{"id":62153,"date":"2024-12-30T11:32:11","date_gmt":"2024-12-30T11:32:11","guid":{"rendered":"https:\/\/biomedpharmajournal.org\/?p=62153"},"modified":"2025-01-06T18:18:14","modified_gmt":"2025-01-06T18:18:14","slug":"edge-detection-and-contrast-enhancement-in-the-examination-of-megaloblastic-anemia-cells-in-medical-images-with-comparative-analysis-of-different-approaches","status":"publish","type":"post","link":"https:\/\/biomedpharmajournal.org\/staging\/vol17no4\/edge-detection-and-contrast-enhancement-in-the-examination-of-megaloblastic-anemia-cells-in-medical-images-with-comparative-analysis-of-different-approaches\/","title":{"rendered":"Edge Detection and Contrast Enhancement in the Examination of Megaloblastic Anemia Cells in Medical Images with Comparative Analysis of Different Approaches"},"content":{"rendered":"\n

Introduction<\/strong><\/p>\n\n\n\n

Megaloblastic anemia is one of\nthe diseases types that are largely identified through a comprehensive blood\ntest 1, 2<\/sup>. The disease is characterized by a low level of hemoglobin\nin the blood, which is associated with a deficiency of vitamin B12 and\/or folic\nacid in the body. This disease is also characterized by the presence of\nenlarged red blood cells and hyper segmented neutrophils, which is important\nfor the analysis and diagnosis of the corresponding disease using separate\nlaboratory methods.<\/p>\n\n\n\n

Symptoms of megaloblastic anemia include: fatigue, shortness of breath, weakness, dizziness, chest pain 3, 4<\/sup>. As a consequence, megaloblastic anemia contributes to the development of fatigue and hair loss 5, 6<\/sup>. Its more serious manifestation is the development of heart failure, the possibility of oncological diseases,7, 8<\/sup>. Also Folate and vitamin B12 deficiencies have been linked to recurrent pregnancy loss (RPL), affecting a woman’s ability to carry a pregnancy to term9<\/sup>. This disease is quite common and, according to WHO estimates, at least 25% of the population is susceptible to it 10<\/sup>. The greatest manifestation of the disease is typical for preschool-age children10<\/sup>. Therefore, diagnosis and early detection of anemia is an important step in the process of its subsequent treatment.<\/p>\n\n\n\n

Diagnosis and in particular\nthe diagnosis of megaloblastic anemia are an important element in determining\nthe disease phase and its treatment. Here you can use various analysis and\ndiagnostic tools. Among these tools, due to several factors, it is necessary to\nhighlight the analysis of a blood smear to detect enlarged red blood cells or\nabnormal neutrophils. For these purposes, digital image analysis methods are\nused, which is reflected in various types of research 11-15<\/sup>. Also, similar studies are\nused considering the megaloblastic anemia analysis and its study.<\/p>\n\n\n\n

The complexity of the\ncorresponding analysis lies in the presence of a transitions set inside the\nmegaloblastic anemia cell, determining its structural features 16, 17<\/sup>.\nTherefore, one of the stages of such analysis is the original image preliminary\nprocessing methods. For example, H. M. Chen, Y. T. Tsao and S. C. Tsai\nemphasize the labor intensity of solving such a problem and talk about the need\nto use methods for removing background and noise 18<\/sup>. However, this\nis difficult to do without losing the quality of the processed image visualization.\nAt the same time, as noted by Abdulhay, E. W., Allow, A. G., & Al-Jalouly,\nM. E., the problem solving requires the presence of related samples with high visualization\nresolution 19<\/sup>. In real conditions, it is necessary to work with\nexisting source images. Therefore, an important aspect of such a research\nprocedure application is to consider various aspects of the corresponding\nanalysis. In the work of T. K. Y\u0131ld\u0131z, N. Yurtay and B. \u00d6ne\u00e7, it is directly\nstated that correct diagnosis is important from the point of view of patient\ntreatment 20<\/sup>. This implies, first, the use of simple but effective\nprocedures for various images types. In particular, various methods of contour detection can be considered\nhere, which are based on such operators as: Prewitt, Roberts, Sobel, LoG, Canny\nand others. This is based on the fact that even special methods do not\nprovide 100% accuracy in detecting and identifying megaloblastic anemia cells 20<\/sup>.\nAn important point here is to improve the quality of the processed image visualization\nto make appropriate decisions. For\nthese purposes, it is desirable to consider both the original images and the\nimages with modified contrast. To generalize the processing results, various\nmetrics for assessing the quality of the resulting images should be taken into\naccount.<\/p>\n\n\n\n

