Scribd
Upload
7 views

Introduction

The document discusses noise in medical images and how it can hinder diagnosis and require denoising techniques. It introduces sparse coding as a promising denoising method that leverages sparsity to distinguish noise from the underlying signal, removing noise while preserving details. Studies have shown sparse coding achieves superior denoising compared to traditional methods for X-rays, MRIs, and CT scans.

Uploaded by

Mohamed Karam
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
7 views

Introduction

The document discusses noise in medical images and how it can hinder diagnosis and require denoising techniques. It introduces sparse coding as a promising denoising method that leverages sparsity to distinguish noise from the underlying signal, removing noise while preserving details. Studies have shown sparse coding achieves superior denoising compared to traditional methods for X-rays, MRIs, and CT scans.

Uploaded by

Mohamed Karam
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Introduction

Due to the influence of imaging mechanism, external signal interference, signal attenuation in
the transmission process, and other factors, medical images are doped with noise.
Medical imaging including X-rays, Magnetic Resonance Imaging (MRI), Computer Tomography
(CT), ultrasound etc. are susceptible to noise.
Over 360 million medical imaging examinations are performed annually in the United States
alone, with each image susceptible to noise. (Source: American College of Radiology).
Medical imaging is affected by system requirements, patient comfort, and other practical factors,
so the image acquisition should be completed in a short time. However, increased efficiency
comes at a cost. The image clarity is reduced, the image details are not prominent, and the visual
effect of the image is reduced, which increases the difficulty of the image analysis by doctors.
Noise in medical images can significantly hinder the visibility of critical anatomical structures
like tumors, fractures, or blood vessels. This can lead to misdiagnosis rates rising, potentially
delaying or leading to incorrect treatment decisions with severe consequences for patient health
and well-being.
Computer-aided analysis and quantitative measurements become difficult and unreliable due to
poor image quality therefore the denoising and enhancement of the images become major
requirements for many applications. By the development of compressive sensing theory, sparse-
representation-based image restoration algorithms have been considered as a kind of promising
methods for image denoising. Generally, this kind of methods utilize a prior knowledge that each
image patch can be sparsely and linearly represented under some over-complete domains
spanned by a set of bases.
Traditional denoising methods often rely on averaging or smoothing techniques that can
inadvertently blur edges and obscure essential details. In contrast, sparse coding leverages the
inherent sparsity of medical images. This means that natural images, including medical scans,
can be represented by a combination of a few basis elements chosen from a learned dictionary.
This sparse representation allows the algorithm to effectively distinguish between noise and the
underlying signal, enabling the targeted removal of noise while preserving crucial details.
Studies have shown that sparse coding can achieve superior denoising performance compared to
traditional methods in various medical imaging modalities, including:
X-rays: Noise reduction of up to 30% while preserving image sharpness. (Source: Nishida et al.,
2016)
MRIs: Improved visualization of brain structures with minimal loss of detail. (Source: Gu et al.,
2014)
CT scans: Enables low-dose CT reconstruction with improved image quality, reducing radiation
exposure for patients. (Source: Liu et al., 2020)

You might also like