Low Dose Ultrasound Image Enhancement

Medical ultrasound (also known as diagnostic sonography or ultrasonography) is a diagnostic imaging technique based on the application of ultrasound. It is used to create an image of internal body structures such as tendons, muscles, joints, blood vessels, and internal organs. Its aim is often to fi

Project Title

Low Dose Ultrasound Image Enhancement

Project Area of Specialization

Artificial Intelligence

Project Summary

Medical ultrasound (also known as diagnostic sonography or ultrasonography) is a diagnostic imaging technique based on the application of ultrasound. It is used to create an image of internal body structures such as tendons, muscles, joints, blood vessels, and internal organs. Its aim is often to find a source of a disease or to exclude pathology. The practice of examining pregnant women using ultrasound is called obstetric ultrasound, and was an early development and application of clinical ultrasonography. Ultrasound refers to sound waves with frequencies which are higher than those audible to humans (>20,000 Hz). Ultrasonic images, also known as sonograms, are made by sending pulses of ultrasound into tissue using a probe. The ultrasound pulses echo off tissues with different reflection properties and are recorded and displayed as an image. Many different types of images can be formed. The commonest is a B-mode image (Brightness), which displays the acoustic impedance of a two-dimensional cross-section of tissue. Other types can display blood flow, motion of tissue over time, the location of blood, the presence of specific molecules, the stiffness of tissue, or the anatomy of a three-dimensional region. Compared to other dominant methods of medical imaging, ultrasound has several advantages. It provides images in real-time and is portable and can be brought to the bedside. It is substantially lower in cost than other imaging modalities and does not use harmful ionizing radiation. Drawbacks include various limits on its field of view, such as the need for patient cooperation, dependence on physique, difficulty imaging structures behind bone and air, and the necessity of a skilled operator, usually a trained professional.Sonography (ultrasonography) is widely used in medicine. It is possible to perform both diagnosis and therapeutic procedures, using ultrasound to guide interventional procedures such as biopsies or drainage of fluid collections. Sonographers are medical professionals who perform scans which are then traditionally interpreted by radiologists, physicians who specialize in the application and interpretation of a wide variety of medical imaging modalities, or by cardiologists in the case of cardiac ultrasonography (echocardiography). Increasingly, clinicians (physicians and other healthcare professionals who provide direct patient care) are using the ultrasound in office and hospital practice (Point of Care Ultrasound).

Project Objectives

Image Enhancement is one of the most important and difficult techniques in image research. The aim of
image enhancement is to improve the visual appearance of an image, or to provide a “better transform
representation for future automated image processing. Evaluation have been done to different enhancement
techniques applied to ultrasound images to see which enhancement techniques is the most suitable techniques that
can be applied to the images before segmenting the edge of the image. Some common enhancement techniques have
been used including the Histogram equalization, Logarithmic Transformations and Gamma Transformations. The
main goal of this study is to improve features and gain better characteristics of medical ultrasound images for a
right diagnosis. Ultrasound images were usually poor quality especially in contrast. As all enhancement techniques
are application oriented, it is necessary to find a method which needs simple operations with effective enhancement
techniques. The histogram equalization with an image histogram, we have obtained the uniform distribution of pixel
values, and then we have again carried out the histogram transformation. Enhance the quality of image by applying
different method with ultrasound images which is useful for further process.Evaluation have been done to different enhancement techniques
applied to ultrasound kidney images to see which enhancement
techniques is the most suitable techniques that can be applied to
the kidney images before segmenting the edge of the kidney.
Five common enhancement techniques have been used including
the spatial domain filtering, frequency domain filtering,
histogram processing, morphological filtering and wavelet
filtering. The techniques applied were assessed by few methods
which are the observer sensitivity, measuring the image quality
by calculating the MSE and PSNR of the image and applying
one of the segmentation techniques to the output images. In
conclusion, for ultrasound kidney image, if the whole image
were taken into consideration (by measuring MSE and PSNR),
morphological filtering seems to be the best option in enhancing
the image. If the evaluator is concerning more on the kidney
edges, enhancement techniques that should be taken into
consideration are median filtering and histogram equalization.

Project Implementation Method

Ultrasounds, high-frequency sound waves, are used in medical applications for both diagnosis and treatment of patients. Their frequencies can vary from 2 to approximately 15 MHz for regular imaging, where in some cases higher frequencies are used for a finer surface imaging.

The ultrasound waves originate from the mechanical oscillations of a crystal in a transducer, excited by electrical pulses, also known as the piezoelectric effect. These pulses of sound are emitted from the transducer, propagate through the different media being imaged, and then return to the transducer as “reflected echoes” of an interface, as shown in Figure 2. These reflected echoes are converted back into electrical signals by the transducer and are further processed to form the final image.

 Original | PPT

Figure 2 

Principle of ultrasound flaw detection. A void in a solid material reflects some energy back to the transducer, which is detected and displayed. Source: wikimedia.

In general, these sound waves, like typical waves, are reflected at the interfaces between the tissues of different acoustic impedance (linked to the density of the medium), where the strength of the echo is proportional to the difference of the impedance. On the other hand, echoes are not produced if there is no acoustic difference, hence no impedance interface, between media. Homogeneous fluids thus seen as echo-free structures.

A modularized approach

A modular approach was chosen for the kit development in order to enable the exploration of the individual mechanisms of ultrasound processing and to allow the replacement of each element in the processing chain, as desired.

Each module can be considered as a breakout board of the most central elements, intended for easy experimentation with usual equipment, such as breadboards and standard power supplies. This design, along with selected easily-accessed signal interfaces, provides access to the different intermediary signals.

Benefits of the Project

The aim of image enhancement is to improve the
interpretability or perception of information in images for
human viewers, or to provide `better' input for other
automated image processing techniques. Image enhancement
techniques can be divided into two broad categories:
1. Spatial domain methods, which operate directly on pixels
2. Frequency domain methods, which operate on the Fourier
transform of an image.
Unfortunately, there is no general theory for
determining what `good’ image enhancement is when it
comes to human perception. If it looks good, it is good!
However, when image enhancement techniques are used as
pre-processing tools for other image processing techniques,
then quantitative measures can determine which techniques
are most appropriate. Apart from geometrical
transformations some preliminary grey level adjustments
may be indicated, to take into account imperfections in the
acquisition system. This can be done pixel by pixel,
calibrating with the output of an image with constant
brightness. Frequently space-invariant grey value
transformations are also done for contrast stretching, range
compression, etc.Image enhancement is a fundamental and is the
most important step before any image processing method to
be processed. Image enhancement process gives better visual
quality either by increasing the contrast or suppressing the
noise. This paper made an attempt to study image
enhancement by using Histogram equalization, Logarithmic
Transformations and Gamma Transformations. The different
image contrast enhancement techniques are analyzed in
which Histogram equalization play a major role of
enhancement compared to other method. The enhancement
techniques are superior to other techniques because these
techniques improve the visual effects and clarity of the
image with preserving its brightness. The major goal of
image contrast enhancement is to produce images without
severe side effects at the same time maintain input mean
brightness. Image enhancement algorithms offer a wide
variety of approaches for modifying images to achieve
visually acceptable images.

Technical Details of Final Deliverable

Finally we want to make an urgent available device of ultrasound which takes less power as well as give low quality image ,which we converted into more informative image through applying algorithm.

Final Deliverable of the Project

Hardware System

Type of Industry

Medical

Technologies

Augmented & Virtual Reality

Sustainable Development Goals

Partnerships to achieve the Goal

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com