The relationship between radiomics and pathomics in Glioblastoma patients: Preliminary results from a cross-scale association study

Abstract

Glioblastoma multiforme (GBM) typically exhibits substantial intratumoral heterogeneity at both microscopic and radiological resolution scales. Diffusion Weighted Imaging (DWI) and dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) are two functional MRI techniques that are commonly employed in clinic for the assessment of GBM tumor characteristics. This work presents initial results aiming at determining if radiomics features extracted from preoperative ADC maps and post-contrast T1 (T1C) images are associated with pathomic features arising from H&E digitized pathology images. 48 patients from the public available CPTAC-GBM database, for which both radiology and pathology images were available, were involved in the study. 91 radiomics features were extracted from ADC maps and post-contrast T1 images using PyRadiomics. 65 pathomic features were extracted from cell detection measurements from H&E images. Moreover, 91 features were extracted from cell density maps of H&E images at four different resolutions. Radiopathomic associations were evaluated by means of Spearman’s correlation (ρ) and factor analysis. p values were adjusted for multiple correlations by using a false discovery rate adjustment. Significant cross-scale associations were identified between pathomics and ADC, both considering features (n = 186, 0.45 < ρ < 0.74 in absolute value) and factors (n = 5, 0.48 < ρ < 0.54 in absolute value). Significant but fewer ρ values were found concerning the association between pathomics and radiomics features (n = 53, 0.5 < ρ < 0.65 in absolute value) and factors (n = 2, ρ = 0.63 and ρ = 0.53 in absolute value). The results of this study suggest that cross-scale associations may exist between digital pathology and ADC and T1C imaging. This can be useful not only to improve the knowledge concerning GBM intratumoral heterogeneity, but also to strengthen the role of radiomics approach and its validation in clinical practice as “virtual biopsy”, introducing new insights for omics integration toward a personalized medicine approach.

Radiomic profiling for insular diffuse glioma stratification with distinct biologic pathway activities

“…This may be related to the fact that T1c features reflect the disruption of the blood-brain barrier by active tumors, a common triggering factor for neuronal degeneration and progression of glioma. [34][35][36] However, T2 features reflect the presence of deoxyhemoglobin associated with high local oxygen extraction in proliferating tissues. 37 Finally, the results of the radiogenomic analysis indicated that 38 Multiple integrin family members have been reported as potential predictive biomarkers for survival in glioma patients.…”

“…For instance, the formation of T1c intensities (RF5, RF6, RF8, RF9, RF10, RF11, and RF12) was regulated by the largest number of biological processes, followed by the T2 textural features (RF16, RF17, and RF18). This may be related to the fact that T1c features reflect the disruption of the blood–brain barrier by active tumors, a common triggering factor for neuronal degeneration and progression of glioma 34–36 . However, T2 features reflect the presence of deoxyhemoglobin associated with high local oxygen extraction in proliferating tissues 37 …”

“…This may be related to the fact that T1c features reflect the disruption of the blood–brain barrier by active tumors, a common triggering factor for neuronal degeneration and progression of glioma. 34 , 35 , 36 However, T2 features reflect the presence of deoxyhemoglobin associated with high local oxygen extraction in proliferating tissues. 37 …”

Artificial Intelligence-Based Opportunities in Liver Pathology—A Systematic Review

“…As such, DNNbased algorithms could provide yet another tool for patient management, in association with existing pathological (TNM classification), clinical (Performance Status) or radiology scoring systems [60,61]. Hence, multimodal approaches such as DNN-based systems compiling radiological and pathological imaging data (reflected through the concepts of "radiomics" and "pathomics", respectively) have been proposed for non-small lung cancer [62], cervical cancer [63], breast cancer [64] and glioblastoma [65] but have yet to be developed in liver pathology. Radiological imaging data are particularly suited to the development and use of deep learning artificial intelligence and share many of its concepts and limitations with the field of pathology [66].…”

Radiomics in [18F]FDG PET/CT: A leap in the dark?

“…Disease burden was already quantified based on the total MTV, but this does not take into account the spatial distributions of the lesions throughout the body, which may be captured by dissemination features like the maximum distance between the two lesions that are the furthest apart. The morphologic basis of MRI and CT radiomic features has been investigated in several tumour types using various approaches [338][339][340]. These studies were mostly hypothesis-generating, but interesting correlations between radiomic features and histopathological characteristics like hypoxia, angiogenesis and Gleason score were identified.…”