Vascularity and Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging

Affinity of PET-MRI Tracers for Hypoxic Cells in Breast Cancer: A Systematic Review

Tumour hypoxia is a known microenvironmental culprit for treatment resistance, tumour recurrence and promotion of metastatic spread. Despite the long-known existence of this factor within the tumour milieu, hypoxia is still one of the greatest challenges in cancer management. The transition from invasive and less reliable detection methods to more accurate and non-invasive ways to identify and quantify hypoxia was a long process that eventually led to the promising results showed by functional imaging techniques. Hybrid imaging, such as PET-CT, has the great advantage of combining the structural or anatomical image (offered by CT) with the functional or metabolic one (offered by PET). However, in the context of hypoxia, it is only the PET image taken after appropriate radiotracer administration that would supply hypoxia-specific information. To overcome this limitation, the development of the latest hybrid imaging systems, such as PET-MRI, enables a synergistic approach towards hypoxia imaging, with both methods having the potential to provide functional information on the tumour microenvironment. This study is designed as a systematic review of the literature on the newest developments of PET-MRI for the imaging of hypoxic cells in breast cancer. The analysis includes the affinity of various PET-MRI tracers for hypoxia in this patient group as well as the correlations between PET-specific and MRI-specific parameters, to offer a broader view on the potential for the widespread clinical implementation of this hybrid imaging technique.

Delta-Radiomics Based on Dynamic Contrast-Enhanced MRI for Predicting Lymphovascular Invasion in Invasive Breast Cancer

RATIONALE AND OBJECTIVES

Treatment strategies for invasive breast cancer require accurate lymphovascular invasion (LVI) predictions. This study aimed to investigate the effectiveness of delta radiomics based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for assessing LVI and develop a nomogram to aid treatment decisions.

MATERIALS AND METHODS

Overall, 293 patients with resectable invasive breast cancer underwent preoperative DCE-MRI. Radiomic features were extracted from pre-contrast (A0), first post-contrast (A1), and subtracted images of A0 and A1. Three radiomics models were developed using several data analyses; logistic analyses were performed to identify radiological features to predict the LVI status. A hybrid model integrating both radiological features and optimal radiomics was developed. Receiver operating characteristic analysis was employed to evaluate model performance, using the area under the curve (AUC) as a quantitative metric for discriminative ability.

RESULTS

In the test set, the Radiomics-Delta model, with 17 radiomic features, had an AUC of 0.781 and accuracy of 0.705. Radiomics-A0, with 10 features, had an AUC of 0.619 and accuracy of 0.523, while Radiomics-A1, with 8 features, had an AUC of 0.715 and accuracy of 0.591. The hybrid model exhibited better performance, with an AUC of 0.868 and accuracy of 0.875, than the radiological and Radiomics-Delta models, with an AUC of 0.759 and 0.781, respectively, and accuracy of 0.773 and 0.705, respectively.

CONCLUSION

Compared to Radiomics-A0 and Radiomics-A1, Radiomics-Delta demonstrated superior performance. Moreover, the hybrid model incorporating Radiomics-Delta and radiological features exhibited excellent performance in determining the LVI status in cases of invasive breast cancer.

Quantification of Radiomics features of Peritumoral Vasogenic Edema extracted from fluid-attenuated inversion recovery images in glioblastoma and isolated brain metastasis, using T1-dynamic contrast-enhanced Perfusion analysis

The peritumoral vasogenic edema (PVE) in brain tumors exhibits varied characteristics. Brain metastasis (BM) and meningioma barely have tumor cells in PVE, while glioblastoma (GB) show tumor cell infiltration in most subjects. The purpose of this study was to investigate the PVE of these three pathologies using radiomics features in FLAIR images, with the hypothesis that the tumor cells might influence textural variation. Ex vivo experimentation of radiomics analysis of T1-weighted images of the culture medium with and without suspended tumor cells was also attempted to infer the possible influence of increasing tumor cells on radiomics features. This retrospective study involved magnetic resonance (MR) images acquired using a 3.0-T MR machine from 83 patients with 48 GB, 21 BM, and 14 meningioma. The 93 radiomics features were extracted from each subject's PVE mask from three pathologies using T1-dynamic contrast-enhanced MR imaging. Statistically significant (< 0.05, independent samples T-test) features were considered. Features maps were also computed for qualitative investigation. The same was carried out for T1-weighted cell line images but group comparison was carried out using one-way analysis of variance. Further, a random forest (RF)-based machine learning model was designed to classify the PVE of GB and BM. Texture-based variations, especially higher nonuniformity values, were observed in the PVE of GB. No significance was observed between BM and meningioma PVE. In cell line images, the culture medium had higher nonuniformity and was considerably reduced with increasing cell densities in four features. The RF model implemented with highly significant features provided improved area under the curve results. The possible infiltrative tumor cells in the PVE of the GB are likely influencing the texture values and are higher in comparison with BM PVE and may be of value in the differentiation of solitary metastasis from GB. However, the robustness of the features needs to be investigated with a larger cohort and across different scanners in the future.