102 AI-Based Molecular Classification of Diffuse Gliomas using Rapid, Label-Free Optical Imaging.

INTRODUCTION: Molecular classification has transformed the management of brain tumors by enabling more accurate prognostication and personalized treatment. Access to timely molecular diagnostic testing for brain tumor patients is limited, complicating surgical and adjuvant treatment and obstructing clinical trial enrollment. METHODS: By combining stimulated Raman histology (SRH), a rapid, label-free, non-consumptive, optical imaging method, and deep learning-based image classification, we are able to predict the molecular genetic features used by the World Health Organization (WHO) to define the adult-type diffuse glioma taxonomy, including IDH-1/2, 1p19q-codeletion, and ATRX loss. We developed a multimodal deep neural network training strategy that uses both SRH images and large-scale, public diffuse glioma genomic data (i.e. TCGA, CGGA, etc.) in order to achieve optimal molecular classification performance. RESULTS: One institution was used for model training (University of Michigan) and four institutions (NYU, UCSF, Medical University of Vienna, and University Hospital Cologne) were included for patient enrollment in the prospective testing cohort. Using our system, called DeepGlioma, we achieved an average molecular genetic classification accuracy of 93.2% and identified the correct diffuse glioma molecular subgroup with 91.5% accuracy within 2 minutes in the operating room. DeepGlioma outperformed conventional IDH1-R132H immunohistochemistry (94.2% versus 91.4% accuracy) as a first-line molecular diagnostic screening method for diffuse gliomas and can detect canonical and non-canonical IDH mutations. CONCLUSIONS: Our results demonstrate how artificial intelligence and optical histology can be used to provide a rapid and scalable alternative to wet lab methods for the molecular diagnosis of brain tumor patients during surgery.

Diagnostic TCD for intracranial stenosis in acute stroke patients: experience from a tertiary care stroke center in Karachi, Pakistan.

BACKGROUND: Stroke is a common cause of morbidity and mortality around the world. Intracranial large artery atherosclerosis (ICAD) is a frequent etiology of stroke in the South Asian population. There is a need for widely available screening tools to identify patients that are at high risk of stroke due to ICAD for aggressive risk management. This study describes the experience of using the transcranial Doppler (TCD) as a screening tool for this purpose at a tertiary care hospital in a developing country. METHODS: 86 Patients admitted with stroke due to ICAD underwent TCD for six arteries (Right and left middle cerebral arteries, right and left anterior cerebral arteries, right and left posterior cerebral arteries) in addition to the magnetic resonance angiography (MRA) that is done routinely at the stroke center. Arteries were labeled with either <50 or >50% stenosis by TCD using two separate criteria. These findings were compared with those from the MRA which was used as the gold standard. The proportion of patients that had complete exams (all six arteries insonated by TCD) was reported. The success rate of each TCD criteria in detecting arteries with >50% stenosis was also calculated. RESULTS: There was an attempt to visualize 516 arteries (86 patients with 6 arteries each) of which 375 (72.7%) were successfully insonated. 38 of the 86 (55.8%) patients had complete examinations. MRA reported 43 (8.3%) arteries as stenosed >50%. The TCD did not categorize any artery as stenosed using either criterion and hence failed to classify any stenosed artery correctly. The positive predictive and sensitivity was 0 for this study and the negative predictive value was 93.3%. CONCLUSIONS: This study indicates the poor sensitivity of TCD to be a reliable screening tool for the presence of ICAD in the South Asian population in a real life clinical setting.

Adult cardiac critical care at the King Abdulaziz Cardiac Center.

Adult Cardiac Critical Cardiac Care division at the King Abdulaziz Cardiac Center - Riyadh, Saudi Arabia, was created in 2011 to address the critical care needs of cardiac surgery and adult cardiology patients that were beyond the scope of their specialties. The division offers its services in two semi-closed intensive care units consisting of 17 beds of Level 3 care. The concept and rationale behind this relatively new subspecialty and its organization in our center are presented in this brief report.