Nonsubsampled rotated complex wavelet transform (NSRCxWT) for medical image fusion related to clinical aspects in neurocysticercosis. (1st February 2017)

• Record Type: Journal Article
• Authors: Chavan, Satishkumar S.; Mahajan, Abhishek; Talbar, Sanjay N.; Desai, Subhash; Thakur, Meenakshi; D'cruz, Anil
• Is Part Of: Computers in biology and medicine. Volume 81(2017)
• Page Start: 64
• Page End: 78
• Publication Date: 2017-02-01
• Subjects: Neurocysticercosis -- Multimodality Medical Image Fusion -- Dual Tree Complex Wavelet Transform -- Nonsubsampled Rotated Complex Wavelet Transform -- Fusion Performance Metrics -- Rotated Wavelet Filter Bank; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2016.12.006
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Neurocysticercosis (NCC) is a parasite infection caused by the tapeworm Taenia solium in its larvae stage which affects the central nervous system of the human body (a definite host). It results in the formation of multiple lesions in the brain at different locations during its various stages. During diagnosis of such symptomatic patients, these lesions can be better visualized using a feature based fusion of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). This paper presents a novel approach to Multimodality Medical Image Fusion (MMIF) used for the analysis of the lesions for the diagnostic purpose and post treatment review of NCC. The MMIF presented here is a technique of combining CT and MRI data of the same patient into a new slice using a Nonsubsampled Rotated Complex Wavelet Transform (NSRCxWT). The forward NSRCxWT is applied on both the source modalities separately to extract the complementary and the edge related features. These features are then combined to form a composite spectral plane using average and maximum value selection fusion rules. The inverse transformation on this composite plane results into a new, visually better, and enriched fused image. The proposed technique is tested on the pilot study data sets of patients infected with NCC. The quality of these fused images is measured using objective and subjective evaluation metrics. Objective evaluation is performed by estimating the fusion parameters like entropy, fusion factor, image quality index, edge quality measure, mean structural similarity index measure, etc. The fused images are also evaluated for their visual quality using subjective analysis with the help of three expert radiologists. The experimental results on 43 image data sets of 17 patients are promising and superior when compared with the state of the art wavelet based fusion algorithms. The proposed algorithm can be a part of computer-aided detection and diagnosis (CADD) system which assists the radiologists in clinical practices. Abstract : Graphical abstract: Abstract : Highlights: The paper presents a novel approach to medical image fusion using nonsubsampled rotated complex wavelet transform (NSRCxWT). The approach aids the radiologist for better visualization of lesions in central nervous system due to neurocysticercosis (NCC). The fusion of CT and MRI images of the patient diagnosed with NCC highlights the stages of the disease prominently in the fused image. The visual quality of the fused images is validated by radiologists and estimating fusion metrics. The fused images using NSRCxWT are visually superior compared to the state of the art wavelet based fusion techniques.