Explainable brain tumor detection in skull base CT using continuous neural representations: comparative evaluation of neural fields, neural operators, and vision transformers.
Authors
Affiliations (13)
Affiliations (13)
- Ministry of National Education, Directorate General for Higher and Foreign Education, Ankara, Turkey. Electronic address: [email protected].
- Beykoz University, Vocational School, Big Data Analytics Program, Istanbul, Turkey. Electronic address: [email protected].
- Department of Artificial Intelligence and Data Engineering, Faculty of Engineering, Ankara University, Ankara 06100, Turkey. Electronic address: [email protected].
- Institute of Artificial Intelligence, Ankara University, Ankara 06100, Turkey. Electronic address: [email protected].
- Department of Biomedical Engineering, Ankara University, Ankara 06830, Turkey. Electronic address: [email protected].
- Department of Neurosurgery, Gamma Knife Unit, Faculty of Medicine, Gazi University, Ankara, Turkey. Electronic address: [email protected].
- Department of Management Science and Information Systems, Oklahoma State University, Stillwater 74078, OK, USA; Department of Management Information Systems, Faculty of Business Administration, Haliç University, 34060 Istanbul, Turkey. Electronic address: [email protected].
- TOBB University of Economics and Technology, Faculty of Medicine, Ankara, Turkey. Electronic address: [email protected].
- Denizli Private Oncology Center, Radiation Oncology Department, Denizli 09010, Turkey. Electronic address: [email protected].
- University of Wisconsin-Madison, Madison, WI, USA. Electronic address: [email protected].
- Gazi University, Faculty of Medicine, Department of Neurosurgery, Ankara, Turkey. Electronic address: [email protected].
- Gazi University, Faculty of Medicine, Department of Neurosurgery Medicine, Ankara, Turkey. Electronic address: [email protected].
- Department of Computer Engineering, Faculty of Engineering, Ankara University, Ankara 06100, Turkey. Electronic address: [email protected].
Abstract
Reliable brain tumor detection in CT remains challenging due to low soft-tissue contrast, skull base complexity, and imaging artifacts. This study evaluates whether continuous neural representation learning improves classification performance and interpretability for CT-based brain tumor detection. We performed a comparative evaluation of coordinate-based neural models, neural operators, and transformer-based vision models using a skull base CT dataset from Gazi University Faculty of Medicine. The dataset includes 200 patients and 40,000 slices (12,000 tumor-positive, 28,000 tumor-negative). An automated multi-stage slice selection framework was developed to extract three anatomically consistent skull base slices per patient using similarity-based ranking and anatomical validation. Ten models were evaluated, including Neural Fields, Implicit Neural Representations, DeepONet, HyperNetworks, FunCNets, Rational Neural Networks, Fourier Neural Networks, and ViT-Base/Small/Large. Neural Fields achieved the best performance with 98.90% accuracy, 98.90% sensitivity, 98.90% specificity, 0.978 MCC, and 0.990 AUC. FunCNets ranked second overall while DeepONet achieved the highest sensitivity but lower overall balance. Transformer-based models underperformed compared to neural representation approaches. Statistical analysis confirmed significant performance differences with Neural Fields significantly outperforming competing methods. LIME analysis showed that Neural Fields focused on clinically relevant lesion regions while reducing influence from skull base artifacts. Continuous neural representations, particularly Neural Fields, provide superior accuracy and robustness for CT-based brain tumor classification compared to transformer and operator-based models. The findings demonstrate that neural field-based learning offers both high diagnostic performance and improved interpretability, supporting its potential for clinical decision-support in challenging skull base CT analysis.