Contrast Enhancement Of The Medical Images To Avoid The Risk Of The Diagnosis Process: [Essay Example], 2261 words GradesFixer
exit-popup-close

Haven't found the right essay?

Get an expert to write your essay!

exit-popup-print

Professional writers and researchers

exit-popup-quotes

Sources and citation are provided

exit-popup-clock

3 hour delivery

exit-popup-persone
close
This essay has been submitted by a student. This is not an example of the work written by professional essay writers.

Contrast Enhancement of the Medical Images to Avoid the Risk of the Diagnosis Process

Download Print

Pssst… we can write an original essay just for you.

Any subject. Any type of essay.

We’ll even meet a 3-hour deadline.

Get your price

121 writers online

blank-ico
Download PDF

This work targets to enhance the low contrast of the medical images to avoid the risk of the diagnosis process. Check whether the extracted image is clear or distorted. If it is distorted, apply median filter to reduce the noise and to detect the edge, canny edge detection is applied. The Fuzzy Logic based Homomorphic Filter (FL-HF) is proposed to enhance the contrast of the medical images which is used to improve the appearance of the images, in-order to obtain better visual interpretation and analysis and to ease the diagnosis process. The performance of contrast enhancement quality is measured by Peak Signal-to-Noise Ratio (PSNR), Contrast Improvement Index (CII), Absolute Mean Brightness Error (AMBE), Image Quality Index (IQI). According to a subjective assessment by a group of radiologists, the proposed technique resulted in excellent enhancement, including that of the contrast and the edges of medical images

Introduction

Image enhancement methods make a image simpler to dissect and translate. The scope of brilliance esteems present on a image is alluded to as differentiation. Complexity enhancement is a procedure that makes the picture highlights emerge all the moreunmistakably by making ideal utilization of the hues accessible on the presentation or yield gadget. Differentiation controls include changing the scope of qualities in a picture with a specific end goal to expand differentiate. For instance, a picture may begin with a scope of qualities somewhere in the range of 40 and 90. At the point when this is extended to a scope of 0 to 255, the contrast between highlights is complemented. Lamentably, unique highlights frequently reflect comparative measures of vitality all through the electromagnetic range, bringing about a moderately low differentiation picture. Hence, it is critical to consider both the biophysical and human segments while improving an image for most extreme difference. Direct and nonlinear advanced procedures are broadly rehearsed techniques for expanding the difference of an image.

Bhardwaj and Singh address the issue of the low complexity in and low quality of restorative pictures by proposing a procedure to upgrade medicinal pictures in light of the Haar change, delicate thresholding, and a nonlinear methodology for difference improvement. The issue with utilizing the Haar wavelet change lies in finding an appropriate method to extricate high-recurrence data and to break down high-recurrence sub-pictures of wavelets.

Rajput et al propose the utilization of nonlinear upgrade methods, for example, the discrete wavelet change and histogram balance to enhance the complexity in therapeutic images. In view of the analyses played out, the calculation proposed by the creators can be utilized to improve differentiate in the image while saving the nature of the image.

Ritika proposes a novel way to deal with upgrade the balance of restorative images with the assistance of morphology. The strategy utilizes a multi scale organizing component, where white and dark (splendid and dull) districts are removed for different sizes of the picture that relate to various sizes of the organizing component. In any case, there is a slight increment in noise. Be that as it may, this disadvantage could be decreased through further research and the calculation could be additionally stretched out using non-level organizing components.

