Scholarlink

<p>This paper primarily focuses on enhancing brain tumor MRI images using dynamic stochastic resonance. The present method aims to enhance the noisy MRI images so that they will be helpful to clinical experts in drawing correct conclusions regarding illnesses with respect to unseen regions inside the body. Using the lifting wavelet transform, the image has been partitioned into three levels. Then, dynamic stochastic resonance is used by doing the tuning process on noisy images with higher frequency sub-bands to improve performance. An inverse transform is applied to reconstruct the image with new detail coefficients. Experimental outcomes are presented in the form of visual appearance, mean opinion score, and quantitative parameters to demonstrate the strength of the proposed method. PSNR, AMBE, PL, SSIM, and REC are used for quantitative study. The outcome of the results demonstrates that the suggested method is better than other state-of-the-art methods like morphological operators, HE, CLAHE, ADFA, and MGL.</p>

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

Enhancement of Medical Images Using Lifting Wavelet Transform and Dynamic Stochastic Resonance

  • 期刊论文

  • 发表日期：

    2025年2月20日

查看全文
  • Anuj Bhardwaj,
  • Ritesh Kumar Dubey,
  • Anjali Wadhwa

摘要

This paper primarily focuses on enhancing brain tumor MRI images using dynamic stochastic resonance. The present method aims to enhance the noisy MRI images so that they will be helpful to clinical experts in drawing correct conclusions regarding illnesses with respect to unseen regions inside the body. Using the lifting wavelet transform, the image has been partitioned into three levels. Then, dynamic stochastic resonance is used by doing the tuning process on noisy images with higher frequency sub-bands to improve performance. An inverse transform is applied to reconstruct the image with new detail coefficients. Experimental outcomes are presented in the form of visual appearance, mean opinion score, and quantitative parameters to demonstrate the strength of the proposed method. PSNR, AMBE, PL, SSIM, and REC are used for quantitative study. The outcome of the results demonstrates that the suggested method is better than other state-of-the-art methods like morphological operators, HE, CLAHE, ADFA, and MGL.