Natural Language Generation Model for Mammography Reports Simulation

Extending the size of labeled corpora of medical reports is a major step towards a successful training of machine learning algorithms. Simulating new text reports is a key solution for reports augmentation, which extends the cohort size. However, text generation in the medical domain is challenging...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2020-09, Vol.24 (9), p.2711-2717
Main Authors: Hoogi, Assaf, Mishra, Arjun, Gimenez, Francisco, Dong, Jeffrey, Rubin, Daniel
Format: Article
Language:English
Subjects:
Algorithms
Cancer
Classification
Computer simulation
Fields (mathematics)
Informatics
Learning algorithms
Machine learning
mammo-graphy reports
Mammography
Medical diagnosis
Medical diagnostic imaging
Natural language generation
Natural languages
Performance evaluation
Qualitative analysis
RNN-LSTM
simulation
Test sets
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Extending the size of labeled corpora of medical reports is a major step towards a successful training of machine learning algorithms. Simulating new text reports is a key solution for reports augmentation, which extends the cohort size. However, text generation in the medical domain is challenging because it needs to preserve both content and style that are typical for real reports, without risking the patients' privacy. In this paper, we present a conditioned LSTM-RNN architecture for simulating realistic mammography reports. We evaluated the performance by analyzing the characteristics of the simulated reports and classifying them into benign and malignant classes. An average classification AUC was calculated over two distinct test sets. A qualitative analysis was also performed in which a masked radiologist classified 0.75 of the simulated reports as real reports, showing that both the style and content of the simulated reports were similar to real reports. Finally, we compared our RNN-LSTM generative model with Markov Random Fields. The RNN-LSTM provided significantly better and more stable performance than MRFs (p< 0.01, Wilcoxon).
ISSN:2168-2194
2168-2208
DOI:10.1109/JBHI.2020.2980118