KR101928907B1 - Apparatus and method for enhancing image for quality improvement in radiographic image - Google Patents

Abstract

Disclosed are an apparatus for enhancing an image to improve quality in a radiographic image, and a method thereof. According to the present invention, a plurality of images obtained by processing a plurality of image quality improving algorithms on the radiographic image in parallel, are synthesized to enhance the radiographic image. According to the present invention, the image quality and readability may be improved.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image enhancing apparatus and method for enhancing an image quality of a radiological image,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image enhancement apparatus and method for improving the image quality of a radiation image, and more particularly, to an apparatus and a method for improving the image quality of a radiation image.

The most important challenge that has arisen as radiographs are stored in electronic form is how the electronic form radiographs can reproduce the detailed expression of film photographs. Among them, chest radiographs have a more difficult problem of expressing subtle differences with a wide range of intensities. Especially, in the veterinary field, these limits are more prominent due to various forms of chest wall. Therefore, image enhancement techniques applied to conventional digital images have also been applied to radiography and are being studied. However, most of the conventional researches are based on applying one image enhancement technique or sequentially applying various techniques.

Korean Patent Laid-Open No. 2003-0067310 (LUVENITICS CORPORATION) 2003. 8. 14. Patent Document 1 discloses a digital radiographic image processing method. In Patent Document 1, a digital radiographic image A log stretching image obtained by log stretching using a log function is obtained in order to convert an input image into an image with improved contrast value.

According to an aspect of the present invention, there is provided an image enhancement apparatus for improving image quality of a radiation image, which enhances a radiation image by synthesizing a plurality of images obtained by processing a plurality of image quality improvement algorithms in parallel on a radiation image, Method.

According to an aspect of the present invention, there is provided an image enhancement apparatus for enhancing an image quality of a radiological image, comprising: a plurality of image quality enhancement algorithms in parallel for processing an input radiation image, An image processing unit for obtaining a processed image; And an image synthesis unit for synthesizing the plurality of processed images acquired through the image processing unit to obtain a final radiation image.

Wherein the plurality of image quality enhancement algorithms comprise a histogram-based image quality enhancement algorithm and a mathematical morphology-based image quality enhancement algorithm, wherein the histogram-based image quality enhancement algorithm comprises Clipping and Stretching , CS, Histogram Equalization (HE), and Contrast Limited Adaptive Histogram Equalization (CLAHE), wherein the mathematical morphological image enhancement algorithm comprises a top-hat filter a top-hat filter, and a bottom-hat filter.

Wherein the image processing unit obtains a first processed image by applying the top-hat filter and the coarse-to-yellow filter to the input image, applies the histogram smoothing (HE) to the input image, And apply the contrast-limited adaptive histogram smoothing (CLAHE) to the input image to obtain a third processed image.

Wherein the image processing unit adds an image obtained by subjecting the clipped and stretched image to an image obtained by clipping and stretching the input image by processing the top-hat filter, The first processed image can be obtained by subtracting the processed image of the hat filter.

Wherein the image processing unit multiplies the clipped and stretched image by multiplying the image processed by the top-hat filter with a first weight, then adding the processed image to the second color filter by a second weight, To obtain the first processed image.

Wherein the image processing unit performs a normalization process on the input image and processes the plurality of image quality improvement algorithms in parallel on the normalized image, Can be obtained.

The image combining unit may multiply each of the plurality of processed images acquired through the image processing unit by a predetermined weight to obtain the final radiation image.

The image combining unit may normalize the final radiation image.

According to another aspect of the present invention, there is provided an image enhancement method for enhancing an image quality of a radiation image, the method comprising the steps of: Processing the image quality improvement algorithm in parallel to obtain a plurality of processed images from the input image; And synthesizing the acquired plurality of processed images to obtain a final radiographic image.

According to another aspect of the present invention, there is provided a computer readable recording medium storing a computer program for causing a computer to execute the method.

According to the image enhancement apparatus and method for improving the image quality of a radiological image according to the present invention, image quality can be improved by combining a plurality of images obtained by processing a plurality of image quality improvement algorithms in parallel, Can be improved.

