Contrast enhancement is essential in brain magnetic resonance (MR) images to improve the visibility and clarity of anatomical structures and pathological features. This paper introduces a novel approach for enhancing image contrast, specifically targeting brain MR images. The method employs an amalgamation of four innovative transformation functions, governed by nine parameters dependent on the structural intricacies of the input image. The proposed transformation functions are designed to effectively enhance contrast while preserving crucial image details. Genetic algorithm optimization is utilized to determine the optimal values of these transformation function parameters. Enriched performance of the proposed approach is justified by rigorous comparison with state-of-the-art contrast enhancement techniques. The proposed algorithm achieves an 11% increase in PSNR, a 42.6% decrease in RMSE, and double the IEF values compared to the next best state-of-the-art method.

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

Brain MRI Contrast Enhancement Using Novel Transformation Function Optimized by Genetic Algorithm

  • Arinjay Bhowmick,
  • Soham Ghosh,
  • Prattay Paul,
  • Amiya Halder

摘要

Contrast enhancement is essential in brain magnetic resonance (MR) images to improve the visibility and clarity of anatomical structures and pathological features. This paper introduces a novel approach for enhancing image contrast, specifically targeting brain MR images. The method employs an amalgamation of four innovative transformation functions, governed by nine parameters dependent on the structural intricacies of the input image. The proposed transformation functions are designed to effectively enhance contrast while preserving crucial image details. Genetic algorithm optimization is utilized to determine the optimal values of these transformation function parameters. Enriched performance of the proposed approach is justified by rigorous comparison with state-of-the-art contrast enhancement techniques. The proposed algorithm achieves an 11% increase in PSNR, a 42.6% decrease in RMSE, and double the IEF values compared to the next best state-of-the-art method.