A Novel Brain Tumor Detection and Coloring Technique from 2D MRI Images

The early automated identification of brain tumors is a difficult task in MRI images. For a long time, continuous research efforts have floated a new idea of replacing different grayscale anatomic regions of diagnostic images with appropriate colors that could overcome the problems being faced by ra...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2022-06, Vol.12 (11), p.5744
Main Authors: Haq, Inayatul, Ullah, Najib, Mazhar, Tehsen, Malik, Muhammad Amir, Bano, Iqra
Format: Article
Language:English
Subjects:
Algorithms
Alzheimer's disease
Automation
Biopsy
Brain cancer
Brain research
brain tumor detection
Brain tumors
Color imagery
Colorization
Gray scale
grayscale conversion
Image contrast
Image enhancement
Image processing
Magnetic resonance imaging
Medical imaging
Optimization techniques
Pixels
PSNR
Radiation
Spectrum analysis
SSIM
Surgery
Tomography
tumor identification
tumor segmentation
Tumors
X-rays
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:The early automated identification of brain tumors is a difficult task in MRI images. For a long time, continuous research efforts have floated a new idea of replacing different grayscale anatomic regions of diagnostic images with appropriate colors that could overcome the problems being faced by radiologists. The colorization of grayscale images is challenging for enhancing various regions’ contrasts by transforming grayscale images into high-contrast color images. This study investigates standard solutions in discriminating between normal and abnormal regions by assigning colors to grayscale human brain MR images to differentiate different kinds of tissues. The proposed approach is influenced by connected component and index-based colorization methods for applying colors to different regions and abnormal areas. It is an automated approach that varies its inputs using luminance and pixel matrix values and provides the possible outcome. After segmentation, a specific algorithm is devised to colorize the region-of-interest (ROI) areas, which distinguishes and applies colors to differentiate the regions. Results show that implementing the watershed-based area segmentation method and ROI selection method based on the morphological operation helps identify tissues during processing. Moreover, the colorization approach based on luminance and pixel matrix after segmentation and ROI selection is beneficial due to better PSNR and SSIM values and visible contrast improvement. Our proposed algorithm works with less processing overhead and uses less time than those of the industry’s previously used color transfer method.
ISSN:2076-3417
2076-3417
DOI:10.3390/app12115744