In another new segmentation approach (SHE) was proposed which manages the Histogram Equalization. This system incorporates the picture smoothening by Gaussian channel, division in view of its valley positions, Histogram Equalization and in last full dynamic range extending pursued by standardization. As of late another strategy Quad Weighted histogram equalization with Adaptive Gamma Correction and Homomorphic Filtering (QWAGC-HF) has been recommended to enhance the difference of medicinal pictures and this strategy does not change the mean brightness of an info picture. It depends on first improving the worldwide differentiation of medical images by utilizing Gama redress and weighted likelihood appropriation of luminance pixels. After that Homomorphic Filtering is utilized for neighbourhood differentiate improvement pursued by standardization to limit the distinction between mean brightness of info and prepared image. Medical image enhancement processing is superior for present plain human tissues and organs and is moreover excellent for aided diagnosis. Contrast enhancement refers to highlight the low frequency component or high frequency component of the medical images based on the application. FL-HF is all about increasing the difference between the maximum intensity value in an image and the minimum one. All the rest of the intensity values are spread out between this range. There exists a one-to-one relationship of the intensity values between the source image and the target image i.e., the original image can be restored from the contrast-stretched image.

Homomorphic Filtering

An image as a capacity can be communicated as the result of enlightenment and reflectance parts as takes after: F(x,y) = I(x,y) * R(x,y) (1) Condition (1) can’t be utilized specifically to work independently on the recurrence parts of light and reflectance on the grounds that the Fourier change of the result of two capacities isn’t distinguishable. Rather the capacity can be spoken to as a logarithmic capacity wherein the result of the Fourier change can be spoken to as the whole of the enlightenment and reflectance segments as demonstrated as follows: ln(x,y) = ln(I(x,y)) + ln(R(x,y)) (2) The Fourier change of condition (2) is Z(u,v) = Fi(u,v) + Fr(u,v) (3) The fourier changed flag is prepared by methods for a channel work H(u,v) and the subsequent capacity is backwards fourier changed. At last, converse exponential activity yields an upgraded image. This upgrade approach is named as homomorphic filtering.

Design of Contrast Enhancement

Check whether the image is clear or distorted. If it is distorted, apply median filter to reduce the noise and to detect the edge, canny edge detection is applied. Now, the standard enhanced image is normalised by the fuzzy rules. Presently, Fuzzy Logic based Homomorphic Filtering (FL-HF) is connected to improve the complexity of the picture. Fig.1, demonstrates the framework design of the complexity improvement. Medical imaging uses image redesign techniques for diminishing confusion and honing inconspicuous components to improve the visual portrayal of the picture. Since minute unobtrusive components expect a fundamental part in end and treatment of infection, it is crucial to feature basic segments while demonstrating restorative pictures. This makes picture upgrade a crucial supporting instrument for overview anatomic ranges in MRI, ultrasound and x-beams et cetera. The technique proposed in this paper consists of three main steps: a. A median filter for noise reduction; b. A Canny edge detection for edge enhancement; and c. A Fuzzy Logic based Homomorphic Filtering for contrast enhancement.

Median Filter for noise reduction

In picture handling, the middle channel is utilized broadly to supplant undesirable pixel esteems with a more appropriate middle an (Check Medical Image Distortion) incentive from the environment. It is a nonlinear sifting system that is regularly used to decrease commotion. This commotion decrease procedure is frequently utilized as a preprocessing venture to enhance the consequences of picture preparing. The middle channel regularly gives preferred outcomes over a mean or normal channel. Besides, it very well may be utilized to expel Gaussian noise and in addition pepper and salt noise.

Canny Edge Detection for edge enhancement

Edge is a basic normal for a picture. Edges can be characterized as limit between two distinct locales in a picture. Edge discovery alludes to the movement of distinguish and find sharp discontinuities in a picture. Edge identification forms extensively decrease the amount of information and sift through futile data, while protecting the basic property in a picture. To identify the edge, watchful edge indicator is utilized. It is a multistage edge discovery calculation. The means are: Pre-handling, Calculating slopes, Non-most extreme concealment, Thresholding with hysterysis.

