Peter Chang

<h3>BACKGROUND AND PURPOSE:</h3> The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. <h3>MATERIALS AND METHODS:</h3> MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify <i>isocitrate dehydrogenase 1</i> (<i>IDH1</i>) mutation status, 1p/19q codeletion, and <i>O6-methylguanine-DNA methyltransferase</i> (<i>MGMT</i>) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. <h3>RESULTS:</h3> Classification had high accuracy: <i>IDH1</i> mutation status, 94%; 1p/19q codeletion, 92%; and <i>MGMT</i> promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. <h3>CONCLUSIONS:</h3> Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training.

BACKGROUND AND PURPOSE: Convolutional neural networks are a powerful technology for image recognition. This study evaluates a convolutional neural network optimized for the detection and quantification of intraparenchymal, epidural/subdural, and subarachnoid hemorrhages on noncontrast CT. MATERIALS AND METHODS: This study was performed in 2 phases. First, a training cohort of all NCCTs acquired at a single institution between January 1, 2017, and July 31, 2017, was used to develop and cross-validate a custom hybrid 3D/2D mask ROI-based convolutional neural network architecture for hemorrhage evaluation. Second, the trained network was applied prospectively to all NCCTs ordered from the emergency department between February 1, 2018, and February 28, 2018, in an automated inference pipeline. Hemorrhage-detection accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value were assessed for full and balanced datasets and were further stratified by hemorrhage type and size. Quantification was assessed by the Dice score coefficient and the Pearson correlation. RESULTS: A 10,159-examination training cohort (512,598 images; 901/8.1% hemorrhages) and an 862-examination test cohort (23,668 images; 82/12% hemorrhages) were used in this study. Accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative-predictive value for hemorrhage detection were 0.975, 0.983, 0.971, 0.975, 0.793, and 0.997 on training cohort cross-validation and 0.970, 0.981, 0.951, 0.973, 0.829, and 0.993 for the prospective test set. Dice scores for intraparenchymal hemorrhage, epidural/subdural hemorrhage, and SAH were 0.931, 0.863, and 0.772, respectively. CONCLUSIONS: A customized deep learning tool is accurate in the detection and quantification of hemorrhage on NCCT. Demonstrated high performance on prospective NCCTs ordered from the emergency department suggests the clinical viability of the proposed deep learning tool.

Although Fc receptor-mediated phagocytosis is accompanied by a variety of transmembrane signaling events, not all signaling events are required for particle ingestion. For example, Fc receptor-mediated phagocytosis in mouse inflammatory macrophages (Di Virgilio, F., B. C. Meyer, S. Greenberg, and S. C. Silverstein. 1988. J. Cell Biol. 106:657; Greenberg, S., J. El Khoury, F. Di Virgilio, and S. C. Silverstein. 1991. J. Cell Biol. 113:757) and neutrophils (Della Bianca, V., M. Grzeskowiak, and F. Rossi. 1990. J. Immunol. 144:1411) occurs in the absence of cytosolic calcium transients. We sought to identify transmembrane signaling events that are essential for phagocytosis. Here we show that tyrosine phosphorylation is an early event after Fc receptor ligation in mouse inflammatory macrophages, and that the formation of tyrosine phosphoproteins coincides temporally with the appearance of F-actin beneath phagocytic cups. The distribution of tyrosine phosphoproteins that accumulated beneath phagocytic cups was punctate and corresponded to areas of high ligand density on the surface of the antibody-coated red blood cells, which provided the phagocytic stimulus. A tyrosine kinase inhibitor, genistein, but not several inhibitors of protein kinase C, blocked the appearance of tyrosine phosphoproteins as assessed by immunofluorescence, the focal accumulation of F-actin beneath immunoglobulin G-opsonized particles, and the ingestion of these particles as well. We suggest that tyrosine phosphorylation is a critical signaling event that underlies Fc receptor-mediated phagocytosis in mouse macrophages, and is necessary for the engulfment per se.

BACKGROUND AND PURPOSE: The complex MR imaging appearance of glioblastoma is a function of underlying histopathologic heterogeneity. A better understanding of these correlations, particularly the influence of infiltrating glioma cells and vasogenic edema on T2 and diffusivity signal in nonenhancing areas, has important implications in the management of these patients. With localized biopsies, the objective of this study was to generate a model capable of predicting cellularity at each voxel within an entire tumor volume as a function of signal intensity, thus providing a means of quantifying tumor infiltration into surrounding brain tissue. MATERIALS AND METHODS: Ninety-one localized biopsies were obtained from 36 patients with glioblastoma. Signal intensities corresponding to these samples were derived from T1-postcontrast subtraction, T2-FLAIR, and ADC sequences by using an automated coregistration algorithm. Cell density was calculated for each specimen by using an automated cell-counting algorithm. Signal intensity was plotted against cell density for each MR image. RESULTS: = 0.74), suggesting that each sequence offers different and complementary information. CONCLUSIONS: Using localized biopsies, we have generated a model that illustrates a quantitative and significant relationship between MR signal and cell density. Projecting this relationship over the entire tumor volume allows mapping of the intratumoral heterogeneity in both the contrast-enhancing tumor core and nonenhancing margins of glioblastoma and may be used to guide extended surgical resection, localized biopsies, and radiation field mapping.