RESUMEN
OBJECTIVES: To evaluate radiomics features' reproducibility using inter-package/inter-observer measurement analysis in renal masses (RMs) based on MRI and to employ machine learning (ML) models for RM characterization. METHODS: 32 Patients (23M/9F; age 61.8 ± 10.6 years) with RMs (25 renal cell carcinomas (RCC)/7 benign masses; mean size, 3.43 ± 1.73 cm) undergoing resection were prospectively recruited. All patients underwent 1.5 T MRI with T2-weighted (T2-WI), diffusion-weighted (DWI)/apparent diffusion coefficient (ADC), and pre-/post-contrast-enhanced T1-weighted imaging (T1-WI). RMs were manually segmented using volume of interest (VOI) on T2-WI, DWI/ADC, and T1-WI pre-/post-contrast imaging (1-min, 3-min post-injection) by two independent observers using two radiomics software packages for inter-package and inter-observer assessments of shape/histogram/texture features common to both packages (104 features; n = 26 patients). Intra-class correlation coefficients (ICCs) were calculated to assess inter-observer and inter-package reproducibility of radiomics measurements [good (ICC ≥ 0.8)/moderate (ICC = 0.5-0.8)/poor (ICC < 0.5)]. ML models were employed using reproducible features (between observers and packages, ICC > 0.8) to distinguish RCC from benign RM. RESULTS: Inter-package comparisons demonstrated that radiomics features from T1-WI-post-contrast had the highest proportion of good/moderate ICCs (54.8-58.6% for T1-WI-1 min), while most features extracted from T2-WI, T1-WI-pre-contrast, and ADC exhibited poor ICCs. Inter-observer comparisons found that radiomics measurements from T1-WI pre/post-contrast and T2-WI had the greatest proportion of features with good/moderate ICCs (95.3-99.1% T1-WI-post-contrast 1-min), while ADC measurements yielded mostly poor ICCs. ML models generated an AUC of 0.71 [95% confidence interval = 0.67-0.75] for diagnosis of RCC vs. benign RM. CONCLUSION: Radiomics features extracted from T1-WI-post-contrast demonstrated greater inter-package and inter-observer reproducibility compared to ADC, with fair accuracy for distinguishing RCC from benign RM. CLINICAL RELEVANCE: Knowledge of reproducibility of MRI radiomics features obtained on renal masses will aid in future study design and may enhance the diagnostic utility of radiomics models for renal mass characterization.
RESUMEN
(1) Background: Colorectal cancer is the third most common type of cancer with a high mortality rate and poor prognosis. The accurate prediction of key genetic mutations, such as the KRAS status, tumor staging, and extramural venous invasion (EMVI), is crucial for guiding personalized treatment decisions and improving patients' outcomes. MRI radiomics was assessed to predict the KRAS status and tumor staging in colorectal cancer patients across different imaging platforms to improve the personalized treatment decisions and outcomes. (2) Methods: Sixty colorectal cancer patients (35M/25F; avg. age 56.3 ± 12.9 years) were treated at an oncology unit. The MRI scans included T2-weighted (T2W) and diffusion-weighted imaging (DWI) or the apparent diffusion coefficient (ADC). The manual segmentation of colorectal cancer was conducted on the T2W and DWI/ADC images. The cohort was split into training and validation sets, and machine learning was used to build predictive models. (3) Results: The neural network (NN) model achieved 73% accuracy and an AUC of 0.71 during training for predicting the KRAS mutation status, while during testing, it achieved 62.5% accuracy and an AUC of 0.68. In the case of tumor grading, the support vector machine (SVM) model excelled with a training accuracy of 72.93% and an AUC of 0.7, and during testing, it reached an accuracy of 72% and an AUC of 0.69. (4) Conclusions: ML models using radiomics from ADC maps and T2-weighted images are effective for distinguishing KRAS genes, tumor grading, and EMVI in colorectal cancer. Standardized protocols are essential to improve MRI radiomics' reliability in clinical practice.