Fuzzy Logic based Homomorphic Filtering for Contrast Enhancement

The homomorphic filtering with fuzzy logic technique combines the logarithmic transform with fuzzy membership functions to deliver an intuitive method of image enhancement. This algorithm reduces the computational complexity by eliminating the need for image dependent filter kernels and the forward and inverse Fourier Transforms. The log transform used here to separate illumination and reflectance components and thereby increasing the reflectance component that is, increases the contrast of the image is shown in Fig. 3 (a) (b). The fuzzy logic is applied to the log transformed image and then exponential operation is applied to get the enhanced image.

Step 1: Linguistic variables and terms

Linguistic variables are input and output variables in the form of simple words or sentence. For vessel image, Gray level differences (High Frequency, Cut-off Frequency, Low Frequency) of pixels are Very Dark (VD), Dark (D), Gray (G), Bright (B), Very Bright (VB), etc., are linguistic terms. Every member of this set is a linguistic term and it can cover some portion of overall pixel values. Five linguistic terms are used, because we were enhancing the contrast of MR images. Even though, the MR image is in high quality, any variation in the contrast is noticed at this level.

Step 2: Membership functions

A membership function (MF) is a curve that defines how each point in the input space is mapped to a membership value (or degree of membership) between 0 and 1. Five triangular fuzzy sets are used to fuzzify the gray level differernces.

Step 3: Knowledge base rules

Build a set of rules into the knowledge base in the form.

Step 4: Obtain fuzzy value

Fuzzy set operations perform evaluation of rules. The operations used for OR and AND are Max and Min respectively. Combine all results of evaluation to form a final result. This result is a fuzzy value.

Step 5: Defuzzification

Defuzzification is then performed according to membership function for output variable (μA). This method provides a crisp value based on the center of gravity of the fuzzy set. Where, Aj denotes the center of frequency difference percent in the jth rule, and n also denotes the number of the rules.

Result Discussion and Analysis

The proposed system parameters are used to evaluate the performance of the contrast enhancement techniques.Contrast Improvement Index (CII): A quantization measure of contrast enhancement can be defined by a contrast improvement index, and its formula can be expressed by the following Eq.6,CII = Cprocessed / Coriginal (6)where Cprocessed and Coriginal are the contrasts of the processed and original images, respectively. Absolute Mean Brightness Error (AMBE): An objective measurement is proposed to rate the performance in preserving the original brightness. Eq. 7 is referred to as Absolute Mean Brightness Error (AMBE) and is defined as the absolute difference between the input and the output image’s mean AMBE = E(X) − E(Y) (7)X and Y denotes the input and output image, respectively. Lower AMBE indicates that the brightness is better preserved.

Universal Image Quality Index (IQI): The universal image quality index is used as image and video quality distortion measure. It is mathematically defined by modelling the image distortion relative to the reference image as a combination of three factors: loss of correlation, luminance distortion, and contrast distortion.

The graph is created based on Contrast Improvement Index (CII) is shown in Fig. 4. In Homomorphic Filtering (HF) the CII is achieved as low, because it only filters out the reflectance part by using transform function. In Quad Weighted histogram equalization with Adaptive Gamma Correction and Homomorphic Filtering (QWAGC-HF) the CII is achieved as low, because segmentation based on the valley position. In Fuzzy Logic based Homomorphic Filter (FL-HF) the CII is achieved as high, because the contrast is enhanced by normalizing non-uniform the illumination in the medical image. Here, the DICOM file format of CT-Scan and MR-Scan images were compared with the proposed algorithm. When compared to MR-image the CT-image gives the better CII. Normally, the resolution of the MR-image is high. But, the CT- image resolution is low when compared to the MR-image as per their equipments. While enhancing the image low contrast image gives the high Contrast Improvement Index. While comparing both CT-image as well as MR-image it gives better results when compared to the other existing method.

