Deep convolutional neural networks outperform vanilla machine learning when predicting language outcomes after stroke
Deep CNNs offer state of the art performance when predicting language outcomes after stroke, outperforming vanilla machine learning and obviating the need to post-process lesion images into lesion features.
Authors
- Howard Bowman (ORCID: https://orcid.org/0000-0003-4736-1869)
- Thomas M.H. Hope (ORCID: https://orcid.org/0000-0003-0714-8545)
- Alexander Leff (ORCID: https://orcid.org/0000-0002-0831-3541)
- C.J. Price (ORCID: https://orcid.org/0000-0001-7448-4835)
Institutions
- University College London (GB)
- John Cabot University (IT)
- University of Birmingham (GB)
Publication Details
- Journal
- NeuroImage Clinical
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1016/j.nicl.2025.103880
- Primary Topic
- Neurobiology of Language and Bilingualism
- Type
- article
- Field-Weighted Citation Impact
- 0.00