MY CONTENT

Between May 2008 and July 2017, endovascular treatment of 1184 aneurysms in 827 patients was performed in a single institution. Twenty-four percent of these aneurysms were located at the MCA, and 150 unruptured MCA bifurcation aneurysms treated with coiling, stent-assistedcoiling, or endovascular flow diverter (WEB device) were identified for this retrospective data analysis. The procedure-associated good clinical outcome was 89.9%, and the mortality rate was 2.7%. Short-term follow-up good clinical outcome/mortality rates were 91.3%/0.7%. At discharge, 137 patients had an mRS of 0–2 (91.3%) and 13 had an mRS of 3–6 (8.7%). The authors conclude that regardless of the architecture of MCA bifurcation aneurysms, endovascular treatment can be performed with low morbidity/mortality rates.

The authors sought to investigate whether co-occurrence of local anisotropic gradient orientations (COLLAGE) measurements from posttreatment gadolinium-contrast T1WI could distinguish varying extents of cerebral radiation necrosis and recurrent tumor classes in a lesion across primary and metastatic brain tumors. On 75 gadolinium-contrast T1WI studies obtained from patients with primary and metastatic brain tumors and nasopharyngeal carcinoma, the extent of cerebral radiation necrosis and recurrent tumor in every brain lesion was histopathologically defined by a neuropathologist as the following: 1) “pure” cerebral radiation necrosis; 2) “mixed” pathology with coexistence of cerebral radiation necrosis and recurrent tumors; 3) “predominant” (>80%) cerebral radiation necrosis; 4) predominant (>80%) recurrent tumor; and 5) pure tumor. COLLAGE features were extracted from the expert-annotated ROIs on MR imaging. COLLAGE features exhibited decreased skewness for patients with pure and predominant cerebral radiation necrosis and were statistically significantly different from those in patients with predominant recurrent tumors, which had highly skewed COLLAGE values.

The authors evaluated tumor cell density using a transfer learning method that generates individualized patient models, grounded in the wealth of population data, while also detecting and adjusting for interpatient variabilities based on each patient's own histologic data. They collected 82 image-recorded biopsy samples, from 18 patients with primary GBM. With multivariate modeling, transfer learning improved performance (r = 0.88) compared with one-model-fits-all (r = 0.39). They conclude that transfer learning significantly improves predictive modeling performance for quantifying tumor cell density in glioblastoma.