Diagnostics, Volume 13, Issue 24
2023 December-2 - 92 articles
Cover Story: Accurately predicting stroke recovery outcomes, measured by the modified Rankin Scale (mRS), from brain CT scans remains challenging yet clinically valuable. We tested deep learning models to predict a patient's mRS at 3 months post-stroke. We experimented with image-only models that make predictions directly from CT scans, and hybrid models that incorporate clinical and demographic information along with imaging data. In the hybrid models, we first extracted quantitative imaging biomarkers reflective of stroke damage from CT scans using deep learning. These imaging features were then incorporated into prognostic machine learning models for making outcome predictions. This approach could help address the challenges faced by image-only approach and also make the resulting model more interpretable. View this paper - Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
