Model-based Hyperparameter Optimization of Convolutional Neural Networks for Information Extraction from Cancer Pathology Reports on HPC
- ORNL
- Argonne National Laboratory (ANL)
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, and hierarchical convolutional attention network 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 demonstrated that hyperparameter optimization using the CANDLE framework is a feasible approach with respect to both scalability and clinical task performance.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1559691
- Resource Relation:
- Conference: IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI 2019) - Chicago, Illinois, United States of America - 5/19/2019 12:00:00 PM-5/22/2019 12:00:00 PM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Information Extraction from Cancer Pathology Reports with Graph Convolution Networks for Natural Language Texts
Selective Information Extraction Strategies for Cancer Pathology Reports with Convolutional Neural Networks