A Novel MRI-Based Deep Learning-Radiomics Framework for Evaluating Cerebrospinal Fluid Signal in Central Nervous System Infection

Ferhat Cüce¹Gokalp Tulum^2*Muhammed İkbal Işık¹Marziye Jalili³Güven Girgin⁴Ömer Karadaş¹Niray Baş¹Berza Özcan¹Ümit Savaşci¹Sena Şakir¹Akçay Övünç Karadaş¹Eda Teomete⁵Onur Osman²Jawad Rasheed^6,7,8

• ¹TC Saglik Bakanligi Ankara Gulhane Egitim ve Arastirma Hastanesi, Ankara, Türkiye
• ²Istanbul Topkapi Universitesi, Istanbul, Türkiye
• ³TC Uskudar Universitesi, Üsküdar, Türkiye
• ⁴TC Saglik Bakanligi Mugla Egitim ve Arastirma Hastanesi, Mugla, Türkiye
• ⁵University of Michigan, Ann Arbor, United States
• ⁶Istanbul Sabahattin Zaim Universitesi, Istanbul, Türkiye
• ⁷Istanbul Nisantasi Universitesi, Sarıyer, Türkiye
• ⁸Applied Science Private University, Amman, Jordan

Accurate and timely diagnosis of central nervous system infections (CNSIs) is critical, yet current goldstandard techniques like lumbar puncture (LP) remain invasive and prone to delay. This study proposes a novel noninvasive framework integrating handcrafted radiomic features and deep learning (DL) to identify cerebrospinal fluid (CSF) alterations on magnetic resonance imaging (MRI) in patients with acute CNSI. Fifty-two patients diagnosed with acute CNSI who underwent LP and brain MRI within 48 hours of hospital admission were retrospectively analyzed alongside 52 control subjects with normal neurological findings. CSF-related signals were segmented from the ventricular system and sublentiform nucleus parenchyma, including perivascular spaces (PVSs), using semi-automated methods on axial T2-weighted images. Two hybrid models (DenseASPP-RadFusion and MobileASPP-RadFusion), fusing radiomics and DL features, were developed and benchmarked against base DL architectures (DenseNet-201 and MobileNet-V3Large) via 5-fold nested cross-validation. Radiomics features were extracted from both original and Laplacian of Gaussian-filtered MRI data. In the sub-lentiform nucleus parenchyma, the hybrid DenseASPP-RadFusion model achieved superior classification performance (accuracy: 78.57 ± 4.76%, precision: 84.09 ± 3.31%, F1-score: 76.12 ± 6.86%), outperforming its corresponding base models. Performance was notably lower in ventricular system analyses across all models. Radiomics features derived from fine-scale filtered images exhibited the highest discriminatory power. A strict, clinically motivated patient-wise classification strategy confirmed the sub-lentiform nucleus region as the most reliable anatomical target for distinguishing infected from non-infected CSF. 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.