| Abstract: |
Image classification is probably the most fundamental task in radiology artificial intelligence. To reduce the burden of acquiring and labeling data sets, we employed a two-pronged strategy. We automatically extracted labels from radiology reports in Part 1. In Part 2, we used the labels to train a data-efficient reinforcement learning (RL) classifier. We applied the approach to a small set of patient images and radiology reports from our institution. For Part 1, we trained sentence-BERT (SBERT) on 90 radiology reports. In Part 2, we used the labels from the trained SBERT to train an RL-based classifier. We trained the classifier on a training set of 40 images. We tested on a separate collection of 24 images. For comparison, we also trained and tested a supervised deep learning (SDL) classification network on the same set of training and testing images using the same labels. Part 1: The trained SBERT model improved from 82 to 100 % accuracy. Part 2: Using Part 1’s computed labels, SDL quickly overfitted the small training set. Whereas SDL showed the worst possible testing set accuracy of 50%, RL achieved 100 % testing set accuracy, with a p-value of 4.9 × 10 - 4. We have shown the proof-of-principle application of automated label extraction from radiological reports. Additionally, we have built on prior work applying RL to classification using these labels, extending from 2D slices to entire 3D image volumes. RL has again demonstrated a remarkable ability to train effectively, in a generalized manner, and based on small training sets. © 2022, The Author(s) under exclusive licence to Society for Imaging Informatics in Medicine. |
