Entropy maximization based segmentation, transmission and Wavelet Fusion of MRI images

Abstract

A method of progressive transmission of Magnetic Resonance Image with lesions over long distances is proposed. The Magnetic Resonance Images at the transmitter end are segregated on the basis of presence of lesions. Entropy Maximization using Hybrid Particle Swarm Optimization algorithm that incorporates a Wavelet theory based mutation operation is used for segmentation of Magnetic Resonance Images. It applies the Multi-resolution Wavelet theory to overcome the stagnation phenomena of the Particle Swarm Optimization. Thus the segmentation algorithm using Hybrid Particle Swarm Algorithm explores the solution space more effectively for a better solution. Varying percentages of Discrete Cosine Transform coefficients of segmented Magnetic Resonance Images are used for progressive image transmission. For a particular image data, the progressively received images are of different resolutions. At the receiver's end the progressively received images of different resolutions are fused using Multi-resolution wavelet analysis to get a visually suitable image for diagnosis. The doctor or a radiologist identifies a particular class of image with lesions and may ask for the entire un-segmented Magnetic Resonance Image dataset of a particular patient for further diagnosis. The proposed system helps to reduce the load on the system by choosing not to transmit the Magnetic Resonance Images without lesions.

Brain MRI segmentation for tumor detection using Grammatical Swarm based clustering algorithm

“…A. De et al [4], [5] used hybrid particle swarm optimization with wavelet mutation based segmentation for Brain MRI. In these methods entropy based maximization is used to select proper threshold values.…”

“…It is also very important in the progressive transmission [4], [5] of images. In progressive transmission, only the segmented MRI of patients having any lesion or tumor is transmitted whereas segmented images having no lesion or tumor are transmitted only on demand to reduce the effective load of the transmitter as stated in articles [4], [5]. Brain MR images have maximum seven classes or objects [6]:(i)background, (ii)cerebrospinal fluid(CSF), (iii)white matter, (iv)gray matter, (v)bone, (vi)scalp and (vii)lesion or tumor(if present).…”

“…Therefore, it is an important tool for the effective diagnosis, treatment and monitoring of the brain disease [1]. It is also very important in the progressive transmission [4], [5] of images. In progressive transmission, only the segmented MRI of patients having any lesion or tumor is transmitted whereas segmented images having no lesion or tumor are transmitted only on demand to reduce the effective load of the transmitter as stated in articles [4], [5].…”

“…In this work, only noise is removed from MR images using Discrete Wavelet Transform(DWT) [9] based de-noising technique. DWT based de-noising technique Soft Thresholding [10] was widely used for de-noising the MR images [4], [5]. First, image is decomposed at level j using DWT in the subbands (LL j , LH j , HL j , HH j ).…”

Grammatical Swarm based Segmentation Methodology for Lesion Segmentation in Brain MRI

“…A. De et al [3,4] used hybrid particle swarm optimization with wavelet mutation based segmentation for brain MRI. In these methods entropy based maximization is used to select proper threshold values for segmentation of the images.…”