RESUMEN
Solid renal masses (SRMs) are increasingly detected and encompass both benign and malignant masses, with renal cell carcinoma (RCC) being the most common malignant SRM. Most patients with SRMs will undergo management without a priori pathologic confirmation. There is an unmet need to noninvasively diagnose and characterize RCCs, as significant variability in clinical behavior is observed and a wide range of differing management options exist. Cross-sectional imaging modalities, including magnetic resonance imaging (MRI), are increasingly used for SRM characterization. Multiparametric (mp) MRI techniques can provide insight into tumor biology by probing different physiologic/pathophysiologic processes noninvasively. These include sequences that probe tissue microstructure, including intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) and T1 relaxometry; oxygen metabolism (blood oxygen level dependent [BOLD-MRI]); as well as vascular flow and perfusion (dynamic contrast-enhanced MRI [DCE-MRI] and arterial spin labeling [ASL]). In this review, we will discuss each mpMRI method in terms of its principles, roles, and discuss the results of human studies for SRM assessment. Future validation of these methods may help to enable a personalized management approach for patients with SRM in the emerging era of precision medicine. EVIDENCE LEVEL: 5. TECHNICAL EFFICACY: 2.
Asunto(s)
Carcinoma de Células Renales , Neoplasias Renales , Imágenes de Resonancia Magnética Multiparamétrica , Humanos , Medios de Contraste , Imagen por Resonancia Magnética/métodos , Imagen de Difusión por Resonancia Magnética/métodos , Carcinoma de Células Renales/diagnóstico por imagen , Neoplasias Renales/diagnóstico por imagen , Movimiento (Física)RESUMEN
Phase-contrast magnetic resonance velocimetry (PC-MRI) has been widely used to investigate flow properties in numerous systems. In a horizontal cylindrical pipe (3 mm diameter), we investigated the accuracy of PC-MRI as the flow transitioned from laminar to turbulent flow (Reynolds number 352-2708). We focus primarily on velocimetry errors introduced by skewed intra-voxel displacement distributions, a consequence of PC-MRI theory assuming symmetric distributions. We demonstrated how rapid fluctuations in the velocity field, can produce broad asymmetric intravoxel displacement distributions near the wall. Depending on the shape of the distribution, this resulted in PC-MRI measurements under-estimating (positive skewness) or over-estimating (negative skewness) the true mean intravoxel velocity, which could have particular importance to clinical wall shear stress measurements. The magnitude of these velocity errors was shown to increase with the variance and decrease with the kurtosis of the intravoxel displacement distribution. These experimental results confirm our previous theoretical analysis, which gives a relationship for PC-MRI velocimetry errors, as a function of the higher moments of the intravoxel displacement distribution (skewness, variance, and kurtosis) and the experimental parameters q and Δ. This suggests that PC-MRI errors in such unsteady/turbulent flow conditions can potentially be reduced by employing lower q values or shorter observation times Δ.
RESUMEN
Phase contrast velocimetry (PCV) has been widely used to investigate flow properties in numerous systems. Several authors have reported errors in velocity measurements and have speculated on the sources, which have ranged from eddy current effects to acceleration artefacts. An often overlooked assumption in the theory of PCV, which may not be met in complex or unsteady flows, is that the intravoxel displacement distributions (propagators) are symmetric. Here, the effect of the higher moments of the displacement distribution (variance, skewness and kurtosis) on the accuracy of PCV is investigated experimentally and theoretically. Phase and propagator measurements are performed on tailored intravoxel distributions, achieved using a simple phantom combined with a single large voxel. Asymmetric distributions (Skewnessâ¯≠â¯0) are shown to generate important phase measurement errors that lead to significant velocimetry errors. Simulations of the phase of the spin vector sum, based on experimentally measured propagators, are shown to quantitatively reproduce the relationship between measured phase and experimental parameters. These allow relating the observed velocimetry errors to a discrepancy between the average phase of intravoxel spins considered in PCV theory and the vector phase actually measured by a PFG experiment. A theoretical expression is derived for PCV velocimetry errors as a function of the moments of the displacement distribution. Positively skewed distributions result in an underestimation of the true mean velocity, while negatively skewed distributions result in an overestimation. The magnitude of these errors is shown to increase with the variance and decrease with the kurtosis of the intravoxel displacement distribution.