Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networks

Extent of resection after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification of residual tumor from post-operative MR images is essential. The current standard method for estimating it is subject to high inter- and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of extent of resection. In this study, two state-of-the-art neural network architectures for pre-operative segmentation were trained for the task. The models were extensively validated on a multicenter dataset with nearly 1000 patients, from 12 hospitals in Europe and the United States. The best performance achieved was a 61% Dice score, and the best classification performance was about 80% balanced accuracy, with a demonstrated ability to generalize across hospitals. In addition, the segmentation performance of the best models was on par with human expert raters. The predicted segmentations can be used to accurately classify the patients into those with residual tumor, and those with gross total resection.

Combined endovascular therapy of ruptured aneurysms and cerebral vasospasm

We describe two patients with subarachnoid haemorrhage due to a ruptured intracranial aneurysm and severe symptomatic vasospasm. The aneurysm was occluded with detachable coils followed by intra-arterial infusion of papaverine to treat vasospasm as an one-stage procedure. There was significant resolution of the vasospasm. The long-term clinical outcome in one patient was excellent, the other still has minor deficits. Combined endovascular aneurysm therapy followed by intra-arterial spasmolysis with papaverine is a technically feasible therapeutic alternative in patients with symptomatic vasospasm.

Heterogeneous expression of E-cadherin and p53 in prostate cancer: clinical implications. BIOMED-II Markers for Prostate Cancer Study Group

Histologic grade and tumor volume are markers of malignant phenotype. More objective markers, however, have been sought for needle biopsy specimens. The aim of this study was to evaluate how immunohistochemical expression of the potential prognostic markers E-cadherin and p53 in biopsy specimens relates to the expression of these markers in prostatectomy specimens. Therefore, we analyzed 47 prostatectomy specimens and their preoperative biopsy specimens. Fixation of surgical specimens and the immunohistochemical assay for both E-cadherin and p53 expression was optimized. All paraffin blocks containing areas of carcinoma were submitted for immunohistochemical analysis. The prevalence of abnormal p53 immunoreactivity was only 11%. In addition, abnormal p53 expression was virtually restricted to cases that were already identified as having a poor prognosis on the basis of the large volume and the high grade of their carcinomas. In 28% of the cases, we found abnormal immunoreactivity for E-cadherin. These cases revealed considerable heterogeneity in topographic distribution of abnormal expression. The level of sensitivity to the detection of abnormal E-cadherin expression or abnormal p53 in the prostatectomy specimen was 15% and 60%, respectively. In view of the inherent heterogeneity of E-cadherin expression and the low prevalence of abnormal p53 expression, we question the use of these markers for prognostic purposes in needle biopsy specimens. Unless representative sampling by needle biopsy can be assured, the use of E-cadherin expression will be of most value in prostatectomy specimens.