Precise segmentation of non-enhanced computed tomography in patients with ischemic stroke based on multi-scale U-Net deep network model

Background and Objective: Acute ischemic stroke requires timely diagnosis and thrombolytic therapy, but it is difficult to locate and quantify the lesion site manually. The purpose of this study was to explore a more rapid and effective method for automatic image segmentation of acute ischemic stroke. Methods: The image features of 30 stroke patients were segmented from non-enhanced computed tomography (CT) images using a multi-scale U-Net deep network model. The Dice loss function training model was used to counter the similar imbalance problem in the data. The difference was compared between manual segmentation and automatic segmentation. Results: The Dice similarity coefficient based on multi-scale convolution U-Net network segmentation was 0.86 +/- 0.04, higher than the Dice based on classic U-Net (0.81 +/- 0.07, P = 0.001). The lesion contour of automatic segmentation based on multi-scale U-Net was very close to manual segmentation. The error of lesion area is 1.28 +/- 0.59 mm(2,) and the Pearson correlation coefficient was r = 0.986 (P < 0.01). The motion time of automatic segmentation is less than 20 ms. Conclusions: Multi-scale U-Net deep network model can effectively segment ischemic stroke lesions in non-enhanced CT and meet real-time clinical requirements. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

This study developed a multi-scale U-Net deep network model for automatic image segmentation of acute ischemic stroke lesions on non-enhanced CT images, which showed higher accuracy and shorter processing time compared to the classic U-Net method.