Abstract TP170: An Explainable Deep Learning Method to Quantitatively Predict Hematoma Progression After Intracerebral Hemorrhage

Abstract

In patients with intracerebral hemorrhage (ICH), it is important to quickly and accurately individualize the treatment decision by quantitatively predicting the hematoma progression using medical information collected on admission. Current approaches only qualitatively predict ICH progression trends leveraging anatomical features extracted from non-contrast computed tomography (NCCT) images. However, these approaches do not consider the hemodynamics of the cerebral circulation system, cannot quantitatively predict ICH progression, and lack the needed explainability. To address these technical challenges, in this work, we developed an explainable deep learning method to quantitatively predict hematoma progression after ICH, which quantitatively predicts ICH progression leveraging (i) deep anatomical features (baseline ICH lesion volume) derived from NCCT images, and (ii) deep hemodynamic features focusing veins-of-interest derived from time-resolved CT images collected on admission. A total of 73 patients categorized into the training data set (containing 58 patients) and the test data set (containing 15 patients), with 216 sets of images, were used in the development and validation of the model. For the ICH lesion volume predicted by this model, the mean difference with respect to the reference volume is -0.96 mL, and the agreement limits are [-9.64 mL, +7.71 mL] (Figure 1). In conclusions, by simultaneously leveraging deep anatomical and hemodynamic features, our model can quantitatively predict ICH progression using multimodal CT images collected on admission and hence help individualize the treatment decision during hospitalization.