Therefore, considering the\nabove, this study main objective is to consider some procedure for analyzing\nimages with megaloblastic anemia cells. The purpose of such a procedure is to\nimprove the processed images visualization quality by highlighting potential\nareas of interest where various objects may be present. Therefore, an important\naspect is to conduct a comparative analysis of various approaches to edge\ndetection on medical images in the study of megaloblastic anemia cells.<\/p>\n\n\n\n

Materials and Methods<\/strong><\/p>\n\n\n\n

Medical image of megaloblastic anemia cells as a research object<\/strong><\/p>\n\n\n\n

One of the research objects in the diseases diagnosis and\nincreasing medical visualization efficiency are images of megaloblastic anemia\ncells, which are made under a microscope. These studies allow to increase the diagnostic\nanalysis accuracy, and to improve the visualization of areas of interest. It is\nimportant to consider in detail not only megaloblastic anemia cells, but also\naccompanying elements, objects of potential interest.<\/p>\n\n\n\n

On Fig. 1 – Fig. 3 show typical digital images with megaloblastic\nanemia cells. Here it will be simply Example 1, Example 2 and Example 3.\nDespite the apparent identity of such images, a number of the corresponding\nimages features should be noted.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 1: Image of a blood smear with megaloblastic anemia cells. Example 1. <\/strong>Original image (a), histogram of the brightness levels distribution (b)<\/strong><\/p>\n<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n\n
\"\"<\/td>\n\n

Figure 2: Image of a blood smear with megaloblastic anemia cells. Example 2. Original image (a), histogram of the brightness levels distribution (b)<\/strong><\/p>\n<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n\n
\"\"<\/td>\n\n

Figure 3: Image of a blood smear with megaloblastic anemia cells. Example 3. Original image (a), histogram of the brightness levels distribution (b).<\/strong><\/p>\n<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

First of all, we see that the cells of megaloblastic anemia have a\npronounced color difference against the background of the general background apparent\nhomogeneity. In particular, the question of the background homogeneity can be\ninvestigated based on contrasting methods, which will emphasize the existing\ndifferences in brightness that are invisible to the naked eye.<\/p>\n\n\n\n

However, the background heterogeneity can be seen from the\nanalysis of the brightness distribution histogram for each image (see Fig. 1b,\nFig. 2b, Fig. 3b). Moreover, the brightness distribution histogram data have\nseveral local maxima (this is typical for the image Example 1 and Example 3).\nIn general, this complicates the detection of megaloblastic anemia cells using\nsimple methods and thus requires an appropriate comparative analysis. It should\nalso be emphasized that the entropy parameter (more details on this parameter\nwill be given below) for the considered types of examples is equal to: Example\n1 \u2013 6.6240; Example 2 \u2013 6.4684; Example 3 \u2013 6.6933. Thus, the greatest number\nof brightness level differences is typical for Example 3, and not for Example\n1, as could be seen from the data of the corresponding brightness distribution\nhistograms.<\/p>\n\n\n\n

All of the above highlights the complexity and ambiguity of the\nsolutions to the stated goal of this study.<\/p>\n\n\n\n

Edge Detection Methods<\/strong><\/p>\n\n\n\n

To\nconduct a corresponding comparative study, we will consider classical approaches,\nand a method based on wavelet ideology as edge detection methods. The choice of\nsuch an analysis is based on the fact that classical approaches form the basis for\nmost edge detection developments. At the same time, wavelet ideology has\nrecently become widespread in the study of digital images.<\/p>\n\n\n\n

The Prewitt method or Prewitt operator is based on calculating the maximum response on a set of convolution kernels to find the local orientation of boundary 21<\/sup>. The following operators are used for these purposes. If we have some input image B<\/em>, then the following convolutions are calculated ( BH<\/em> \u2013 horizontal, BV<\/em> \u2013 vertical), which are then combined into a single resulting image (BR<\/em>) 21<\/sup> :<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

The Roberts operator for edge detection computes the sum of the squared differences between diagonally adjacent pixels of the input image B<\/em> 22<\/sup>. This can then also be written as a convolution of the image using the following kernels ( G1<\/sub>, G2<\/sub>)22<\/sup> :<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Then the resulting image is defined as:<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

The Sobel operator is based on convolution of the image with small separable integer filters in the vertical (GY<\/sub>) and horizontal (Gx<\/sub>) directions 21<\/sup>. Mathematically, this is written as follows 23<\/sup> :<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

The LoG operator is based on the Laplacian of Gauss. The original\nimage is convolved using a Gaussian kernel 24<\/sup>. The main problem with\napplying this operator at a single scale is that the response of the operator\nstrongly depends on the ratio between the size of the spot structures in the\nimage region and the size of the Gaussian kernel used for pre-smoothing 24<\/sup>.<\/p>\n\n\n\n

