In Press                   Back to the articles list | Back to browse issues page

XML Print

Image Fusion using Bio-Inspired Neural P Systems and Non-Subsampled Shearlet Transform for Improved Diagnosis of Brain Tumors
Ch Suryababu , B Vijaya , Arempula Sreenivasa Rao , G Sattibabu , R Rambabu , K Ravi Kumar
Abstract:   (104 Views)
Diagnostic image fusion across multiple modalities integrates diverse images, making it a crucial tool for improved diagnosis. To achieve the best fusion outcomes between MRI and PET brain images, the study presents an enhanced image fusion strategy that combines Spiking Neural P Systems with Non-subsampled Shearlet Transform (NSST). The proposed system first decomposes images into low-frequency and high-frequency regions by applying NSST and employs dynamic threshold neural P (DTNP) systems for high-frequency fusion and Coupled Neural P (CNP) systems for low-frequency fusion. Through practical testing of 48 pairs of PET and MRI related to various disorders of the brain, it is demonstrated that the suggested strategy outperforms seven popular fusion techniques, such as neuro-fuzzy and CNN-based models. It provides an Improvement in Structural Similarity Index (SSIM) and entropy by 23.8%, 17.6% respectively, compared to existing methods. Our approach helps medical practitioners make better decisions by producing precise observations about brain tumors, neurodegenerative disorders, and Alzheimer's disease. This contemporary fusion technique enhances the clinical interpretation and noticeable quality of fused images, leading to improved medical imaging capabilities.
Keywords: image fusion, Spiking Neural P System, Non-subsampled Shearlet Transform, Coupled Neural P, dynamic threshold neural P, brain tumors, neurodegenerative disorders, Alzheimer's disease
Full-Text [PDF 1817 kb]   (63 Downloads)    
Type of Study: Research Paper | Subject: Biomedical Signal & Image Processing
Received: 2025/06/12 | Revised: 2026/05/29 | Accepted: 2026/02/16
Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Creative Commons License
© 2022 by the authors. Licensee IUST, Tehran, Iran. This is an open access journal distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.