Optimizing Deep Learning Algorithms for Segmentation of Acute Infarcts on Non-Contrast Material-enhanced CT Scans of the Brain Using Simulated Lesions.

Abstract

To test the efficacy of lesion segmentation using a deep learning algorithm on non-contrast material-enhanced CT (NCCT) images with synthetic lesions resembling acute infarcts. In this retrospective study, 40 diffusion-weighted imaging (DWI) lesions in patients with acute stroke (median age, 69 years; range, 62-76 years; 17 women; screened between 2011 and 2017) were coregistered to 40 normal NCCT scans (median age, 70 years; range, 55-76 years; 25 women; screened between 2008 and 2011), which produced 640 combinations of DWI-NCCT with and without lesions for training (<i>n</i> = 420), validation (<i>n</i> = 110), and testing (<i>n</i> = 110). The signal intensity on the NCCT scans was depressed by 4 HU (a 13% drop) in the region of the diffusion-weighted lesion. Two U-Net architectures (standard and symmetry aware) were trained with two different training strategies. One was a naive strategy, in which the model started training with random coefficients. The other was a progressive strategy, which started with coefficients derived from a model trained on a dataset with lesions that were depressed by 10 HU. The Dice scores from the two architectures and training strategies were compared from the test dataset. Dice scores of symmetry-aware U-Nets were 25% higher than those of standard U-Nets (median, 0.49 vs 0.65; <i>P</i> < .001). Use of a progressive training strategy had no clear effect on model performance. Symmetry-aware U-Nets offer promise for segmentation of acute stroke lesions on NCCT scans.<b>Keywords:</b> Adults, CT-Quantitative, Stroke<i>Supplemental material is available for this article.</i>© RSNA, 2021.