The Canny operator uses a multi-stage algorithm to detect a wide\nrange of edges in images based on the first derivative of a Gaussian 25<\/sup>.<\/p>\n\n\n\n

Ideologically based edge extraction also involves performing convolution in the horizontal and vertical directions (GWH<\/sub> , GWV<\/sub><\/em>) of the original image with the mother wavelet (MWH<\/em>, MWV)26<\/sup> :<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Next, the individual convolution results are combined into the\nresulting image 23<\/sup> :<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Each edge detection approach has its own advantages and\ndisadvantages, which are the most typically manifested on certain types of\ninput images 27-29<\/sup>, which also emphasizes the feasibility and\nnecessity of conducting the corresponding study.<\/p>\n\n\n\n

Contrast as a Tool for Changing Image Quality<\/strong><\/p>\n\n\n\n

For more accurate and effective edge detection, many researchers\nfirst perform contrasting of the original image. This allows one to highlight\nsubtle differences in brightness in the image being examined 21, 23<\/sup>.\nHowever, at the same time, this approach can lead to false detection of edge points.\nIt is also important to choose the right contrast change method for a\nparticular type of image.<\/p>\n\n\n\n

However, this paper primarily examines various edge detection\napproaches. Therefore, contrasting the original image is an additional factor\nin the corresponding study. Moreover, the contrasting basis is the methods of\nchanging the brightness distribution histogram for the original image.<\/p>\n\n\n\n

A common approach to contrasting an input image is to transform\nthe corresponding histogram so that it is close to a uniform distribution 27,\n30, 31<\/sup>. This is the approach that is used later to analyze and compare\ndifferent edge detection approaches.<\/p>\n\n\n\n

Quality Ratings of Processed Images<\/strong><\/p>\n\n\n\n

To conduct the corresponding study, an important point is the\nchoice of the processed images quality assessments 32, 33<\/sup>. When\nchoosing such assessments, one should take into account the task being solved\nand the possibility of calculating the selected assessments.<\/p>\n\n\n\n

In this case, the problem of comparing different edge detection\nmethods is solved. Therefore, it is inappropriate to use reference quality\nindicators. This is due to the impossibility and complexity of constructing a\nreference edge detection model. At the same time, in a specific case of edge\ndetection, there may be a discrepancy in individual edge formation coordinates.\nThen, a priori, comparing different edge detection methods using such\nassessments is impossible.<\/p>\n\n\n\n

It is also important to consider the fact that visualization plays\nan important role in medical diagnostics. Therefore, the quality of\nvisualization can be considered the basis for choosing the appropriate\nassessments. Among such assessments, attention should be paid to no-reference\nquality metrics. These are assessments such as:<\/p>\n\n\n\n

niqe is a measure of an image naturalness 34<\/sup>. The lower\nthe niqe value, the better the perceptual quality.<\/p>\n\n\n\n

brisque is a spatial quality score 35<\/sup>. The lower the\nbrisque value, the better the perceptual quality.<\/p>\n\n\n\n

piqe is an overall perceptual quality score without a reference\nimage quality score 36<\/sup>. A lower score indicates better perceptual\nquality.<\/p>\n\n\n\n

The entropy parameter should also be considered as a measure that\nshows the change in uncertainty 37<\/sup>. In this aspect, a higher value\nof the entropy indicator indicates the presence of more details in the image,\nwhich can be considered as one aspect of edge detection. This also allows for\nsome evaluation of the contour detection quality.<\/p>\n\n\n\n

Results<\/strong><\/p>\n\n\n\n

First of all, we note that the\ncorresponding comparative analysis general scheme consists of considering\nvarious quality indicators of images processed by different edge detection\noperators under conditions of input image contrasting and without contrasting.\nHere, such quality indicators are also considered for input images different\ntypes (Fig. 1, Fig. 2 and Fig. 3). Then, the obtained indicators are compared\nwith each other, and certain conclusions are made.<\/p>\n\n\n\n

The results of the quality\nindicators calculations are summarized in Table 1 \u2013 Table 6 for each type of\npresented images without their preliminary contrasting and with contrasting.<\/p>\n\n\n\n

Table 1: Quality ratings of the processed image for Example 1 (without contrast)<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Edge detection method<\/strong><\/p>\n<\/td>\n

