IHP can be suspected on MRI and defined pathologically on biopsy. Untreated, the clinical course is usually marked by severe headache and progressive neurologic deterioration and vision loss. Although initially steroid-responsive, clinical manifestations frequently recur with corticosteroid taper, requiring the addition of immunosuppressive agents in some cases.

Intraoperative diagnosis is essential for providing safe and effective care during cancer surgery 1. The existing workflow for intraoperative diagnosis based on hematoxylin and eosin-staining of processed tissue is time-, resource-, and labor-intensive 2,3. Moreover, interpretation of intraoperative histologic images is dependent on a contracting, unevenly distributed pathology workforce 4. Here, we report a parallel workflow that combines stimulated Raman histology (SRH) 5-7 , a label-free optical imaging method, and deep convolutional neural networks (CNN) to predict diagnosis at the bedside in near real-time in an automated fashion. Specifically, our CNN, trained on over 2.5 million SRH images, predicts brain tumor diagnosis in the operating room in under 150 seconds, an order of magnitude faster than conventional techniques (e.g., 20-30 minutes) 2. In a multicenter, prospective clinical trial (n = 278) we demonstrated that CNN-based diagnosis of SRH images was non-inferior to pathologist-based interpretation of conventional histologic images (overall accuracy, 94.6% vs. 93.9%). Our CNN learned a hierarchy of recognizable histologic feature representations to classify the major histopathologic classes of brain tumors. Additionally, we implemented a semantic segmentation method to identify tumor infiltrated, diagnostic regions within SRH images. These results demonstrate how intraoperative cancer diagnosis can be streamlined, creating a complimentary pathway for tissue diagnosis that is independent of a traditional pathology laboratory.

No abstract

Glioblastoma multiforme (GBM) is the most aggressive brain tumor. Standard treatment includes surgery, radiation and chemotherapy. Prognosis is dismal with an average survival of approximately 1 year. Gliadel wafers are one treatment option, working as a source for local chemotherapy delivery. Their use is controversial with questionable survival benefit and potential side effects. We reviewed the literature in an effort to clarify their role in the treatment of high-grade gliomas. A systematic PubMed search was performed using the keywords 'Gliadel', 'carmustine' or 'BCNU wafers' in newly diagnosed high-grade glioma patients. Treatment regimen, and median survival were analyzed. Adverse event ratio was calculated by computing the number of adverse events in a study per patient receiving carmustine wafers. Nineteen studies with 795 patients were included in our review. Survival was 8.7-22.6 months with a mean overall survival (OS) of 16.2 months (control survival is approximately 14 months with surgery and adjuvant chemoradiotherapy). Adverse event ratio using Gliadel wafersin control group. Complication rate was 42.7%. Gliadel wafers may marginally increase survival and local control in newly diagnosed GBM patients but are associated with a high complication rate; therefore, we do not recommend using Gliadel wafers in patients with GBM. Further research may be warranted once a safer alternative to Gliadel wafers has been introduced.