A novel MRI-based deep learning–radiomics framework for evaluating cerebrospinal fluid signal in central nervous system infection
This study introduces a robust and interpretable MRI-based deep learning-radiomics pipeline for CNSI classification, with promising diagnostic potential. The proposed framework may offer a noninvasive alternative to LP in selected cases, particularly by leveraging CSF signal alterations in PVS-adjacent parenchymal regions. These findings establish a foundation for future multicenter validation and integration into clinical workflows.
Authors
- Gökalp Tulum (ORCID: https://orcid.org/0000-0003-1906-0401)
- Nuri Serdar Baş (ORCID: https://orcid.org/0000-0003-1625-4868)
- Onur Osman (ORCID: https://orcid.org/0000-0001-7675-7999)
- Ömer Karadaş (ORCID: https://orcid.org/0000-0003-0457-3722)
- Ümit Savaşçı (ORCID: https://orcid.org/0000-0003-3663-2053)
- Meltem Isik
- Ferhat Cüce (ORCID: https://orcid.org/0000-0003-1831-3868)
- Jawad Rasheed (ORCID: https://orcid.org/0000-0003-3761-1641)
- Burcu Özcan (ORCID: https://orcid.org/0000-0002-9893-085X)
- Güven Girgin (ORCID: https://orcid.org/0000-0002-6077-9824)
- Akçay Övünç Karadaş
- Mehrdad Jalili
- Sena Şakir
- Eda Teomete
Institutions
- İstanbul Sabahattin Zaim Üniversitesi (TR)
- Üsküdar University (TR)
- Applied Science Private University (JO)
- University of Health Science (KH)
- University of Michigan (US)
- İstanbul Nişantaşı Üniversitesi (TR)
- Istanbul Medipol University (TR)
- Psychiatric Association of Turkey (TR)
- Türkisch-Deutsche Universität (TR)
- Sağlık Bilimleri Üniversitesi (TR)
- Muğla University (TR)
- University of Health Sciences Antigua (AG)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-08-20
- DOI
- https://doi.org/10.3389/fmed.2025.1659653
- Citations
- 1
- Primary Topic
- Infectious Diseases and Tuberculosis
- Type
- article
- Field-Weighted Citation Impact
- 2.01