\n

Quality ratings<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

niqe<\/strong><\/p>\n<\/td>\n

\n

brisque<\/strong><\/p>\n<\/td>\n

\n

entropy<\/strong><\/p>\n<\/td>\n

\n

piqe<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Prewitt<\/p>\n<\/td>\n

\n

14.7793<\/p>\n<\/td>\n

\n

49.5523<\/p>\n<\/td>\n

\n

1.0244<\/p>\n<\/td>\n

\n

15.6029<\/p>\n<\/td>\n<\/tr>\n

\n

Roberts<\/p>\n<\/td>\n

\n

16.8688<\/p>\n<\/td>\n

\n

49.7236<\/p>\n<\/td>\n

\n

1,666<\/p>\n<\/td>\n

\n

26.6450<\/p>\n<\/td>\n<\/tr>\n

\n

Sobel<\/p>\n<\/td>\n

\n

14.7367<\/p>\n<\/td>\n

\n

49.5620<\/p>\n<\/td>\n

\n

1.0266<\/p>\n<\/td>\n

\n

15.6070<\/p>\n<\/td>\n<\/tr>\n

\n

LoG<\/p>\n<\/td>\n

\n

16.1030<\/p>\n<\/td>\n

\n

51.2647<\/p>\n<\/td>\n

\n

1,7284<\/p>\n<\/td>\n

\n

27.7567<\/p>\n<\/td>\n<\/tr>\n

\n

Canny<\/p>\n<\/td>\n

\n

17.3403<\/p>\n<\/td>\n

\n

45.7670<\/p>\n<\/td>\n

\n

1,878<\/p>\n<\/td>\n

\n

34.3264<\/p>\n<\/td>\n<\/tr>\n

\n

Wavelet<\/p>\n<\/td>\n

\n

8,8495<\/p>\n<\/td>\n

\n

47.9526<\/p>\n<\/td>\n

\n

1,3317<\/p>\n<\/td>\n

\n

11.0569<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Table 2: Quality ratings of the processed image for Example 1 (with contrast)<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Edge detection method<\/strong><\/p>\n<\/td>\n

\n

Quality ratings<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

niqe<\/strong><\/p>\n<\/td>\n

\n

brisque<\/strong><\/p>\n<\/td>\n

\n

entropy<\/strong><\/p>\n<\/td>\n

\n

piqe<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Prewitt<\/p>\n<\/td>\n

\n

16.4635<\/p>\n<\/td>\n

\n

50.8991<\/p>\n<\/td>\n

\n

1,6554<\/p>\n<\/td>\n

\n

26.6523<\/p>\n<\/td>\n<\/tr>\n

\n

Roberts<\/p>\n<\/td>\n

\n

16.8688<\/p>\n<\/td>\n

\n

49.7236<\/p>\n<\/td>\n

\n

1,666<\/p>\n<\/td>\n

\n

26.6450<\/p>\n<\/td>\n<\/tr>\n

\n

Sobel<\/p>\n<\/td>\n

\n

16.5339<\/p>\n<\/td>\n

\n

50.4923<\/p>\n<\/td>\n

\n

1,672<\/p>\n<\/td>\n

\n

27.1415<\/p>\n<\/td>\n<\/tr>\n

\n

LoG<\/p>\n<\/td>\n

\n

16.3438<\/p>\n<\/td>\n

\n

50.4617<\/p>\n<\/td>\n

\n

2,2138<\/p>\n<\/td>\n

\n

40.6998<\/p>\n<\/td>\n<\/tr>\n

\n

Canny<\/p>\n<\/td>\n

\n

17.6094<\/p>\n<\/td>\n

\n

51.0705<\/p>\n<\/td>\n

\n

2,1949<\/p>\n<\/td>\n

\n

42.9896<\/p>\n<\/td>\n<\/tr>\n

\n

Wavelet<\/p>\n<\/td>\n

\n

8,7037<\/p>\n<\/td>\n

\n

49.1124<\/p>\n<\/td>\n

\n

2,1839<\/p>\n<\/td>\n

\n

13.0392<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

The data analysis of Table 1\nand Table 2 allows us to identify the method based on the wavelet ideology\n(Wavelet method) as the most effective for edge detection in images with\nmegaloblastic anemia cells among all those considered (based on the selected\ngroup of indicators). For a number of individual indicators, contrasting the\noriginal image (Fig. 1) allows us to improve individual indicators. This\nconcerns the niqe and entropy indicators. For most other edge detection\nmethods, the quality indicators deteriorate after contrasting. This is\nexplained by the complexity of the general background, many small details in\nthe area of the megaloblastic anemia cell itself, which is displayed in the brightness\ndistribution histogram for this image (Fig. 1b). However, the presented quality metrics generally allow\none to evaluate and compare the original image and the image after contrasting (here\nand further in the tables the best indicators are highlighted in bold and\nunderlined).<\/p>\n\n\n\n

As an example, Fig. 4 shows\nindividual edge detection results for the original image Example 1 (Fig. 1a).<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 4: Edge detection results for image Example 1 using individual operators<\/strong><\/p>\n<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

