Open Access

ARTICLE

Enhancing Multi-Modality Medical Imaging: A Novel Approach with Laplacian Filter + Discrete Fourier Transform Pre-Processing and Stationary Wavelet Transform Fusion

by Mian Muhammad Danyal^1,2, Sarwar Shah Khan^3,4,*, Rahim Shah Khan⁵, Saifullah Jan², Naeem ur Rahman⁶

1 Department of Computer Science, Institute of Management Sciences, Peshawar, 25000, Pakistan
2 Department of Computer Science, City University of Science & Technology, Peshawar, 25000, Pakistan
3 Department of Computer Science, Iqra National University, Swat, 19200, Pakistan
4 Department of Computer Science and Software Technology, University of Swat, Swat, 19200, Pakistan
5 Department of Medical Science, Saidu Medical College, Swat, 19200, Pakistan
6 Department of Allied Health Science, Iqra National University, Swat, 19200, Pakistan

* Corresponding Author: Sarwar Shah Khan. Email:

Journal of Intelligent Medicine and Healthcare 2024, 2, 35-53. https://doi.org/10.32604/jimh.2024.051340

Received 03 March 2024; Accepted 28 May 2024; Issue published 08 July 2024

Abstract

Multi-modality medical images are essential in healthcare as they provide valuable insights for disease diagnosis and treatment. To harness the complementary data provided by various modalities, these images are amalgamated to create a single, more informative image. This fusion process enhances the overall quality and comprehensiveness of the medical imagery, aiding healthcare professionals in making accurate diagnoses and informed treatment decisions. In this study, we propose a new hybrid pre-processing approach, Laplacian Filter + Discrete Fourier Transform (LF+DFT), to enhance medical images before fusion. The LF+DFT approach highlights key details, captures small information, and sharpens edge details, effectively identifying meaningful discontinuities and modifying image frequencies from low to high. The sharpened images are then fused using the Stationary Wavelet Transform (SWT), an advanced technique. Our primary objective is to improve image clarity and facilitate better analysis, diagnosis, and decision-making in healthcare. We evaluate the performance of the resultant images both visually and statistically, comparing the novel SWT (LF+DFT) approach with baseline techniques. The proposed approach demonstrates superior results on both breast and brain datasets, with evaluation metrics such as Root Mean Square Error (RSME), Percentage Fit Error (PFE), Mean Absolute Error (MAE), Entropy, and Signal-to-Noise Ratio (SNR) confirming its effectiveness. The technique aims to enhance image quality, enable better medical analysis, and outperform existing fusion methods. In conclusion, our proposed LF+DFT approach followed by SWT fusion shows promising results for enhancing multi-modality medical images, which could significantly impact medical diagnosis and treatment in the future.

---

Keywords

---