Related Experiment Video
Updated: Sep 3, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Unsupervised Deep Learning for Stroke Lesion Segmentation on Follow-up CT Based on Generative Adversarial Networks
H van Voorst1,2, P R Konduri3,2, L M van Poppel3,2
1From the Departments of Radiology and Nuclear Medicine (H.v.V., P.R.K., L.M.v.P., B.J.E., C.B.L.M.M., H.A.M.) h.vanvoorst@amsterdamumc.nl.
Background And Purpose:
Supervised deep learning is the state-of-the-art method for stroke lesion segmentation on NCCT. Supervised methods require manual lesion annotations for model development, while unsupervised deep learning methods such as generative adversarial networks do not. The aim of this study was to develop and evaluate a generative adversarial network to segment infarct and hemorrhagic stroke lesions on follow-up NCCT scans.
Materials And Methods:
Training data consisted of 820 patients with baseline and follow-up NCCT from 3 Dutch acute ischemic stroke trials. A generative adversarial network was optimized to transform a follow-up scan with a lesion to a generated baseline scan without a lesion by generating a difference map that was subtracted from the follow-up scan. The generated difference map was used to automatically extract lesion segmentations. Segmentation of primary hemorrhagic lesions, hemorrhagic transformation of ischemic stroke, and 24-hour and 1-week follow-up infarct lesions were evaluated relative to expert annotations with the Dice similarity coefficient, Bland-Altman analysis, and intraclass correlation coefficient.
Results:
The median Dice similarity coefficient was 0.31 (interquartile range, 0.08-0.59) and 0.59 (interquartile range, 0.29-0.74) for the 24-hour and 1-week infarct lesions, respectively. A much lower Dice similarity coefficient was measured for hemorrhagic transformation (median, 0.02; interquartile range, 0-0.14) and primary hemorrhage lesions (median, 0.08; interquartile range, 0.01-0.35). Predicted lesion volume and the intraclass correlation coefficient were good for the 24-hour (bias, 3 mL; limits of agreement, -64-59 mL; intraclass correlation coefficient, 0.83; 95% CI, 0.78-0.88) and excellent for the 1-week (bias, -4 m; limits of agreement,-66-58 mL; intraclass correlation coefficient, 0.90; 95% CI, 0.83-0.93) follow-up infarct lesions.
Conclusions:
An unsupervised generative adversarial network can be used to obtain automated infarct lesion segmentations with a moderate Dice similarity coefficient and good volumetric correspondence.
