Multi-Modal Feature Extraction Network for Medical Image Fusion

Abstract

Medical image fusion is to synthesize multiple medical images from single or different imaging devices. This paper aims to improve imaging quality with accurate preserving for accurate diagnosis and treatment. This work plays an important role in the fields of surgical navigation, routine staging, and radio-therapy planning of malignant disease. Nowadays, computerized tomography (CT), magnetic resonance imaging (MRI), single-photo emission computed tomography (SPECT) modalities, and positron emission tomography (PET) are focused using medical image fusion. Bones and implants are clearly reflected by CT Image. High-resolution anatomical details for soft tissues are recorded using MRL images. However, the MRI image is not sensitive to the diagnosis of fractures compared to CT image. SPECT image is utilized to study the blood flow of tissues and organs by nuclear imaging technique. Our proposed work is Multi-Modal Based Medical Image fusion for directly learning image features from original images. Medical image fusion is a powerful tool that enhances the clinical value of individual imaging modalities, leading to better patient outcomes. As imaging technology advances and computational techniques evolve, the role of image fusion in modern medicine continues to grow.