کنفرانس بین المللی محاسبات نرم

صفحه اصلی / ششمین کنفرانس بین المللی محاسبات نرم

EARLY DETECTION OF ASYMPTOMATIC BRAIN TUMORS USING AI : A RADIOMICS-DRIVEN CASE STUDY

نویسندگان :

Melika Mahboobi fard¹ Abdorreza Hesam Mohseni²

1- 'دانشگاه گیلان - دانشکده فنی و مهندسی شرق گیلان 2- 'دانشگاه گیلان - دانشکده فنی و مهندسی شرق گیلان

کلمات کلیدی :

Brain Tumor

چکیده :

Early detection of asymptomatic brain tumors is vital for improving survival rates, yet conventional MRI analysis often fails to identify subtle abnormalities in early stages. This study presents an artificial intelligence (AI)-driven radiomics framework for automated and non-invasive detection of early brain tumors. Radiomic features—including statistical, shape, and texture descriptors—were extracted from MRI datasets such as BraTS and analyzed using deep learning architectures to identify subtle tumor-related biomarkers invisible to the human eye. Results indicate that integrating radiomic feature engineering with deep neural models significantly improves sensitivity and specificity for early tumor detection. Key features such as entropy, contrast, and homogeneity provided strong discriminative power between normal and early pathological tissue. Furthermore, Vision Transformer–based hybrids and self-supervised learning approaches enhanced model generalizability across diverse MRI protocols. This research demonstrates the transformative role of AI in neuro-oncology, offering a foundation for multimodal and radiogenomic integration. The proposed framework supports early, personalized, and non-invasive brain tumor diagnosis, contributing to the future of precision neuro-oncology and proactive brain health monitoring.