Gradient, Texture Driven Based Dynamic-Histogram Equalization For Medical Image Enhancement

In many clinical diagnostic measurements, medical images play some significant role but often suffer from various types of noise and low-luminance, which causes some notable changes in overall system accuracy with misdiagnosis rate. To improve the visual appearance of object regions in medical images, image enhancement techniques are used as potential pre-processing techniques. Due to its simplicity and easiness of implementation, histogram equalization is widely preferred in many applications. But due to its mapping function based image transformation during enhancement process affect the biomedical patterns which are essential for diagnosis. To mitigate these issues in medical images, a new method based on gradient computations and Texture Driven based Dynamic histogram equalization (GTDDHE) is accomplished to increase the visual perception. The spatial texture pattern is also included to ensure the texture retention and associated control over its variations during histogram modifications. Experimental results on MRI, CT images, eyes images from medical image datasets and quantitative analysis by PSNR, structural similarity index measurement (SSIM), information entropy (IE) and validated that the proposed method offers improved quality with maximum retention of biomedical patterns across all types of medical images.

Geometric Regularized Hopfield Neural Network for Medical Image Enhancement

One of the major shortcomings of Hopfield neural network (HNN) is that the network may not always converge to a fixed point. HNN, predominantly, is limited to local optimization during training to achieve network stability. In this paper, the convergence problem is addressed using two approaches: (a) by sequencing the activation of a continuous modified HNN (MHNN) based on the geometric correlation of features within various image hyperplanes via pixel gradient vectors and (b) by regulating geometric pixel gradient vectors. These are achieved by regularizing proposed MHNNs under cohomology, which enables them to act as an unconventional filter for pixel spectral sequences. It shifts the focus to both local and global optimizations in order to strengthen feature correlations within each image subspace. As a result, it enhances edges, information content, contrast, and resolution. The proposed algorithm was tested on fifteen different medical images, where evaluations were made based on entropy, visual information fidelity (VIF), weighted peak signal-to-noise ratio (WPSNR), contrast, and homogeneity. Our results confirmed superiority as compared to four existing benchmark enhancement methods.