In Homomorphic Filtering the AMBE is achieved as high because it works only on the object which is present in the image. In Quad Weighted histogram equalization with Adaptive Gamma Correction and Homomorphic Filtering (QWAGC-HF) the AMBE is achieved as high because of the dynamic range stretching and normalization. In Fuzzy Logic based Homomorphic Filter (FL-HF) the AMBE is achieved as low, because in the frequency level of the image the fuzzy rule is applied. Here, the DICOM file format of CT-Scan and MR-Scan images were compared with the proposed algorithm. When compared to CT-image the MR-image gives the low error rate. Normally, the resolution of the MR-image is high. But, the CT- image resolution is low when compared to the MR-image as per their equipments used to get the image. While enhancing the image high contrast image gives the low Absolute Mean Brightness Error. While comparing both CT-image as well as MR-image it gives better results when compared to the other existing method.

Conclusion

The principal goal of image enhancement involves modifying the attributes of an image tomake it more suitable than the original image for a certain observer and a specific activity. Image enhancement encompasses manipulation of contrast and intensity, background removal, reduction of noise, filtering, and sharpening of edges to improve quality. The results presented in this paper show that the proposed technique can enhance medical DICOM images effectively, and this finding is supported by the results of a subjective assessment by a group of medical experts. Enhancements were made to the contrast and the edges of a range of medical DICOM images. From the medical perspective, the proposed technique clarified the arteries, tissues, and nodules. In addition, blurred nodules were enhanced effectively. Thus the proposed technique can help radiologists in the detection of lung nodules as well as assist in diagnosing the presence of tumours and in the detection of abnormal growths.

Remember: This is just a sample from a fellow student.

Your time is important. Let us write you an essay from scratch

100% plagiarism free

Sources and citations are provided

Find Free Essays

We provide you with original essay samples, perfect formatting and styling

Cite this Essay

To export a reference to this article please select a referencing style below:

Contrast Enhancement Of The Medical Images To Avoid The Risk Of The Diagnosis Process. (2020, May 19). GradesFixer. Retrieved November 25, 2020, from https://gradesfixer.com/free-essay-examples/contrast-enhancement-of-the-medical-images-to-avoid-the-risk-of-the-diagnosis-process/
“Contrast Enhancement Of The Medical Images To Avoid The Risk Of The Diagnosis Process.” GradesFixer, 19 May 2020, gradesfixer.com/free-essay-examples/contrast-enhancement-of-the-medical-images-to-avoid-the-risk-of-the-diagnosis-process/
Contrast Enhancement Of The Medical Images To Avoid The Risk Of The Diagnosis Process. [online]. Available at: <https://gradesfixer.com/free-essay-examples/contrast-enhancement-of-the-medical-images-to-avoid-the-risk-of-the-diagnosis-process/> [Accessed 25 Nov. 2020].
Contrast Enhancement Of The Medical Images To Avoid The Risk Of The Diagnosis Process [Internet]. GradesFixer. 2020 May 19 [cited 2020 Nov 25]. Available from: https://gradesfixer.com/free-essay-examples/contrast-enhancement-of-the-medical-images-to-avoid-the-risk-of-the-diagnosis-process/
copy to clipboard
close

Sorry, copying is not allowed on our website. If you’d like this or any other sample, we’ll happily email it to you.

    By clicking “Send”, you agree to our Terms of service and Privacy statement. We will occasionally send you account related emails.

    close

    Attention! this essay is not unique. You can get 100% plagiarism FREE essay in 30sec

    Recieve 100% plagiarism-Free paper just for 4.99$ on email
    get unique paper
    *Public papers are open and may contain not unique content
    download public sample
    close

    Sorry, we cannot unicalize this essay. You can order Unique paper and our professionals Rewrite it for you

    close

    Thanks!

    Your essay sample has been sent.

    Want us to write one just for you? We can custom edit this essay into an original, 100% plagiarism free essay.

    thanks-icon Order now
    boy

    Hi there!

    Are you interested in getting a customized paper?

    Check it out!
    Having trouble finding the perfect essay? We’ve got you covered. Hire a writer

    GradesFixer.com uses cookies. By continuing we’ll assume you board with our cookie policy.