From the data in Fig. 4 it is\nevident that contrasting the original image as a result of its subsequent\nprocessing for the edge detection increases the visible brightness differences number.\nThis affects the processed image corresponding evaluation indicators. In this\ncase, many false edge points appear. The exception is the Wavelet edge\ndetection method. This method allows you to emphasize the true edges on the original\nimage objects.<\/p>\n\n\n\n

The data analysis of Table 3\nand Table 4 for the image Example 2 also confirms the prevalence of the Wavelet\nedge detection method compared to other approaches. In this case, overall, an\nimprovement in the evaluation indicators of the processed image after\ncontrasting the input image is visible. This is based on a more uniform\ndistribution of the background point brightness and a smaller number of their\npeak values for the entire image.<\/p>\n\n\n\n

Table 3: Quality ratings of the processed image for Example 2 (without contrast)<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Edge detection method<\/strong><\/p>\n<\/td>\n

\n

Quality ratings<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

niqe<\/strong><\/p>\n<\/td>\n

\n

brisque<\/strong><\/p>\n<\/td>\n

\n

entropy<\/strong><\/p>\n<\/td>\n

\n

piqe<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Prewitt<\/p>\n<\/td>\n

\n

21.4605<\/p>\n<\/td>\n

\n

53.3878<\/p>\n<\/td>\n

\n

1,4206<\/p>\n<\/td>\n

\n

22.5627<\/p>\n<\/td>\n<\/tr>\n

\n

Roberts<\/p>\n<\/td>\n

\n

21.5650<\/p>\n<\/td>\n

\n

52.6917<\/p>\n<\/td>\n

\n

1,4817<\/p>\n<\/td>\n

\n

25.3519<\/p>\n<\/td>\n<\/tr>\n

\n

Sobel<\/p>\n<\/td>\n

\n

21.6411<\/p>\n<\/td>\n

\n

53.4302<\/p>\n<\/td>\n

\n

1,4129<\/p>\n<\/td>\n

\n

22.6225<\/p>\n<\/td>\n<\/tr>\n

\n

LoG<\/p>\n<\/td>\n

\n

23.7022<\/p>\n<\/td>\n

\n

53.7618<\/p>\n<\/td>\n

\n

1,569<\/p>\n<\/td>\n

\n

25.5712<\/p>\n<\/td>\n<\/tr>\n

\n

Canny<\/p>\n<\/td>\n

\n

20.6207<\/p>\n<\/td>\n

\n

51.7153<\/p>\n<\/td>\n

\n

1,7573<\/p>\n<\/td>\n

\n

32.2018<\/p>\n<\/td>\n<\/tr>\n

\n

Wavelet<\/p>\n<\/td>\n

\n

8,5086<\/p>\n<\/td>\n

\n

28.9681<\/p>\n<\/td>\n

\n

3,8376<\/p>\n<\/td>\n

\n

18.6117<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Table 4: Quality ratings of the processed image for Example 2 (with contrast)<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Edge<\/strong><\/p>\n

detection method<\/strong><\/p>\n<\/td>\n

\n

Quality ratings<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

niqe<\/strong><\/p>\n<\/td>\n

\n

brisque<\/strong><\/p>\n<\/td>\n

\n

entropy<\/strong><\/p>\n<\/td>\n

\n

piqe<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Prewitt<\/p>\n<\/td>\n

\n

21.1925<\/p>\n<\/td>\n

\n

50.1839<\/p>\n<\/td>\n

\n

1,6308<\/p>\n<\/td>\n

\n

23.4704<\/p>\n<\/td>\n<\/tr>\n

\n

Roberts<\/p>\n<\/td>\n

\n

17.5236<\/p>\n<\/td>\n

\n

52.4189<\/p>\n<\/td>\n

\n

1,4227<\/p>\n<\/td>\n

\n

18.5347<\/p>\n<\/td>\n<\/tr>\n

\n

Sobel<\/p>\n<\/td>\n

\n

20.5683<\/p>\n<\/td>\n

\n

49.9179<\/p>\n<\/td>\n

\n

1,6589<\/p>\n<\/td>\n

\n

24.0004<\/p>\n<\/td>\n<\/tr>\n

\n

LoG<\/p>\n<\/td>\n

\n

24.8985<\/p>\n<\/td>\n

\n

43.8370<\/p>\n<\/td>\n

\n

2,8014<\/p>\n<\/td>\n

\n

53.5161<\/p>\n<\/td>\n<\/tr>\n

\n

Canny<\/p>\n<\/td>\n

\n

20.3263<\/p>\n<\/td>\n

\n

43.1628<\/p>\n<\/td>\n

\n

3,2421<\/p>\n<\/td>\n

\n

78.3213<\/p>\n<\/td>\n<\/tr>\n

\n

Wavelet<\/p>\n<\/td>\n

\n

8,4886<\/p>\n<\/td>\n

\n

32.9681<\/p>\n<\/td>\n

\n

4,4376<\/p>\n<\/td>\n

\n

20.1403<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\u00a0<\/p>\n\n\n

On Fig. 5 shows some results\nof processing the image Example 2 using different edge detection operators.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 5: Some results of image processing Example 2 using  different edge detection operators<\/strong><\/p>\n<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