1 is a block diagram for explaining an image enhancement apparatus for improving the quality of a radiation image according to a preferred embodiment of the present invention.
2 is a diagram for explaining a conventional image quality improvement algorithm.
3 is a diagram for explaining an example of the normalization process, which is one of the conventional image quality improvement algorithms.
FIG. 4 is a view for explaining an example of the clipping and stretching process, which is one of the conventional image quality improvement algorithms shown in FIG. 2. FIG.
FIG. 5 is a diagram for explaining an example of histogram smoothing (HE) processing which is one of conventional image quality improvement algorithms.
FIG. 6 is a diagram for explaining an example of a contrast-limited adaptive histogram smoothing (CLAHE) process, which is one of conventional image quality improvement algorithms.
FIG. 7 is a view for explaining an example of a top-hat filter and a bar-hat filter process which are one of conventional image quality improvement algorithms.
8 is a view for explaining an example of an image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention.
FIG. 9 is a flowchart illustrating an image enhancement method for improving the image quality of a radiological image according to a preferred embodiment of the present invention.
FIG. 10 is a flow chart for explaining the plurality of processed image acquisition steps shown in FIG. 9 in more detail.
11 is a flow chart for explaining the first processed image acquisition step shown in FIG. 10 in more detail.
Fig. 12 is a flowchart for explaining the final radiographic image acquisition step shown in Fig. 9 in more detail.
13 is a diagram for explaining a method for evaluating the performance of an image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention.
FIG. 14 is a diagram for explaining a radiation image used for performance evaluation by the performance evaluation method shown in FIG. 13; FIG.
FIG. 15 is a diagram for explaining a quantitative evaluation method among the performance evaluation methods shown in FIG. 13; FIG.
FIG. 16 is a diagram for explaining a qualitative evaluation method among the performance evaluation methods shown in FIG. 13;
17 is a view for explaining an example of a result image obtained by applying an image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention.
18 is a diagram for explaining a performance evaluation result of an image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to the preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings.

First, referring to FIG. 1, an image intensifier for enhancing the quality of a radiological image according to a preferred embodiment of the present invention will be described.

1 is a block diagram for explaining an image enhancement apparatus for improving the quality of a radiation image according to a preferred embodiment of the present invention.

Referring to FIG. 1, an image enhancement apparatus 100 (hereinafter, referred to as 'image enhancement apparatus') for improving the image quality of a radiological image according to a preferred embodiment of the present invention includes a plurality of image quality enhancement algorithms A plurality of images obtained by parallel processing are synthesized to enhance the radiation image.

Here, the plurality of image quality enhancement algorithms consist of a histogram-based image enhancement algorithm and a mathematical morphology-based image enhancement algorithm. Histogram-based image quality enhancement algorithms include normalization, clipping and stretching (CS), histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE) . The morphological-based image quality improvement algorithms include top-hat filters, bottom-hat filters, and the like.

To this end, the image enhancement apparatus 100 may include an image input unit 110, an image processing unit 130, and an image synthesis unit 150.

The image input unit 110 receives a radiation image from an external device (not shown) and provides the radiation image to the image processing unit 130.

The image processing unit 130 processes a plurality of image quality improvement algorithms in parallel on the radiation image input through the image input unit 110 to obtain a plurality of processed images from the input image. Here, the plurality of image quality improvement algorithms are composed of a histogram-based image quality improvement algorithm and a repair morphology-based image quality improvement algorithm, and the histogram-based image quality improvement algorithm includes clipping and stretching (CS), histogram smoothing (HE) And an adaptive histogram smoothing (CLAHE), and the mathematical morphological image enhancement algorithm may include at least one of a top-hat filter and a bottom-hat filter.

That is, the image processing unit 130 may apply the top-hat filter and the bottom-hat filter to the input image to obtain the first processed image.

More specifically, the image processing unit 130 adds a top-hat filter processed image to an image obtained by clipping and stretching the input image, clipping and stretching the clipped and stretched image, The first processed image can be obtained by subtracting the processed image of the hat filter. Here, clipping and stretching are methods of linear interpolation stretching after upper and lower histogram clipping. For example, the intensity of the upper 1% and lower 1% of the input image is removed, It can be rearranged by linear insertion method.

