Please use this identifier to cite or link to this item:
http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31914| Title: | Development and Implementation of Physics-Informed Segresnetunet for Brain Tumor Segmentation Using BRATS2020 Dataset |
| Authors: | Aaron, Aniebiet Dada, Michael Awojoyogbe, Bamidele Udeme, Iniobong Sanni, Henry Iorumbur, Moses Olasehinde, Emmanuel |
| Keywords: | Brain Tumor Segmentation Magnetic Resonance Imaging (MRI) Physics-Informed ResNetUNet Deep Learning U-Net ResNet Physics-Informed Machine Learning (PIML) Tumor Growth Modeling |
| Issue Date: | 20-Apr-2026 |
| Publisher: | Springer |
| Citation: | Aniebiet Aaron, Michael O. Dada, Bamidele O. Awojoyogbe, Iniobong N. Udeme, Henry A. Sanni, Moses A. Iorumbur, Emmanuel O. Olasehinde (2025). Development and Implementation of Physics-Informed Segresnetunet for Brain Tumor Segmentation Using BRATS2020 Dataset. Molecular Imaging and Biology 28 (Suppl 2), 224. |
| Series/Report no.: | Curriculum Vitae;36 |
| Abstract: | Accurate brain tumor segmentation is crucial for effective diagnosis and treatment planning in brain cancer cases. Traditional segmentation methods often fall short in capturing the complex nature of tumors. This study presents the Physics-InformedResNetUNet model, a deep learning framework that integrates a physics-informed layer simulating realistic tumor growth dynamics into U-Net's segmentation capabilities and ResNet's residual learning. The physics informed component models thectumor growth using simplified diffusion equations, reflecting how tumors evolve spatially over time, thereby enhancing the network's understanding of tumor morphology. |
| Description: | None |
| URI: | http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31914 |
| Appears in Collections: | Physics |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.