Abstract 78: Fully Automated Segmentation Algorithm for Hematoma Volumetric Analysis in Spontaneous Intracerebral Hemorrhage

Abstract

Background and Purpose: Hematoma volume measurements influence prognosis and treatment decisions in patients with spontaneous intracerebral hemorrhage (ICH). The aims of this study are to derive and validate a fully automated segmentation algorithm for ICH volumetric analysis using deep learning methods. Methods: Inpatient computed tomography scans of 300 consecutive adults (age ≥18 years) with spontaneous, supratentorial ICH who were enrolled in the Intracerebral Hemorrhage Outcomes Project (2009-2018) were separated into training (n=260) and test (n=40) datasets. A fully automated segmentation algorithm was derived using convolutional neural networks (CNN), and it was trained on manual segmentations from the training dataset. The algorithm’s performance was assessed against manual and semi-automated segmentation methods in the test dataset. Results: The mean volumetric Dice similarity coefficients for the fully automated segmentation algorithm when tested against manual and semi-automated segmentation methods were 0.894±0.264 and 0.905±0.254, respectively. ICH volumes derived from fully automated vs. manual (R 2 =0.981;p<0.0001), fully automated vs. semi-automated (R 2 =0.978;p<0.0001), and semi-automated vs. manual (R 2 =0.990;p<0001) segmentation methods had strong between-group correlations. The fully automated segmentation algorithm (mean 12.0±2.7 seconds/scan) was significantly faster than both of the manual (mean 201.5±92.2 seconds/scan; p<0.001) and semi-automated (mean 288.58±160.3 seconds/scan; p<0.001) segmentation methods. Conclusions: The fully automated segmentation algorithm quantified hematoma volumes from CT scans of supratentorial ICH patients with similar accuracy and substantially greater efficiency compared with manual and semi-automated segmentation methods.