Scholarlink

Medical image fusion is the process to enhance the image quality for clinically identification of disease and better treatment planning. The multimodal medical image modalities are MRI (magnetic resonance imaging), PET (positron emission tomography), and SPECT (single-photon emission computed tomography). In this article, we presented a new approach of fusion technology based on homomorphic filtering in transform domain. In the first phase, color images were changed into HSV color modal. Then, apply the homomorphic filter to MRI and intensity component (V) images for noise removal and quality enhancement. In the second phase, those images were decomposed into low and high coefficients. In the third phase, perform the fusion rules, namely spatial frequency for low frequency and visibility for high frequency components, respectively, which highlights the quality and edge details of the coefficients. In the last phase, an inverse transform is performed to get a quality fused image without distortion. The presented work was tested on two medical datasets, and its quality was assessed with five different performance parameters; it shows the better results over the other existing techniques.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fusion of Multimodal Medical Images in Transform Domain Using Homomorphic Filtering and Statistical Fusion Rules

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Haribabu Maruturi,
  • Hima Bindu,
  • Elamaran Elangovan,
  • Murali,
  • Shyamala Anto Mary,
  • Srinivasulu Rami Reddy

摘要

Medical image fusion is the process to enhance the image quality for clinically identification of disease and better treatment planning. The multimodal medical image modalities are MRI (magnetic resonance imaging), PET (positron emission tomography), and SPECT (single-photon emission computed tomography). In this article, we presented a new approach of fusion technology based on homomorphic filtering in transform domain. In the first phase, color images were changed into HSV color modal. Then, apply the homomorphic filter to MRI and intensity component (V) images for noise removal and quality enhancement. In the second phase, those images were decomposed into low and high coefficients. In the third phase, perform the fusion rules, namely spatial frequency for low frequency and visibility for high frequency components, respectively, which highlights the quality and edge details of the coefficients. In the last phase, an inverse transform is performed to get a quality fused image without distortion. The presented work was tested on two medical datasets, and its quality was assessed with five different performance parameters; it shows the better results over the other existing techniques.