At this time, the image processing unit 130 multiplies the clipped and stretched image by the first weight (for example, 0.3, etc.) by adding the image processed by the top-hat filter and then adds the weight to the image subjected to the cropping- (E. G., 0.3, etc.), and subtracting it, to obtain a first processed image.

The image processing unit 130 may apply a histogram smoothing (HE) to the input image to obtain a second processed image.

In addition, the image processing unit 130 may apply the contrast-limited adaptive histogram smoothing (CLAHE) to the input image to obtain the third processed image.

At this time, the image processing unit 130 normalizes the input image, parallelly processes a plurality of image quality improving algorithms on the normalized image, and obtains a plurality of processed images from the normalized image .

In summary, the image processing unit 130 performs the above-described three image processing operations in parallel, and then performs the above-described processing on the plurality of acquired images, i.e., the first processed image, the second processed image, To the image synthesis unit 150. [0034] FIG.

The image synthesis unit 150 synthesizes a plurality of processed images obtained through the image processing unit 130 to obtain a final radiation image.

That is, the image combining unit 150 multiplies each of the plurality of processed images (the first processed image, the second processed image, and the third processed image) acquired through the image processing unit 130 by a predetermined weight , It is possible to obtain the final radiation image. For example, the image synthesis unit 150 may generate a first processed image (an image in which a top-hat filter and a bottom-hat filter are applied), a second processed image (an image in which histogram smoothing is applied) Images with adaptive histogram smoothing applied) may be multiplied by a weight of "0.65-0.85", "0.05-0.25", and "0.05-0.26", respectively, to obtain the final radiological image. For example, each of the first processed image, the second processed image, and the third processed image may be multiplied by a weight of "0.75", "0.15", and "0.10".

Then, the image synthesis unit 150 may normalize the final radiation image. In addition, the image synthesis unit 150 may convert the normalized final radiation image into a 16-bit gray scale image.

The image enhancement algorithm for enhancing the quality of a radiological image according to a preferred embodiment of the present invention will now be described in more detail with reference to FIGS. 2 to 8. FIG.

FIG. 2 is a view for explaining a conventional image quality improving algorithm, FIG. 3 is a view for explaining an example of a normalizing process, which is one of conventional image quality improving algorithms, FIG. 4 is a block diagram of a conventional image FIG. 5 is a view for explaining an example of histogram smoothing (HE) processing, which is one of image quality enhancement algorithms in the related art, and FIG. 6 is a diagram for explaining an example of clipping and stretching processing, FIG. 7 is a view for explaining an example of a contrast-limited adaptive histogram smoothing (CLAHE) process, which is one of image quality improvement algorithms of a top-hat filter and a bottom- Fig.

Conventional image quality improvement algorithms are roughly divided into two types based on their operation principles. Clipping and Stretching (CS), histogram smoothing (HE), and contrast-limited adaptive histogram smoothing (CLAHE) as shown in Figure 2 (a) . The second type is a mathematical morphology-based image quality enhancement algorithm, such as a top-hat filter and a bar-hat filter, as shown in FIG. 2 (b).

Normalization, which is one of the histogram-based image quality improvement algorithms, is a method of moving the intensity of each pixel to a broader category. As shown in FIG. 3, the normalization increases the overall contrast of the original image.

Clipping and stretching is a method of linear interpolation stretching after upper and lower histogram clipping. As shown in Fig. 4, clipping and stretching improve the contrast of the image while maintaining the overall anatomical distinction.

Histogram Smoothing (HE), one of the image enhancement algorithms based on histograms, is a method of flatly modifying a histogram. As shown in FIG. 5, it can be seen that histogram smoothing (HE) distinguishes between fat opacity and soft tissue opacity.

Contrast-limited adaptive histogram smoothing (CLAHE), which is one of the histogram-based image quality improvement algorithms, is a method of transforming histogram smoothing (HE), which increases the contrast of images by placing values exceeding a certain level in the histogram . As shown in FIG. 6, it can be seen that the contrast-limited adaptive histogram smoothing (CLAHE) further enhances the classification of the skeletal structure.

