Skip to main content
SHARE
Publication

Coarse-to-Fine Multi-Task Training of Convolutional Neural Networks for Automated Information Extraction from Cancer Patholog...

by Mohammed M Alawad, Hong Jun Yoon, Georgia Tourassi
Publication Type
Conference Paper
Book Title
2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)
Publication Date
Page Numbers
218 to 221
Publisher Location
New York, United States of America
Conference Name
International Conference on Biomedical and Health Informatics
Conference Location
Las Vegas, Nevada, United States of America
Conference Sponsor
IEEE
Conference Date
-

Information extraction and coding of free-text pathology reports is an important activity for cancer registries to support national cancer surveillance. Cancer registrars must process high volumes of pathology reports on an annual basis. In this study, we investigated an automated approach using a coarse-to-fine training of convolutional neural networks (CNNs) for extracting the primary site, histological grade and laterality from unstructured cancer pathology text reports. Our proposed training scheme consists of two stages. In the first stage, the multi-task learning (MTL) with hard parameter sharing approach is used to train a multi-task MT-CNN model for all the tasks. Then, the TM-CNN parameters are used to initialize a CNN model for each task to be fine trained individually using its corresponding dataset. The performance of our proposed model was compared against a state-of-the-art CNN and the commonly used SVM classifier. We observed that the proposed model consistently outperformed the base line models, especially for the less prevalent classes. Specifically, the proposed training approach achieved a micro-F score of 0.7749 over 12 ICD- O-3 topography codes which is a significant improvement as compared with state-of-the-art CNN (0.7101) and the SVM (0.6019) classifiers. Also, the results demonstrate the potential of the proposed method for handling class imbalance within each task. It significantly improves macro-F score by 24% and 12% of the primary site and histology grade tasks, respectively.