Fuzzy Gray Level Difference Histogram Equalization for Medical Image Enhancement

Contrast enhancement methods are used to reduce image noise and increase the contrast of structures of interest. In medical images where the distinction between normal and abnormal tissue is subtle, accurate interpretation may become difficult if noise levels are relatively high. To provide accurate...

Full description

Saved in:
Bibliographic Details
Published in:Journal of medical systems 2020-06, Vol.44 (6), p.103-103, Article 103
Main Authors: Subramani, Bharath, Veluchamy, Magudeeswaran
Format: Article
Language:English
Subjects:
Algorithms
Data Interpretation, Statistical
Diagnostic Imaging - methods
Equalization
Health Informatics
Health Sciences
Histograms
Humans
Image & Signal Processing
Image contrast
Image enhancement
Image Enhancement - methods
Mathematical analysis
Medical imaging
Medicine
Medicine & Public Health
Noise
Noise levels
Noise reduction
Pattern Recognition, Automated - methods
Radiographic Image Enhancement - methods
Radiographic Image Interpretation, Computer-Assisted - methods
Statistics for Life Sciences
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Contrast enhancement methods are used to reduce image noise and increase the contrast of structures of interest. In medical images where the distinction between normal and abnormal tissue is subtle, accurate interpretation may become difficult if noise levels are relatively high. To provide accurate interpretation and clearer image for the observer with reduced noise levels “a novel adaptive fuzzy gray level difference histogram equalization algorithm” is proposed. At first, gray level difference of an input image is calculated using the binary similar patterns. Then, the gray level differences are fuzzified in order to deal the uncertainties present in the input image. Following the fuzzification, fuzzy gray level difference clip limit is computed to control the insignificant contrast enhancement. Finally, a fuzzy clipped histogram is equalized to obtain the contrast-enhanced MR medical image. The proposed algorithm is analysed both visually and analytically to calculate its performance against the other existing algorithms. Visual and analytical results on various test images affirm that the proposed algorithm outperforms all other existing algorithms and provide a clear path to analyse the fine details and infected portions effectively.
ISSN:0148-5598
1573-689X
DOI:10.1007/s10916-020-01568-9