A top-hat filter, one of the image morphology-based image enhancement algorithms, is a method of extracting bright portions of an image, and a bar-hat filter is a method of extracting dark portions of an image. As shown in FIG. 7, it can be seen that the top-hat filter and the bar-hat filter increase the subtle difference in lung parentheses.

8 is a view for explaining an example of an image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention.

Referring to FIG. 8, the input radiation image is normalized from 0 to 1 (I ₀ ) through the following equation (1), and then sent to three layers.

Here, X is an input image. min (X) is the minimum pixel value of X and max (X) is the maximum pixel value of X.

The first layer clipping and stretching the input image, then applying top-hat and bottom-hat filters. That is, in the first layer, an image obtained by clipping and stretching a processed image is subjected to a clipping and stretching process, an image obtained by processing a top-hat filter is multiplied by a first weight (e.g., 0.3, etc.) And an output image can be obtained by multiplying the stretched image by the second weight (for example, 0.3, etc.) and subtracting it from the image obtained by processing the gap-hat filter.

In the second layer, the input image is subjected to histogram smoothing (HE).

In the third layer, the input image is subjected to contrast-limited adaptive histogram smoothing (CLAHE).

Then, each of the images output from the three layers is multiplied by a different weight, and then added to obtain a single result image. That is, "0.65 to 0.85", "0.05 to 0.25", and "0.15 to 0.25" are applied to each of the images to which the top-hat filter and the bar-hat filter are applied, the histogram smoothing (HE) and the contrast-limited adaptive histogram smoothing The resultant image can be obtained by multiplying by a weight of "0.05 to 0.26 ". For example, "0.75", "0.15", and "0.10" are assigned to each of the images to which the top-hat filter and the bar-hat filter are applied, the histogram smoothing (HE) is applied and the contrast limited adaptive histogram smoothing (CLAHE) Weights can be multiplied.

Then, the resultant image is normalized.

9 to 12, an image enhancement method for enhancing the image quality of a radiological image according to a preferred embodiment of the present invention will be described.

FIG. 9 is a flowchart illustrating an image enhancement method for improving the image quality of a radiological image according to a preferred embodiment of the present invention.

Referring to FIG. 9, the image enhancement apparatus 100 acquires a plurality of processed images from an input image by processing a plurality of image enhancement algorithms in parallel on an input radiation image (S110).

Then, the image enhancement apparatus 100 synthesizes the plurality of acquired processed images to obtain a final radiation image (S130).

FIG. 10 is a flow chart for explaining the plurality of processed image acquisition steps shown in FIG. 9 in more detail.

Referring to FIG. 10, the image enhancement apparatus 100 may normalize the input image (S111).

The image enhancement apparatus 100 may then apply a top-hat filter and a bottom-hat filter to the image to obtain a first processed image (S113).

Then, the image enhancement apparatus 100 can obtain a second processed image by applying histogram smoothing (HE) to the image (S115).

In addition, the image enhancement apparatus 100 may acquire a third processed image by applying contrast-limited adaptive histogram smoothing (CLAHE) to the image (S117).

Steps S113, S115, and S117 for applying the above image quality improvement algorithm are performed in parallel by the image enhancement apparatus 100. [

11 is a flow chart for explaining the first processed image acquisition step shown in FIG. 10 in more detail.

Referring to FIG. 11, the image enhancement apparatus 100 may perform clipping and stretching processing on an input image (S113a).

The image enhancement apparatus 100 may then apply a top-hat filter to the image (S113b).

Then, the image enhancement apparatus 100 may apply a gap-hat filter to the image (S113c).

The above-described filter application steps (S113b, S113c) are performed in parallel by the image enhancement apparatus (100).

Thereafter, the image enhancement apparatus 100 can acquire the first processed image (S113d). That is, the image enhancement apparatus 100 adds the clipped and stretched image to the clipped and stretched image, adds the top-hat filtered image to the clipped and stretched image, To obtain the first processed image. At this time, the image enhancement apparatus 100 multiplies the clipped and stretched image by the first weight (for example, 0.3, etc.) by adding the image processed by the top-hat filter to the image obtained by processing the cut- The second weighted value (e.g., 0.3, etc.) may be multiplied and subtracted to obtain the first processed image.

Fig. 12 is a flowchart for explaining the final radiographic image acquisition step shown in Fig. 9 in more detail.