The data in Fig. 5 indicate\napproximately the same results of processing the image Example 2 using\ndifferent edge detection operators. Therefore, here we pay attention to the entropy index, which allows\nbetter structure of the megaloblastic anemia cell identification, which can be\nassessed without contrast (Table 3).<\/p>\n\n\n\n

The data analysis of Table 5\nand Table 6 (for image \u2013\nExample 3) also indicates a more efficient use of the Wavelet method for\nedge detection in an image.<\/p>\n\n\n\n

Table 5: Quality ratings of the processed image for Example 3 (without contrast)<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Edge<\/strong><\/p>\n

detection method<\/strong><\/p>\n<\/td>\n

\n

Quality ratings<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

niqe<\/strong><\/p>\n<\/td>\n

\n

brisque<\/strong><\/p>\n<\/td>\n

\n

entropy<\/strong><\/p>\n<\/td>\n

\n

piqe<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Prewitt<\/p>\n<\/td>\n

\n

17.6717<\/p>\n<\/td>\n

\n

49.8982<\/p>\n<\/td>\n

\n

1,0646<\/p>\n<\/td>\n

\n

15.3035<\/p>\n<\/td>\n<\/tr>\n

\n

Roberts<\/p>\n<\/td>\n

\n

17.8587<\/p>\n<\/td>\n

\n

49.5139<\/p>\n<\/td>\n

\n

1,0118<\/p>\n<\/td>\n

\n

15.2313<\/p>\n<\/td>\n<\/tr>\n

\n

Sobel<\/p>\n<\/td>\n

\n

17.7230<\/p>\n<\/td>\n

\n

49.8893<\/p>\n<\/td>\n

\n

1,063<\/p>\n<\/td>\n

\n

15.3059<\/p>\n<\/td>\n<\/tr>\n

\n

LoG<\/p>\n<\/td>\n

\n

18.6288<\/p>\n<\/td>\n

\n

53.2788<\/p>\n<\/td>\n

\n

1,5778<\/p>\n<\/td>\n

\n

25.6888<\/p>\n<\/td>\n<\/tr>\n

\n

Canny<\/p>\n<\/td>\n

\n

17.2408<\/p>\n<\/td>\n

\n

45.6353<\/p>\n<\/td>\n

\n

1,9843<\/p>\n<\/td>\n

\n

37.1334<\/p>\n<\/td>\n<\/tr>\n

\n

Wavelet<\/p>\n<\/td>\n

\n

5.0643<\/p>\n<\/td>\n

\n

35.0228<\/p>\n<\/td>\n

\n

4,4625<\/p>\n<\/td>\n

\n

16.4014<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\u00a0<\/p>\n\n\n

Table 6: Quality ratings of the processed image for Example 3 (with contrast)<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Edge<\/strong><\/p>\n

