Remarkable response of a patient with secondary glioblastoma to a histone deacetylase inhibitor.

Secondary glioblastoma is a rare brain tumor characterized by a mutation in isocitrate dehydrogenase, which is reported to lead to epigenetic modification. Patients with secondary glioblastoma experience poor survival and quality-of-life outcomes due to the disease's aggressiveness and a lack of targeted therapies. In this report, a patient with a secondary glioblastoma was treated with a histone deacetylase inhibitor, an epigenetic drug with potent anti-inflammatory properties, in addition to the standard regimen. The patient showed very favorable survival and quality-of-life measures, and a restoration of several neuro-metabolites as measured by spectroscopic magnetic resonance imaging.

Interactive phenotyping of large-scale histology imaging data with HistomicsML.

Whole-slide imaging of histologic sections captures tissue microenvironments and cytologic details in expansive high-resolution images. These images can be mined to extract quantitative features that describe tissues, yielding measurements for hundreds of millions of histologic objects. A central challenge in utilizing this data is enabling investigators to train and evaluate classification rules for identifying objects related to processes like angiogenesis or immune response. In this paper we describe HistomicsML, an interactive machine-learning system for digital pathology imaging datasets. This framework uses active learning to direct user feedback, making classifier training efficient and scalable in datasets containing 108+ histologic objects. We demonstrate how this system can be used to phenotype microvascular structures in gliomas to predict survival, and to explore the molecular pathways associated with these phenotypes. Our approach enables researchers to unlock phenotypic information from digital pathology datasets to investigate prognostic image biomarkers and genotype-phenotype associations.

Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models.

Translating the vast data generated by genomic platforms into accurate predictions of clinical outcomes is a fundamental challenge in genomic medicine. Many prediction methods face limitations in learning from the high-dimensional profiles generated by these platforms, and rely on experts to hand-select a small number of features for training prediction models. In this paper, we demonstrate how deep learning and Bayesian optimization methods that have been remarkably successful in general high-dimensional prediction tasks can be adapted to the problem of predicting cancer outcomes. We perform an extensive comparison of Bayesian optimized deep survival models and other state of the art machine learning methods for survival analysis, and describe a framework for interpreting deep survival models using a risk backpropagation technique. Finally, we illustrate that deep survival models can successfully transfer information across diseases to improve prognostic accuracy. We provide an open-source software implementation of this framework called SurvivalNet that enables automatic training, evaluation and interpretation of deep survival models.