Referring to FIG. 12, the image enhancement apparatus 100 may synthesize a plurality of acquired images to obtain a final radiation image (S131). That is, the image enhancement apparatus 100 multiplies each of the acquired plurality of processed images (the first processed image, the second processed image, and the third processed image) by a preset weight, Can be obtained. For example, the image enhancement apparatus 100 may include a first processed image (an image in which a top-hat filter and a bottom-hat filter are applied), a second processed image (an image in which histogram smoothing is applied) and a third processed image Images with adaptive histogram smoothing applied) may be multiplied by a weight of "0.65-0.85", "0.05-0.25", and "0.05-0.26", respectively, to obtain the final radiological image. For example, each of the first processed image, the second processed image, and the third processed image may be multiplied by a weight of "0.75", "0.15", and "0.10".

The image enhancement apparatus 100 may then normalize the acquired final radiation image (S133). Then, the image enhancement apparatus 100 can convert the normalized final radiation image into a 16-bit gray scale image.

Next, the performance of the image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention will be described with reference to FIGS. 13 to 18. FIG.

FIG. 13 is a diagram for explaining a method for evaluating the performance of an image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention. FIG. 14 is a flowchart illustrating a performance evaluation FIG. 15 is a view for explaining a quantitative evaluation method among the performance evaluation methods shown in FIG. 13, and FIG. 16 is a diagram for explaining a quantitative evaluation method among the performance evaluation methods shown in FIG. 13 Fig.

The performance of the image enhancement algorithm for improving the image quality of the radiological image according to the present invention was evaluated using quantitative evaluation and qualitative evaluation as shown in FIG.

The radiographs used for the performance evaluation of the present invention show high contrast, medium contrast, and low contrast according to the contrast of the image as shown in FIG. 14 Three groups were used. Each group consisted of 5 ventrodorsal views and 5 lateral views, and a total of 30 radiographs were used for performance evaluation. A total of 30 radiographs consisted of 15 normal images and 15 abnormal images with 22 abnormalities.

The quantitative evaluation used for the performance evaluation of the present invention utilized the entropy shown in Fig. Entropy is one of the texture analysis methods that can determine the complexity of the image. The entropy of the image to which the original image and the image enhancement algorithm according to the present invention (referred to as 'IEF' -test.

Here, p includes a histogram count.

The qualitative evaluation used for the performance evaluation of the present invention compares images before and after application of the image enhancement algorithm (IEF) according to the present invention, as shown in FIG. 16, in total of eight skilled radiologists. The evaluation criterion is based on the three points that the image enhancement algorithm (IEF) according to the present invention does not affect the readability, 2 points if the readability is slightly lowered, 1 point if the readability is lowered, 4 points if the readability was improved a little, and 5 points if the improvement was remarkably improved. In addition, the interobserver agreement was evaluated for reliability analysis.

FIG. 17 is a view for explaining an example of a result image obtained by applying an image enhancement algorithm for improving the image quality of a radiological image according to a preferred embodiment of the present invention. FIG. 18 is a view for explaining an image enhancement FIG. 2 is a diagram for explaining a performance evaluation result of the image enhancement algorithm for the image enhancement algorithm.

The image enhancement algorithm (IEF) according to the present invention can confirm that each of the image quality improvement algorithms has all the advantages as shown in FIG. 17 by applying a plurality of image quality enhancement algorithms in parallel.

As shown in FIG. 18, the image enhancement algorithm (IEF) according to the present invention can confirm that the image quality is improved as a result of quantitative evaluation and qualitative evaluation.

That is, as a result of the quantitative evaluation, it can be confirmed that the image with the image enhancement algorithm (IEF) according to the present invention shows a higher entropy average value than the original image. Accordingly, it can be confirmed that the image enhanced with the image enhancement algorithm (IEF) according to the present invention has a more detailed representation than the original image.

As a result of the qualitative evaluation, it can be confirmed that the average score of each group is 4 or more when the image enhancement algorithm (IEF) according to the present invention is applied. In addition, agreement between radiologist and radiologist was 0.73, which is acceptable. Accordingly, it can be seen that the image enhancement algorithm (IEF) according to the present invention has improved readability over the original image. In addition, the radiologists who participated in the evaluation had a common opinion that the visibility of the lungs and mediastinum increased without any noticeable vision or noise.

