Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : CogITo Smart Journal

Neural Dynamic Network for Brain Tumor Classification: An Attention-Based Feature Selection Approach Naseer, Muchammad; Agustina, Nova; Gusdevi, Harya; Riyanti, Niken
CogITo Smart Journal Vol. 11 No. 2 (2025): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v11i2.989.430-446

Abstract

Magnetic Resonance Imaging (MRI) plays a vital role in the early detection of brain tumors. However, standard Convolutional Neural Network (CNN) models often struggle to extract truly relevant features from complex MRI structures. This limitation creates a gap in achieving robust and clinically interpretable classifications, as feature redundancy and weak attention toward tumor-specific regions may reduce diagnostic reliability. To address this gap, this study introduces a Neural Dynamic Network (NDN) that integrates EfficientNetV2S with a dynamic attention-based mechanism to adaptively highlight informative features while suppressing noise. The proposed model was evaluated using a 5-fold cross-validation scheme and tested on unseen data. Compared with the baseline CNN, the NDN consistently demonstrated higher accuracy, precision, recall, and F1-score across folds and final testing, reflecting improved robustness and balanced sensitivity. NDN yielded significant improvements, with the 5-fold validation averaging an accuracy of 88.44%, a precision of 87.84%, a recall of 87.88%, and an F1-score of 87.82%.  Beyond numerical performance, interpretability analysis utilizing Grad-CAM demonstrated that NDN generates more concentrated and clinically consistent heatmaps. In contrast, the baseline CNN produced dispersed activations that exhibited less alignment with tumor regions. Overall, the findings confirm that incorporating a dynamic attention-based mechanism substantially enhances both feature selection and visual interpretability. This makes the NDN architecture more reliable for MRI-based brain tumor classification and highly suitable as a decision-support tool in clinical workflows.
Co-Authors A.A. Ketut Agung Cahyawan W Abdul Fatah Adhe Setya Pramayoga, Adhe Setya Agus Benny Setiawan, Agus Benny Agustina, Nova Alfian Ma’arif Aprilia Yustika Dewi, Aprilia Ariansyah Fadillah Arifman Arifman, Arifman Bagus Pribadi Dedy Panji Agustino Dedy Panji Agustino, Dedy Panji Dedy Panji Agustino,S.Kom, Dedy Panji Deni Rinaldi Dimas Herjuno Eucharistia Theopilia Letedara, Eucharistia Theopilia Eva Istiana Dewi, Eva Istiana Fahmi Abdullah, Fahmi Gusdevi, Harya Guterres, Antonio Hadhiwibowo, Ari I Gede Adhi Pradana, I Gede Adhi I Gede Harsemadi I Gede Muriarka, S.Kom, I Gede I Gede Pande Pratama Setiadarma, I Gede Pande Pratama I Gede Suardika I Gusti Ngurah Wikranta Arsa, I Gusti Ngurah I Komang Try Adi Stanaya, I Komang Try Adi I Made Budi Adnyana, I Made I Nyoman Kusuma Wardana I Putu Agus Suyasa Ida Bagus Ketut Surya Arnawa, Ida Bagus Ketut Surya Ihsan, Candra Nur Jaelani, Widi Linggih Kristian Ismail Made Indirayani, Made Muhamad Sabar Muhammad Fadhil Muttaqin Mukadar Mukadar Mukadar Mukadar, Mukadar Mutoffar, Muhamad Malik Naser Jawas, Naser Ni Kadek Nuning Pratiwi, Ni Kadek Ni Made Prabasari, Ni Made Ni Putu Christine Arnawati, Ni Putu Christine Nova Agustina Nova Agustina Padma Nyoman Crisnapati Padma Nyoman Krisnapati, Padma Nyoman Purwono, Purwono Putu Sinta Puspadewi, Putu Sinta Qazi Mazhar ul Haq Rahayudin, Rahayudin Ririn Ramadhani, Ririn Risandi, Risal Riyanti, Niken Rosalia Hadi Rusdi, Jack Febrian Satrya Flymertho Luik, Satrya Flymertho Shinta Wulandari, Shinta Tatang Bukhori Triana Wasitama Putra, Triana Wahyu Rahmaniar Yanto Yanto