming standard clinical variables (77)(78)(79)(80)(81)(82), though not in all (83). Radiomicsbased statistical approaches can predict various radiation normal tissue complication probabilities including radiation pneumonitis, xerostomia, and rectal wall toxicity (84)(85)(86)(87)(88)(89).…”