The present invention can also be embodied as computer-readable codes on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer is stored. Examples of the computer-readable recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device. In addition, the computer-readable recording medium may be distributed to computer devices connected to a wired / wireless communication network, and a computer-readable code may be stored and executed in a distributed manner.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the appended claims.

100: image intensifier, 110: image input section,
130: Image processing unit, 150:

Claims (10)

An image processing unit for processing a plurality of image quality improvement algorithms in parallel on an input radiation image to obtain a plurality of processed images from the input image; And
An image synthesis unit for synthesizing the plurality of processed images acquired through the image processing unit to acquire a final radiation image;
/ RTI >
Wherein the plurality of image quality enhancement algorithms comprise a histogram-based image enhancement algorithm and a mathematical morphology-based image enhancement algorithm,
The histogram-based image quality enhancement algorithm includes at least one of Clipping and Stretching (CS), Histogram Equalization (HE), and Contrast Limited Adaptive Histogram Equalization (CLAHE) ,
Wherein the mathematical morphology-based image quality enhancement algorithm comprises at least one of a top-hat filter and a bottom-hat filter,
Wherein the image processing unit obtains a first processed image by applying the top-hat filter and the coarse-to-yellow filter to the input image, applies the histogram smoothing (HE) to the input image, And acquiring a third processed image by applying the contrast-limited adaptive histogram smoothing (CLAHE) to the input image. delete delete The method of claim 1,
Wherein the image processing unit comprises:
The image obtained by subjecting the clipped and stretched image to the clipping and stretching process is added to the image obtained by clipping and stretching the input image, and the clipped and stretched processed image is subjected to the clipping and stretching process, Subtracting the image to obtain the first processed image,
Image enhancement device for improving the image quality of radiation image. 5. The method of claim 4,
Wherein the image processing unit comprises:
Wherein the image processed by the top-hat filter is multiplied by a first weight, then the clipped and stretched image is added to the image after the clipping and stretching process is multiplied by a second weight, Acquiring the processed image,
Image enhancement device for improving the image quality of radiation image. The method of claim 1,
Wherein the image processing unit comprises:
Processing the input image with a plurality of image quality improvement algorithms in parallel for the normalized image and obtaining the plurality of processed images from the normalized image ,
Image enhancement device for improving the image quality of radiation image. The method of claim 1,
Wherein the image synthesizing unit comprises:
Wherein each of the plurality of processed images acquired through the image processing unit is multiplied by a preset weight,
Image enhancement device for improving the image quality of radiation image. 8. The method of claim 7,
Wherein the image synthesizing unit comprises:
Normalizing the final radiation image to a target,
Image enhancement device for improving the image quality of radiation image. A method of enhancing an image of an image intensifier for improving an image quality of a radiation image,
Processing a plurality of image quality enhancement algorithms in parallel on an input radiation image to obtain a plurality of processed images from the input image; And
Synthesizing the acquired plurality of processed images to obtain a final radiographic image;
/ RTI >
Wherein the plurality of image quality enhancement algorithms comprise a histogram-based image enhancement algorithm and a mathematical morphology-based image enhancement algorithm,
The histogram-based image quality enhancement algorithm includes at least one of Clipping and Stretching (CS), Histogram Equalization (HE), and Contrast Limited Adaptive Histogram Equalization (CLAHE) ,
Wherein the mathematical morphology-based image quality enhancement algorithm comprises at least one of a top-hat filter and a bottom-hat filter,
Wherein the plurality of processed image acquiring steps acquires a first processed image by applying the top-hat filter and the coarse-fine filter to the input image, and applying the histogram smoothing (HE) to the input image And applying the contrast-limited adaptive histogram smoothing (CLAHE) to the input image to obtain a third processed image. The image enhancement method according to claim 1, wherein the third processed image is obtained by applying the contrast-limited adaptive histogram smoothing (CLAHE) to the input image. A computer program stored in a computer-readable recording medium for causing a computer to execute an image enhancement method for improving the image quality of a radiological image according to claim 9.

Images