Abstract: A weakly supervised intracranial hemorrhage (ICH) detection workflow includes training a deep learning (DL) model including a coupled convolutional neural network and recurrent neural network on a large dataset of CT scans with expert-labeled slices indicating presence or absence of ICH. Transfer learning (TL) is used to further train the DL model using a second large dataset of CT scans with only scan labels extracted from radiology reports using natural language processing (NLP). The DL model weights each slice of the scan against the final ICH diagnosis using an attention-based bi-directional long-short term memory network, where the attention weights represent slice-level ICH predictions. Model-generated heatmaps highlight significant regions of the CT scans that lead to the provided ICH predictions.

Abstract: A system for automatically labeling massive quantities of image report data includes a memory configured to store image data and metadata corresponding to the image data. The system also includes a processor operatively coupled to the memory and configured to apply a natural language processing algorithm to identify one or more characteristics of the image report data and the metadata. The processor is also configured to label the image report data based at least in part on the one or more identified characteristics to form a labeled dataset.