Deep Learning to Classify Radiology Free-Text Reports

Abstract

Purpose To evaluate the performance of a deep learning convolutional neural network (CNN) model compared with a traditional natural language processing (NLP) model in extracting pulmonary embolism (PE) findings from thoracic computed tomography (CT) reports from two institutions. Materials and Methods Contrast material-enhanced CT examinations of the chest performed between January 1, 1998, and January 1, 2016, were selected. Annotations by two human radiologists were made for three categories: the presence, chronicity, and location of PE. Classification of performance of a CNN model with an unsupervised learning algorithm for obtaining vector representations of words was compared with the open-source application PeFinder. Sensitivity, specificity, accuracy, and F1 scores for both the CNN model and PeFinder in the internal and external validation sets were determined. Results The CNN model demonstrated an accuracy of 99% and an area under the curve value of 0.97. For internal validation report data, the CNN model had a statistically significant larger F1 score (0.938) than did PeFinder (0.867) when classifying findings as either PE positive or PE negative, but no significant difference in sensitivity, specificity, or accuracy was found. For external validation report data, no statistical difference between the performance of the CNN model and PeFinder was found. Conclusion A deep learning CNN model can classify radiology free-text reports with accuracy equivalent to or beyond that of an existing traditional NLP model. RSNA, 2017 Online supplemental material is available for this article.

Antimicrobial prescribing for children in primary care

“…At the moment, they are designed largely for in‐practice use. As the ability to utilise natural language processing to systematically analyse free‐text data improve, it is likely that future studies will be able to enhance the analyses of these data …”

Radiomics and Machine Learning in Oral Healthcare

“…Consequently, automatic methods based on deep neural networks have been tested for several purposes, which are as follows: classification, image registration, segmentation, lesion detection, image retrieval, image guided therapy, image generation, and enhancement . Most recently, radiomics and AI research have been advancing in the dental field, revealing the potential of these technologies to substantially improve clinical care …”

Sensor‐based activity recognition independent of device placement and orientation

“…Deep learning algorithm has been paid great attention in recent years. It has excellent performance in many fields such as image processing, natural language processing, and data mining . Several practical and efficient DL network structures have been designed in former research like AlexNet and Resnet .…”