detection method<\/strong><\/p>\n<\/td>\n

\n

Quality ratings<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

niqe<\/strong><\/p>\n<\/td>\n

\n

brisque<\/strong><\/p>\n<\/td>\n

\n

entropy<\/strong><\/p>\n<\/td>\n

\n

piqe<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Prewitt<\/p>\n<\/td>\n

\n

18.0005<\/p>\n<\/td>\n

\n

52.9498<\/p>\n<\/td>\n

\n

1,6164<\/p>\n<\/td>\n

\n

25.5550<\/p>\n<\/td>\n<\/tr>\n

\n

Roberts<\/p>\n<\/td>\n

\n

16.7611<\/p>\n<\/td>\n

\n

53.3776<\/p>\n<\/td>\n

\n

1,5161<\/p>\n<\/td>\n

\n

22.3826<\/p>\n<\/td>\n<\/tr>\n

\n

Sobel<\/p>\n<\/td>\n

\n

17.9964<\/p>\n<\/td>\n

\n

52.7035<\/p>\n<\/td>\n

\n

1,6441<\/p>\n<\/td>\n

\n

26.0477<\/p>\n<\/td>\n<\/tr>\n

\n

LoG<\/p>\n<\/td>\n

\n

18.2448<\/p>\n<\/td>\n

\n

51.0766<\/p>\n<\/td>\n

\n

2,3855<\/p>\n<\/td>\n

\n

44.5935<\/p>\n<\/td>\n<\/tr>\n

\n

Canny<\/p>\n<\/td>\n

\n

17.4163<\/p>\n<\/td>\n

\n

40.7631<\/p>\n<\/td>\n

\n

2,7122<\/p>\n<\/td>\n

\n

57.4449<\/p>\n<\/td>\n<\/tr>\n

\n

Wavelet<\/p>\n<\/td>\n

\n

5.0943<\/p>\n<\/td>\n

\n

35.4228<\/p>\n<\/td>\n

\n

4,7625<\/p>\n<\/td>\n

\n

17.4693<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n\n\n

On Fig. 6 shows some examples\nof image processing Example 3 for edge detection.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 6: Some examples of image processing Example 3 for edge enhancement<\/strong><\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Thus, the obtained results\nallow us to evaluate various edge detection methods for images with\nmegaloblastic anemia cells, taking into account the original image processing\nwithout preliminary changes in its contrast and contrasting.<\/p>\n\n\n\n

Discussion<\/strong><\/p>\n\n\n\n

Digital image analysis has\nbecome an essential tool in modern hematology, enhancing the precision and\nefficiency of laboratory diagnostics38<\/sup>. Numerous studies focus on analyzing blood components, such as red\nblood cells (RBCs) and white blood cells (WBCs), using medical digital imaging\ntechniques. Among these studies, images with megaloblastic anemia cells occupy\na special place.<\/p>\n\n\n\n

The work by K. T. Navya, K.\nPrasad and B. M. K. Singh provides an overview of blood smear image analysis\nfor detecting anemia 39<\/sup>. First of all, the authors emphasize the\nimportance of conducting relevant studies and in particular the anemia diagnosis\nusing peripheral blood smear analysis. At the same time, attention is drawn to this\nprocess automation, which involves the use of simple and adequate approaches.\nFor these purposes, the authors consider various methods and the possibility of\ntheir use for a certain type of digital images. In this aspect, this correlates\nwith the ideas that are considered in our work. At the same time, an important\npoint of such analysis is the input data segmentation, which is also emphasized\nin our study.<\/p>\n\n\n\n

In the work of K. T. Navya, K. Prasad and B. M. K. Singh it is emphasized\nthat such edge detection operators as Canny, LOG and Sobel allow to achieve up\nto 85% accuracy in identifying blood components 39<\/sup>. These figures\ncannot be unambiguously compared with our results, since we operate with\nquality metrics. At the same time, the data analysis of Table 1 \u2013 Table 6 also\nallows to distinguish the Canny, LOG and Sobel operators in comparison with the\nWavelet operator for edge detection. In this regard, our study correlates with\nthe conclusions of the work 39<\/sup>, where edge detection using wavelets\nwas not considered.<\/p>\n\n\n\n

B. Ballar\u00f2, A. M. Florena, V.\nFranco, D. Tegolo, C. Tripodo and C. Valenti consider some issues of images\nwith megakaryocyte cells automated analysis40<\/sup>. For these purposes,\nfirst of all, the input image is segmented. The authors note that this can be\ndone based on various approaches, including edge detection methods, wavelet\ntransform of data. This emphasizes the feasibility of the studies conducted in\nour study. The authors also pay attention to the megakaryocyte cells geometric\ncharacteristics. However, this approach is controversial, since the geometric\ncharacteristics will correlate with the input image size, such an image\npresentation type and features. Nevertheless, study 40<\/sup> offers useful\nassistance in supporting a specialist in the classification of megakaryocyte\ndisorders.<\/p>\n\n\n\n

The paper 40<\/sup> also notes that edge detection methods can\nincrease the accuracy of blood component classification to 97%. Thus, the\nchoice of edge detection operator and the change in the original image contrast\nare key factors in identifying and classifying megaloblastic anemia cells. Then\nthe data in Table 1 \u2013 Table 6 are a tool for selecting a specific edge\ndetection operator when solving the tasks set, taking into account the image type\nunder consideration.<\/p>\n\n\n\n

H. A. Elsalamony considers red\nblood cells in human blood smears based on the analysis of digital images using\nneural networks 41<\/sup>. The author notes that one of such an analysis methods\nis based on microscopic examination of blood smears. Based on this, the paper\npresents a general algorithm for detecting and counting three types of\nanemia-infected red blood cells. This algorithm allows achieving maximum detection of approximately 97.8%\nof all cells in the examined images. For these purposes, the Hough transform,\nand a number of morphological tools are used 41<\/sup>. Further, a neural\nnetwork is used to classify the cells. However, the author does not note the\ntype of input images and its main characteristics, which is important in this\nkind of research. At the same\ntime, considering perception metrics to evaluate the preliminary image analysis\nresults before classifying subsequent results is an important step. This is\nwhat is summarized in the data in Table 1 \u2013 Table 6.<\/p>\n\n\n\n

