HPC-Based Hyperparameter Search of MT-CNN for Information Extraction from Cancer Pathology Reports
Abstract: Finding optimal hyperparameters is necessary to identify the best performing deep learning models, but the process is costly. In this paper, we applied model-based optimization, also known as Bayesian optimization, using the CANDLE framework implemented on a High-Performance Computing environment. As a use case, we selected information extraction from cancer pathology reports using a multi-task convolutional neural network, a model with 10 hyperparameters to be optimized. We utilized a synthesized text corpus of 8,000 training cases and 2,000 validation cases with four types of clinical task labels including primary cancer site, laterality, behavior, and histological grade. We conducted the experiments on the Titan supercomputer at the Oak Ridge Leadership Computing Facility (OLCF), reported the optimal hyperparameters found, and demonstrated that hyperparameter optimization using the CANDLE framework is a feasible approach with respect to both scalability and clinical task performance.
Back to Fourth Computational Approaches for Cancer Workshop (CAFCW18) Archive Listing
Back to Full Workshop Archive Listing