Search

Simple Summary: Uveal melanoma (UM) is the most common primary intraocular malignancy in adults. Local treatment of tumors is typically straightforward. Yet, despite successful local treatment, a portion of patients will still develop subsequent distant metastases which are usually fatal. The current gold standard tool for prognostication is gene expression profiling (GEP), which is only available in the United States. The goal of this research is to develop an artificial intelligence (deep learning-based) tool which can predict patient survival directly from digital cytopathology images generated from fine-needle aspiration biopsies. Our deep learning model was able to predict Month 48 survival status directly from digital cytopathology images with reasonably robust performance. This approach, if validated prospectively, could serve as an alternative survival prediction tool for patients with UM to whom GEP is not available. Background: Uveal melanoma (UM) is the most common primary intraocular malignancy in adults. The median overall survival time for patients who develop metastasis is approximately one year. In this study, we aim to leverage deep learning (DL) techniques to analyze digital cytopathology images and directly predict the 48 month survival status on a patient level. Methods: Fine-needle aspiration biopsy (FNAB) of the tumor was performed in each patient diagnosed with UM. The cell aspirate was smeared on a glass slide and stained with H&E. Each slide then underwent whole-slide scanning. Within each whole-slide image, regions of interest (ROIs) with UM cells were automatically extracted. Each ROI was converted into super pixels, and the super pixels were automatically detected, segmented and annotated as "tumor cell" or "background" using DL. Cell-level features were extracted from the segmented tumor cells. The cell-level features were aggregated into slide-level features which were learned by a fully connected layer in an artificial neural network, and the patient survival status was predicted directly from the slide-level features. The data were partitioned at the patient level (78% training and 22% testing). Our DL model was trained to perform the binary prediction of yes-versus-no survival by Month 48. The ground truth for patient survival was established via a retrospective chart review. Results: A total of 74 patients were included in this study (43% female; mean age at the time of diagnosis: 61.8 ± 11.6 years), and 207,260 unique ROIs were generated for model training and testing. By Month 48 after diagnosis, 18 patients (24%) died from UM metastasis. Our hold-out test set contained 16 patients, where 6 patients had passed away and 10 patients were alive at Month 48. When using a sensitivity threshold of 80% in predicting UM-specific death by Month 48, our model achieved an overall accuracy of 75%. Within the subgroup of patients who died by Month 48, our model achieved a prediction accuracy of 83%. Of note, one patient in our test set was a clinical surprise, namely death by Month 48 despite having a GEP class 1A tumor, which typically portends a good prognosis. Our model correctly predicted this clinical surprise as well. Conclusions: Our DL model was able to predict the Month 48 survival status directly from digital cytopathology images obtained from FNABs of UM tumors with reasonably robust performance. This approach, if validated prospectively, could serve as an alternative survival prediction tool for patients with UM to whom GEP is not available. [ABSTRACT FROM AUTHOR]

Background Combined BRAF and MEK inhibition is effective for some BRAFV600E-altered gliomas, a cancer for which there are few effective therapies. While recent clinical trials demonstrate objective response rates of 30%–40%, tolerable adverse event rates are 70%–90%, and 12%–15% of patients stop therapy for toxicity. There are no clear guidelines regarding the timing and reinitiation of BRAF-targeted therapies following drug holidays. Here, we describe 4 patients with rapid disease progression during periods of treatment interruption. All patients experienced a response upon resumption of targeted therapy. Methods This is a multi-institutional, retrospective review of 4 patients. Results Three patients were diagnosed with BRAFV600E mutated anaplastic pleomorphic xanthoastrocytoma (aPXA) and 1 with epithelioid glioblastoma. The age range was 32 to 46; 3 patients were female and one patient was male. All patients were initially treated with radiation and were subsequently treated with BRAF/MEK inhibitors after disease progression. All patients with aPXA required the targeted therapy to be held due to toxicity and 1 patient held the therapy prior to transitioning to a novel BRAF-targeted agent. All patients were restarted on BRAF/MEK inhibitors after a drug holiday. Three patients required a dose reduction and all improved clinically following reinitiation. Conclusions Clinical and radiographic progression may occur rapidly upon holding BRAF-targeted therapy, warranting judicious dose reductions and minimization of drug holidays. [ABSTRACT FROM AUTHOR]

Background: Early diagnosis of encephalitis involves identifying signs of neuroinflammation, including cerebrospinal fluid (CSF) pleocytosis. However, absence of CSF pleocytosis in encephalitis has been described, most notably in autoimmune encephalitis. We examined clinical characteristics and outcomes associated with the absence or presence of CSF white blood cell pleocytosis (≥ 5 cells/µL), to inform timely diagnosis and management of encephalitis., Methods: This retrospective study compares initial CSF profiles in 597 adult patients with all-cause encephalitis., Results: Of the 597 patients, 446 (74.7%) had CSF pleocytosis while 151 (25.3%) did not. CSF pleocytosis occurred more commonly in infectious cases (200/446, 44.8%), along with 59 (13.2%) autoimmune cases, comprised chiefly of anti-NMDAR encephalitis (37/59, 62.7%). Notably, the group without pleocytosis was comprised of similar proportions of infectious (47/151, 31.1%) and autoimmune (38/151, 25.92%; p>0.05) encephalitis. Among those with infectious encephalitis, 47/247 (19%) had absent pleocytosis, including 18/76 (23.7%) with HSV-1 encephalitis. The absence of pleocytosis was associated with a decreased rate of acyclovir administration (47.7% in patients without pleocytosis vs. 71.1% in patients with pleocytosis, p<0.001). Despite pleocytosis being associated with some measures of clinical severity at admission such as a Full Outline of UnResponsiveness (FOUR) score ≤14, it was not associated with mortality or prolonged hospitalization., Conclusion: CSF pleocytosis is an important criterion for encephalitis diagnosis, but 25.3% of patients with all-cause encephalitis and 23.7% of those with HSV-1 encephalitis exhibit absence of pleocytosis on initial LP. Acyclovir initiation should not be delayed in the absence of pleocytosis in patients with suspected encephalitis., (© The Author(s) 2024. Published by Oxford University Press on behalf of Infectious Diseases Society of America. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com.)