Machine and deep learning technologies, mining imaging, and clinical information have made outstanding progress in the understanding, diagnosis, and prognosis of stroke patients. State of the art approaches are capable of extracting, combining, and exploiting novel data representations and inference methods to leverage prediction performance in many stroke applications. Data availability and curation, and effective ways to leverage longitudinal and sparse information are among the important areas requiring further interdisciplinary research.
In this Research Topic, we call for papers tackling challenges associated with data handling and its exploitation towards accurate and robust machine and deep learning systems for stroke imaging and stroke recovery prediction. Particularly, we welcome groups to submit novel scientific contributions utilizing clinical and/or neurological parameters obtained via machine and deep learning technologies, as well as novel machine and deep learning methodologies for stroke imaging applications, ranging from diagnosis, disease quantification, disease evolution, personalized stroke rehabilitation, and outpatient triaging.
Areas of interest include, but are not limited to the following:
• Classification/outcome prediction employing machine/deep learning technologies to clinical findings for information extraction and hypothesis testing.
• Novel machine/deep learning stroke neuroimaging methodologies for lesion quantification, decision support, and outcome prediction.
• Longitudinal stroke neuroimaging analysis.
• Multiomics stroke analysis, combining clinical, paraclinical, and imaging information.
• Personalized neuroimaging stroke rehabilitation technologies.
• Interhospital LVO triage.
• Image-based recovery assessment & treatment
The Editors would like to receive clinical, methodological, or translational research, in the form of Original Research, Opinions, Perspectives, or Reviews.
Machine and deep learning technologies, mining imaging, and clinical information have made outstanding progress in the understanding, diagnosis, and prognosis of stroke patients. State of the art approaches are capable of extracting, combining, and exploiting novel data representations and inference methods to leverage prediction performance in many stroke applications. Data availability and curation, and effective ways to leverage longitudinal and sparse information are among the important areas requiring further interdisciplinary research.
In this Research Topic, we call for papers tackling challenges associated with data handling and its exploitation towards accurate and robust machine and deep learning systems for stroke imaging and stroke recovery prediction. Particularly, we welcome groups to submit novel scientific contributions utilizing clinical and/or neurological parameters obtained via machine and deep learning technologies, as well as novel machine and deep learning methodologies for stroke imaging applications, ranging from diagnosis, disease quantification, disease evolution, personalized stroke rehabilitation, and outpatient triaging.
Areas of interest include, but are not limited to the following:
• Classification/outcome prediction employing machine/deep learning technologies to clinical findings for information extraction and hypothesis testing.
• Novel machine/deep learning stroke neuroimaging methodologies for lesion quantification, decision support, and outcome prediction.
• Longitudinal stroke neuroimaging analysis.
• Multiomics stroke analysis, combining clinical, paraclinical, and imaging information.
• Personalized neuroimaging stroke rehabilitation technologies.
• Interhospital LVO triage.
• Image-based recovery assessment & treatment
The Editors would like to receive clinical, methodological, or translational research, in the form of Original Research, Opinions, Perspectives, or Reviews.