NeXtBrain: Combining local and global feature learning for brain tumor classification
Brain Research · 2025-09 · 1863 · 149762
DOI: 10.1016/j.brainres.2025.149762 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Research, 2025-09. Verfasst von Ishak Pacal und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Faculty of Engineering, Igdir University, 76000 Igdir, Turkey; Department of Electronics and Information Technolo…. Hauptthemen laut MEDLINE: Brain Neoplasms, Deep Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The accurate and timely diagnosis of brain tumors is of paramount clinical significance for effective treatment planning and improved patient outcomes. While deep learning has advanced medical image analysis, concurrently achieving high classification accuracy, robust generalization, and computational efficiency remains a formidable challenge. This is often due to the difficulty in optimally capturing both fine-grained local tumor features and their broader global contextual cues without incurring substantial computational costs. This paper introduces NeXtBrain, a novel hybrid architecture meticulously designed to overcome these limitations. NeXtBrain's core innovations, the NeXt Convolutional Block (NCB) and the NeXt Transformer Block (NTB), synergistically enhance feature learning: NCB leverages Multi-Head Convolutional Attention and a SwiGLU-based MLP to precisely extract subtle local tumor morphologies and detailed textures, while NTB integrates self-attention with convolutional attention and a SwiGLU MLP to effectively model long-range spatial dependencies and global contextual relationships, crucial for differentiating complex tumor characteristics. Evaluated on two publicly available benchmark datasets, Figshare and Kaggle, NeXtBrain was rigorously compared against 17 state-of-the-art (SOTA) models. On Figshare, it achieved 99.78 % accuracy and a 99.77 % F1-score. On Kaggle, it attained 99.78 % accuracy and a 99.81 % F1-score, surpassing leading SOTA ViT, CNN, and hybrid models. Critically, NeXtBrain demonstrates exceptional computational efficiency, achieving these SOTA results with only 23.91 million parameters, requiring just 10.32 GFLOPs, and exhibiting a rapid inference time of 0.007 ms. This efficiency allows it to outperform significantly larger models such as DeiT3-Base with 85.82 M parameters, Swin-Base with 86.75 M parameters in both accuracy and computational demand.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Engineering, Faculty of Engineering, Igdir University, 76000 Igdir, Turkey; Department of Electronics and Information Technologies, Faculty of Architecture and Engineering, Nakhchivan State Univer…
- Department of Computer Engineering, Faculty of Engineering, Igdir University, 76000 Igdir, Turkey. Electronic address: ozan.akhan@igdir.edu.tr.
- Department of Pediatric Hematology-Oncology, Istanbul Medeniyet University, Göztepe Prof. Dr. Süleyman Yalçın City Hospital, 34722 Istanbul, Turkey. Electronic address: rumeysatuna@gmail.com.
- Department of Industrial Engineering, Turkish Naval Academy, National Defence University, 34942 Tuzla, Istanbul, Türkiye; The Bartlett School of Sustainable Construction, University College London, London WC1E 6BT, UK;…
Zitieren
APA
Pacal, I., Akhan, O., Deveci, R. T., & Deveci, M. (2025). NeXtBrain: Combining local and global feature learning for brain tumor classification. Brain Research, 1863, 149762. https://doi.org/10.1016/j.brainres.2025.149762
Vancouver
Pacal I, Akhan O, Deveci RT, Deveci M. NeXtBrain: Combining local and global feature learning for brain tumor classification. Brain Research. 2025;1863:149762. doi:10.1016/j.brainres.2025.149762
BibTeX
@article{Pacal2025,
author = {Pacal, Ishak and Akhan, Ozan and Deveci, Rumeysa Tuna and Deveci, Muhammet},
title = {NeXtBrain: Combining local and global feature learning for brain tumor classification},
journal = {Brain Research},
year = {2025},
volume = {1863},
pages = {149762},
doi = {10.1016/j.brainres.2025.149762}
}
EUVIMED