Outcome Prediction Based on Automatically Extracted Infarct Core Image Features in Patients with Acute Ischemic Stroke

Manon L. Tolhuisen*, Jan W. Hoving, Miou S. Koopman, Manon Kappelhof, Henk van Voorst, Agnetha E. Bruggeman, Adam M. Demchuck, Diederik W.J. Dippel, Bart J. Emmer, Serge Bracard, Francis Guillemin, Robert J. van Oostenbrugge, Peter J. Mitchell, Wim H. van Zwam, Michael D. Hill, Yvo B.W.E.M. Roos, Tudor G. Jovin, Olvert A. Berkhemer, Bruce C.V. Campbell, Jeffrey SaverPhil White, Keith W. Muir, Mayank Goyal, Henk A. Marquering, Charles B. Majoie, Matthan W.A. Caan, CLEAN NO IV and HERMES investigators on behalf of the

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

8 Citations (Scopus)
26 Downloads (Pure)

Abstract

Infarct volume (FIV) on follow-up diffusion-weighted imaging (FU-DWI) is only moderately associated with functional outcome in acute ischemic stroke patients. However, FU-DWI may contain other imaging biomarkers that could aid in improving outcome prediction models for acute ischemic stroke. We included FU-DWI data from the HERMES, ISLES, and MR CLEAN-NO IV databases. Lesions were segmented using a deep learning model trained on the HERMES and ISLES datasets. We assessed the performance of three classifiers in predicting functional independence for the MR CLEAN-NO IV trial cohort based on: (1) FIV alone, (2) the most important features obtained from a trained convolutional autoencoder (CAE), and (3) radiomics. Furthermore, we investigated feature importance in the radiomic-feature-based model. For outcome prediction, we included 206 patients: 144 scans were included in the training set, 21 in the validation set, and 41 in the test set. The classifiers that included the CAE and the radiomic features showed AUC values of 0.88 and 0.81, respectively, while the model based on FIV had an AUC of 0.79. This difference was not found to be statistically significant. Feature importance results showed that lesion intensity heterogeneity received more weight than lesion volume in outcome prediction. This study suggests that predictions of functional outcome should not be based on FIV alone and that FU-DWI images capture additional prognostic information.

Original languageEnglish
Article number1786
JournalDiagnostics
Volume12
Issue number8
DOIs
Publication statusPublished - 23 Jul 2022

Bibliographical note

Funding Information:
The CONTRAST consortium is supported by the Netherlands Cardiovascular Research Initiative (CVON), an initiative of the Dutch Heart Foundation, and by the Brain Foundation Netherlands, Medtronic, and Cerenovus. AMC and Erasmus MC received additional unrestricted funding on behalf of CONTRAST for the execution of MR CLEAN-NO IV from Stryker European Operations BV.

Publisher Copyright:
© 2022 by the authors.

Fingerprint

Dive into the research topics of 'Outcome Prediction Based on Automatically Extracted Infarct Core Image Features in Patients with Acute Ischemic Stroke'. Together they form a unique fingerprint.

Cite this