TY - JOUR
T1 - Unsupervised Deep Learning for Stroke Lesion Segmentation on Follow-up CT Based on Generative Adversarial Networks
AU - van Voorst, H.
AU - Konduri, P. R.
AU - van Poppel, L. M.
AU - van der Steen, W.
AU - van der Sluijs, P. M.
AU - Slot, E. M. H.
AU - Emmer, B. J.
AU - van Zwam, W. H.
AU - Roos, Y. B. W. E. M.
AU - Majoie, C. B. L. M.
AU - Zaharchuk, G.
AU - Caan, M. W. A.
AU - Marquering, H. A.
N1 - Funding Information: This study was funded by the CONTRAST consortium. The CONTRAST consortium acknowledges the support from the Netherlands Cardiovascular Research Initiative, an initiative of the Dutch Heart Foundation (CVON2015-01: CONTRAST) and from the Brain Foundation of the Netherlands (HA2015.01.06). The collaboration project is additionally financed by the Ministry of Economic Affairs by means of the Public-private partnerships Allowance made available by the Top Sector Life Sciences & Health to stimulate public-private partnerships (LSHM17016). This work was funded, in part, through unrestricted funding by Stryker, Medtronic, and Cerenovus. Publisher Copyright: © 2022 American Society of Neuroradiology. All rights reserved.
PY - 2022/8/1
Y1 - 2022/8/1
N2 - 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, -64-59mL; 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.
AB - 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, -64-59mL; 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.
UR - http://www.scopus.com/inward/record.url?scp=85136301527&partnerID=8YFLogxK
U2 - https://doi.org/10.3174/ajnr.A7582
DO - https://doi.org/10.3174/ajnr.A7582
M3 - Article
C2 - 35902122
SN - 0195-6108
VL - 43
SP - 1107
EP - 1114
JO - American journal of neuroradiology
JF - American journal of neuroradiology
IS - 8
ER -