Patra, Devi Prasad

Abstract This is the case of an 86-yr-old gentleman who presented with left facial pain exacerbated by eating, drinking, chewing, and shaving (distribution: V2, V3). The patient was diagnosed with trigeminal neuralgia and was refractory to medications. Imaging showed a superior cerebellar artery (SCA) loop adjacent to the trigeminal nerve root entry zone and a decision to perform a microvascular decompression of the fifth nerve was presented to the patient. After patient informed consent was obtained, a standard 3 cm × 3 cm retrosigmoid craniotomy was performed with the patient in a supine head turned position and in reverse Trendelenburg. The arachnoid bands tethering the SCA to the trigeminal nerve were sharply divided. A slit was then made in the tentorium and a 3 mm fenestrated clip was then used to secure the transposed SCA away from the trigeminal nerve. The SCA proximal to this was slightly patulous in its course so a small amount of a fibrin glue was also used to secure the more proximal SCA to the tentorium. The patient was symptom-free postoperatively and no longer required medical therapy. Additionally, imaging was consistent with adequate separation of the nerve from adjacent vessels. 1-5

Abstract INTRODUCTION The quantification of intratumoral heterogeneity – through radiomics-based approaches - can help resolve the regionally distinct genetic drug targets that may co-exist within a single Glioblastoma (GBM) tumor. While this offers potential diagnostic value under the paradigm of individualized oncology, clinical decision-making must also consider the degree of uncertainty associated with each model. In this study, we evaluate the performance of a novel machine-learning (ML) algorithm, called Gaussian Process (GP) modeling, that can quantify the impact of multiple sources of uncertainty in ML model development and prediction accuracy, including variabilities in the copy number measurement, radiomics features, training sample characteristics, and training sample size. METHOD We collected 95 image-localized biopsies from 25 primary GBM patients. We coregistered stereotactic locations with preoperative multi-parametric MRI features (conventional MRI, DSC perfusion, Diffusion Tensor Imaging) to generate spatially matched pairs of MRI and copy number variants (CNV) for for each biopsy. We developed a Gaussian Process (GP) model to predict CNV for Epidermal Growth Factor Receptor (EGFR) based on MRI radiomic features in each patient. We used leave-one-patient-out cross validation to quantify prediction accuracy and model uncertainty. Spatial prediction and uncertainty (p-value) maps were overlaid to help visualize regional genetic variation of EGFR and uncertainty of the radiomic predictions. RESULT: The initial GP radiomics model for EGFR amplification (CNV > 3.5) produced a sensitivity of 0.8 and specificity of 0.8. Samples/regions associated with high uncertainty (p-value >0.05) correlated with either 1) extrapolation of radiomic features from the training set-defined feature space or 2) insufficient training samples in the feature space. CONCLUSION We present a ML-based model that quantifies spatial genetic heterogeneity in GBM, while also estimating model uncertainties that result from multi-source data variabilities. This approach lays the groundwork for prospective clinical integration of modeling-based diagnostic approaches in the paradigm of individualized medicine.

Roberts Bartholow, a physician, born and raised in Maryland, was a surgeon and Professor in Medicine who had previously served the Union during the Civil War. His interest in scientific research drove him to perform the first experiment that tested the excitability of the human brain cortex. His historical experiment on one of his patients, Mary Rafferty, with a cancerous ulcer on the skull, was one of his great accomplishments. His inference from this experiment and proposed scientific theory of cortical excitation and localization in humans was one of the most critically acclaimed topics in the medical community, which attracted the highest commendation for the unique discovery as well as criticism for possible ethical violations. Despite that criticism, his theory and methods of cortical localization are the cornerstone of modern brain mapping and have, in turn, led to countless medical innovations.