A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans

Abstract

Acute Intracranial hemorrhage (ICH) is a life-threatening disease that requires emergency medical attention, which is routinely diagnosed using non-contrast head CT imaging. The diagnostic accuracy of acute ICH on CT varies greatly among radiologists due to the difficulty of interpreting subtle findings and the time pressure associated with the ever-increasing workload. The use of artificial intelligence technology may help automate the process and assist radiologists for more prompt and better decision-making. In this work, we design a deep learning approach that mimics the interpretation process of radiologists, and combines a 2D CNN model and two sequence models to achieve accurate acute ICH detection and subtype classification. Being developed using the extensive 2019-RSNA Brain CT Hemorrhage Challenge dataset with over 25000 CT scans, our deep learning algorithm can accurately classify the acute ICH and its five subtypes with AUCs of 0.988 (ICH), 0.984 (EDH), 0.992 (IPH), 0.996 (IVH), 0.985 (SAH), and 0.983 (SDH), respectively, reaching the accuracy level of expert radiologists. Our method won 1st place among 1345 teams from 75 countries in the RSNA challenge. We have further evaluated our algorithm on two independent external validation datasets with 75 and 491 CT scans, respectively, and our method maintained high AUCs of 0.964 and 0.949 for acute ICH detection. These results have demonstrated the high performance and robust generalization ability of our proposed method, which makes it a useful second-read or triage tool that can facilitate routine clinical applications.

Keywords: Deep learning; Head CT; Image classification; Intracranial hemorrhage (ICH); Sequence model.

Fig. 1

The pipeline of our study. The AI system comprises three stages. In the first stage, a 2D CNN classifier is used to extract features and produce an initial prediction of ICH and its subtypes on each input slice. The generated feature vectors for all slices of a 3D scan are fed into Sequence Model 1 (the second stage) to get more refined and spatially coherent ICH detection results on every image slice. In the third stage, the classification results of the CNN classifier and Sequence Model 1 are assembled together and passed through Sequence Model 2 to perform adaptive model averaging. The output of Sequence Model 2 gives the final ICH prediction results for every slice of the input scan. Each DICOM file represents one 3D scan, which can be considered as a sequence of 2D slices.

Fig. 2

ROC curves of our AI algorithm evaluated on three test data sets: the RSNA batch-1 test set, the PhysioNet-ICH, and the CQ500 datasets for predicting (a) ICH, (b) EDH, (c) IPH, (d) IVH, (e) SAH, and (f) SDH. The “RSNA-1” means the batch-1 test set from the 2019-RSNA Brain CT Hemorrhage Challenge.

Fig. 3

Visualization of model predictions using saliency maps on the CQ500 dataset (left panel (a)–(e)) and the PhysioNet-ICH dataset (right panel (f)–(j)). In each subfigure, the original CT slice (left column), the corresponding saliency map (middle column), and the manual annotation by experienced radiologists (right column) are shown. In the saliency maps, warmer colors represent more relevant regions for the model prediction of the corresponding bleeding type. The same color scale is used for all the saliency maps, which is indicated by the color bar. The brain window is used for displaying the CT images.