Radiomics-based aortic flow profile characterization with 4D phase-contrast MRI

Abstract

4D PC MRI of the aorta has become a routinely available examination, and a multitude of single parameters have been suggested for the quantitative assessment of relevant flow features for clinical studies and diagnosis. However, clinically applicable assessment of complex flow patterns is still challenging. We present a concept for applying radiomics for the quantitative characterization of flow patterns in the aorta. To this end, we derive cross-sectional scalar parameter maps related to parameters suggested in literature such as throughflow, flow direction, vorticity, and normalized helicity. Derived radiomics features are selected with regard to their inter-scanner and inter-observer reproducibility, as well as their performance in the differentiation of sex-, age- and disease-related flow properties. The reproducible features were tested on user-selected examples with respect to their suitability for characterizing flow profile types. In future work, such signatures could be applied for quantitative flow assessment in clinical studies or disease phenotyping.

Perfect Match: Radiomics and Artificial Intelligence in Cardiac Imaging

“…36 In addition, recent approaches combined radiomic feature extraction with classification algorithms for the detection and understanding of clinical phenotypes, leveraging the explainability of the approach for hypothesis generation and quantitative characterization of cardiovascular pathologies. 37,38 The development of such explainable radiomics/AI solutions in cardiac imaging is a field of ongoing research. Salih et al 39 cardiac imaging.…”

“…27 Some authors could demonstrate that through adapted preprocessing, comparability of higher-order radiomics features could be achieved. 38,72,73 Recently, the AutoRadiomics platform has been introduced 30 as an intuitive open-source framework enabling reproducible radiomics research via an interactive graphical user interface. Nevertheless, is has been shown that even with standardized image-processing methods, only limited success was evident regarding robustness and reproducibility.…”

Inter and intra‐operator reliability of Lekholm and Zarb classification and proposal of a novel radiomic data‐driven clustering for qualitative assessment of edentulous alveolar ridges

“…By analyzing features from medical images, radiomics may create accurate prediction models to support clinical decision-making (Felfli et al, 2023;O'Donnell et al, 2022). The potential applications of radiomics are broad and span various medical fields, including oncology, neurology, and cardiology (Cassinelli Petersen et al, 2022;Huellebrand et al, 2023;Lambin et al, 2017;Santos et al, 2023).…”