Olivia Prior

Purpose: We aim to inform the design of new diffusion MRI (dMRI) approaches for microvasculature quantification that enhance the biological specificity of imaging towards cancer. Methods: We adopted simulation‐informed modelling of the vascular dMRI signal. We synthesised signals from 1500 synthetic vascular networks, for a variety of protocols (flow‐compensated [FC], non‐compensated [NC], hybrid), featuring different samplings and diffusion times. We estimated the number of independent, recoverable signal degrees of freedom in presence of noise (signal‐to‐noise ratio of 5), and ranked 12 microvascular metrics depending on the quality of their estimation. Lastly, we demonstrated the feasibility of estimating the top‐ranking metrics on 3T dMRI of a healthy volunteer and of a metastatic colorectal cancer (CRC) patient. Results: Both NC and FC synthetic vascular signals exhibited complex behaviour as, for example, non‐zero kurtosis and diffusion time dependence. Two independent degrees of freedom appeared recoverable from directionally‐averaged vascular signals (SNR of 5). Mean volumetric flow rate and an Apparent Network Branching (ANB) index maximised correlations between ground truth and estimated values in silico. In the patient, both and detected re‐vascularisation after 3 months of targeted therapy against liver metastases, consistently with Intra‐Voxel Incoherent Motion (IVIM) metrics. Conclusions: Simulation‐based modelling of the vascular dMRI signal suggests and as the most promising metrics for tissue microvasculature characterisation. Their estimation in vivo appears feasible to capture general trends, and demonstrates contrasts that are biologically plausible, encouraging their usage in future studies.

Purpose: We aim to inform the design of new diffusion MRI (dMRI) approaches for microvasculature mapping that enhance the biological specificity of imaging towards cancer. Methods: We adopted simulation-informed modelling of the vascular dMRI signal. We synthesised signals from 1500 synthetic vascular networks, for a variety of protocols (flow-compensated (FC), non-compensated (NC), hybrid), featuring different b samplings and diffusion times. We estimated the number of independent, recoverable signal degrees of freedom in presence of noise (signal-to-noise ratio of 5), and ranked 12 microvascular metrics depending on the quality of their estimation. Lastly, we demonstrated the feasibility of estimating the top-ranking metrics on 3T dMRI of a healthy volunteer and of a metastatic colorectal cancer (CRC) patient. Results: Both NC and FC synthetic vascular signals exhibit complex behaviour, e.g., non-zero kurtosis and diffusion time dependence. Two independent degrees of freedom appear recoverable from directionally-averaged vascular signals (SNR of 5). Mean volumetric flow rate q _m and an Apparent Network Branching (ANB) index maximise correlations between ground truth and estimated values in silico . Their estimation is proposed for in vivo imaging, and demonstrated herein. In the patient, both q _m and ANB detect re-vascularisation after 3 months of targeted therapy against liver metastases, consistently with Intra-Voxel Incoherent Motion (IVIM) metrics. Conclusions: Simulation-based modelling of the vas-cular dMRI signal informs the design of promising approaches for in vivo microvasculature characterisation.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To identify precise 3D radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 318 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). 3D radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius (R) and bin size (B). The lower 95% confidence limit (LCL) of the intraclass correlation coefficient was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL ≥ 0.50). Habitats were obtained with Gaussian Mixture Models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI (mpMRI) and tumor biopsies. Results 3D radiomics showed poor repeatability (median LCL[IQR] of 0.442 [0.312-0.516]) and poor reproducibility against R (0.44[0.33-0.526]) but excellent reproducibility against B (0.929[0.853-0.988]). Twentysix radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC, 0.601 (0.494-0.712) and 0.651 (0.52-0.784) for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC, 0.532 (0.424-0.637) and 0.587 (0.465-0.703), respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively, with heterogeneity observed in mpMRI habitats and histology. Conclusion Precise 3D radiomics features were identified on CT that enabled tumor heterogeneity assessment through stable tumor habitat computation. ©RSNA, 2024.

The search for understanding immunotherapy response has sparked interest in diverse areas of oncology, with artificial intelligence (AI) and radiomics emerging as promising tools, capable of gathering large amounts of information to identify suitable patients for treatment. The application of AI in radiology has grown, driven by the hypothesis that radiology images capture tumor phenotypes and thus could provide valuable insights into immunotherapy response likelihood. However, despite the rapid growth of studies, no algorithms in the field have reached clinical implementation, mainly due to the lack of standardized methods, hampering study comparisons and reproducibility across different datasets. In this review, we performed a comprehensive assessment of published data to identify sources of variability in radiomics study design that hinder the comparison of the different model performance and, therefore, clinical implementation. Subsequently, we conducted a use-case meta-analysis using homogenous studies to assess the overall performance of radiomics in estimating programmed death-ligand 1 (PD-L1) expression. Our findings indicate that, despite numerous attempts to predict immunotherapy response, only a limited number of studies share comparable methodologies and report sufficient data about cohorts and methods to be suitable for meta-analysis. Nevertheless, although only a few studies meet these criteria, their promising results underscore the importance of ongoing standardization and benchmarking efforts. This review highlights the importance of uniformity in study design and reporting. Such standardization is crucial to enable meaningful comparisons and demonstrate the validity of biomarkers across diverse populations, facilitating their implementation into the immunotherapy patient selection process.