Abstract:Both radiographic (Rad) imaging, such as multi-parametric magnetic resonance imaging, and digital pathology (Path) images captured from tissue samples are currently acquired as standard clinical practice for glioblastoma tumors. Both these data streams have been separately used for diagnosis and treatment planning, despite the fact that they provide complementary information. In this research work, we aimed to assess the potential of both Rad and Path images in combination and comparison. An extensive set of engineered features was extracted from delineated tumor regions in Rad images, comprising T1, T1-Gd, T2, T2-FLAIR, and 100 random patches extracted from Path images. Specifically, the features comprised descriptors of intensity, histogram, and texture, mainly quantified via gray-level-co-occurrence matrix and gray-level-run-length matrices. Features extracted from images of 107 glioblastoma patients, downloaded from The Cancer Imaging Archive, were run through support vector machine for classification using leave-one-out cross-validation mechanism, and through support vector regression for prediction of continuous survival outcome. The Pearson correlation coefficient was estimated to be 0.75, 0.74, and 0.78 for Rad, Path and RadPath data. The area-under the receiver operating characteristic curve was estimated to be 0.74, 0.76 and 0.80 for Rad, Path and RadPath data, when patients were discretized into long- and short-survival groups based on average survival cutoff. Our results support the notion that synergistically using Rad and Path images may lead to better prognosis at the initial presentation of the disease, thereby facilitating the targeted enrollment of patients into clinical trials.
Abstract:Cancer histology reveals disease progression and associated molecular processes, and contains rich phenotypic information that is predictive of outcome. In this paper, we developed a computational approach based on deep learning to predict the overall survival and molecular subtypes of glioma patients from microscopic images of tissue biopsies, reflecting measures of microvascular proliferation, mitotic activity, nuclear atypia, and the presence of necrosis. Whole-slide images from 663 unique patients [IDH: 333 IDH-wildtype, 330 IDH-mutants, 1p/19q: 201 1p/19q non-codeleted, 129 1p/19q codeleted] were obtained from TCGA. Sub-images that were free of artifacts and that contained viable tumor with descriptive histologic characteristics were extracted, which were further used for training and testing a deep neural network. The output layer of the network was configured in two different ways: (i) a final Cox model layer to output a prediction of patient risk, and (ii) a final layer with sigmoid activation function, and stochastic gradient decent based optimization with binary cross-entropy loss. Both survival prediction and molecular subtype classification produced promising results using our model. The c-statistic was estimated to be 0.82 (p-value=4.8x10-5) between the risk scores of the proposed deep learning model and overall survival, while accuracies of 88% (area under the curve [AUC]=0.86) were achieved in the detection of IDH mutational status and 1p/19q codeletion. These findings suggest that the deep learning techniques can be applied to microscopic images for objective, accurate, and integrated prediction of outcome for glioma patients. The proposed marker may contribute to (i) stratification of patients into clinical trials, (ii) patient selection for targeted therapy, and (iii) personalized treatment planning.