Dynamic Contrast-enhanced MRI Quantification of Altered Vascular Permeability in Autoimmune Encephalitis.

Background Blood-brain barrier (BBB) permeability change is a possible pathologic mechanism of autoimmune encephalitis. Purpose To evaluate the change in BBB permeability in patients with autoimmune encephalitis as compared with healthy controls by using dynamic contrast-enhanced (DCE) MRI and to explore its predictive value for treatment response in patients. Materials and Methods This single-center retrospective study included consecutive patients with probable or possible autoimmune encephalitis and healthy controls who underwent DCE MRI between April 2020 and May 2021. Automatic volumetric segmentation was performed on three-dimensional T1-weighted images, and volume transfer constant (Ktrans) values were calculated at encephalitis-associated brain regions. Ktrans values were compared between the patients and controls, with adjustment for age and sex with use of a nonparametric approach. The Wilcoxon rank sum test was performed to compare Ktrans values of the good (improvement in modified Rankin Scale [mRS] score of at least two points or achievement of an mRS score of ≤2) and poor (improvement in mRS score of less than two points and achievement of an mRS score >2) treatment response groups among the patients. Results Thirty-eight patients with autoimmune encephalitis (median age, 38 years [IQR, 29-59 years]; 20 [53%] female) and 17 controls (median age, 71 years [IQR, 63-77 years]; 12 [71%] female) were included. All brain regions showed higher Ktrans values in patients as compared with controls (P < .001). The median difference in Ktrans between the patients and controls was largest in the right parahippocampal gyrus (25.1 × 10-4 min-1 [95% CI: 17.6, 43.4]). Among patients, the poor treatment response group had higher baseline Ktrans values in both cerebellar cortices (P = .03), the left cerebellar cortex (P = .02), right cerebellar cortex (P = .045), left cerebral cortex (P = .045), and left postcentral gyrus (P = .03) than the good treatment response group. Conclusion DCE MRI demonstrated that BBB permeability was increased in all brain regions in patients with autoimmune encephalitis as compared with controls, and baseline Ktrans values were higher in patients with poor treatment response in the cerebellar cortex, left cerebral cortex, and left postcentral gyrus as compared with the good response group. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Filippi and Rocca in this issue.

Deep Learning-based Image Enhancement Techniques for Fast MRI in Neuroimaging.

Despite its superior soft tissue contrast and non-invasive nature, MRI requires long scan times due to its intrinsic signal acquisition principles, a main drawback which technological advancements in MRI have been focused on. In particular, scan time reduction is a natural requirement in neuroimaging due to detailed structures requiring high resolution imaging and often volumetric (3D) acquisitions, and numerous studies have recently attempted to harness deep learning (DL) technology in enabling scan time reduction and image quality improvement. Various DL-based image reconstruction products allow for additional scan time reduction on top of existing accelerated acquisition methods without compromising the image quality.

Added value of dynamic contrast-enhanced MR imaging in deep learning-based prediction of local recurrence in grade 4 adult-type diffuse gliomas patients.

Local recurrences in patients with grade 4 adult-type diffuse gliomas mostly occur within residual non-enhancing T2 hyperintensity areas after surgical resection. Unfortunately, it is challenging to distinguish non-enhancing tumors from edema in the non-enhancing T2 hyperintensity areas using conventional MRI alone. Quantitative DCE MRI parameters such as Ktrans and Ve convey permeability information of glioblastomas that cannot be provided by conventional MRI. We used the publicly available nnU-Net to train a deep learning model that incorporated both conventional and DCE MRI to detect the subtle difference in vessel leakiness due to neoangiogenesis between the non-recurrence area and the local recurrence area, which contains a higher proportion of high-grade glioma cells. We found that the addition of Ve doubled the sensitivity while nonsignificantly decreasing the specificity for prediction of local recurrence in glioblastomas, which implies that the combined model may result in fewer missed cases of local recurrence. The deep learning model predictive of local recurrence may enable risk-adapted radiotherapy planning in patients with grade 4 adult-type diffuse gliomas.