P. Dhar, K. Suganya Devi, S.\nK. Satti and P. Srinivasan investigate the possibility of red blood cell\nclassification from digital images using wavelet ideology 42<\/sup>. The\nauthors propose a hybrid approach using color quantized segmented K-mean convolutional\nneural network with deep attention and extreme gradient boosting algorithm for\npoikilocytosis classification to detect and classify abnormal cells 42<\/sup>.\nIn this case, the features of the segmented red blood cells are extracted using\nGabor wavelets. The proposed approach gives good results, which justifies the\nuse of wavelet ideology for this purpose. The model proposed by the authors allows obtaining\nestimates at the level of 95.38% and 93.43% in further classification of\nabnormal cells 42<\/sup>. In this process, an important role is given to the\noriginal image segmentation using wavelets. This fact is also confirmed and\ncorrelated with the results of our study, where the Wavelet operator gives the\nbest results in edge detection (Table 1 – Table 6).<\/p>\n\n\n\n

S. Mitra, N. Das, S. Dey, S.\nChakraborty, M. Nasipuri and M. K. Naskar conduct a systematic review of\ndigital cytological image analysis methods, paying attention to the possibility\nof automating this process 43<\/sup>. The authors clearly distinguish the\ntypes of cytological objects. However, insufficient attention is paid to the corresponding\ndigital images types. At the same time, it is the digital image type and its\ncharacteristics that determine the certain methods application sequence in\norder to solve the problem. Nevertheless, the authors pay attention to the\nimportance of using the wavelet ideology in studying the texture and structural\nfeatures of megaloblastic anemia cells. This also correlates with the results of our study and\nconfirms their validity and significance.<\/p>\n\n\n\n

The researchers also highlight\nthe complexity and ambiguity in using edge operators to isolate megaloblastic\nanemia cells. <\/p>\n\n\n\n

For example, C. C. Hortinela,\nJ. R. Balbin, J. C. Fausto, P. D. C. Divina, and J. P. T. Felices emphasize the\nneed for a balanced approach in the use of image processing methods in the\nstudy of abnormal red blood cells and the anemia certain types diagnosis 44<\/sup>.\nVarious procedures for such analysis can also be used here, where it is\nappropriate to use edge enhancement operators. However, such analysis should be\nperformed taking into account the input image type and the parameters for edge\nenhancement definition by different operators. This is especially important\nwhen different types of red blood cells can be in the field of view. Thus, the\nauthors confirm the need for appropriate studies to examine the feasibility of\nusing edge enhancement methods in certain conditions. The work notes a high degree of abnormal red blood cells\nvarious types identification from 95% to 98.33% 44<\/sup>, where it is\nimportant to take into account the type of input image. Our work also shows the\nhigh efficiency of using the Wavelet operator to highlight the edge on various\ntypes of images with megaloblastic anemia cells (Table 1 – Table 6).<\/p>\n\n\n\n

V. Yadav, P. Ganesh, and G.\nThippeswamy also highlight the need for consistency in the selection of edge\noperators in the study of red blood cells using a computer-aided framework for\nthe blood disorders diagnosis 45<\/sup>. This analysis technique is based\non granulometric assessment, which involves the relevant image preliminary\nsegmentation, for example, using edge detection methods. This is also consistent with the\napproaches considered in our study and confirms the significance of such an\nanalysis. However, it is not possible to compare the corresponding results,\nsince V. Yadav, P. Ganesh and G. Thippeswamy operate with the concept of\ndiagnostic accuracy in blood disorders, in our case, quality metrics act as an evaluation\nparameter.<\/p>\n\n\n\n

V. Acharya and P. Kumar also\nuse edge detection methods in their study on red blood cell identification. In\nparticular, the authors pay attention to such an edge detection method as the\nuse of the Sobel operator 46<\/sup>. This method is used in combination\nwith granulometric analysis to separate red blood cells from white blood cells.\nHowever, the work does not consider preliminary methods for processing the\ninput image. Also, the work does not describe the original image parameters. However, the results presented in\nTable 1\u2013Table 6 confirm the validity of using the Sobel operator for edge\ndetection for erythrocyte identification.<\/p>\n\n\n\n

As for the obtained results\nevaluating methods, here researchers, first of all, take into account the\nproblem they are solving.<\/p>\n\n\n\n

Study 47<\/sup> uses\nevaluation measures that allow us to evaluate the quality of the segmentation\nperformed. Reference quality metrics are used here. However, it is not entirely\nclear what (with what base result) the corresponding comparison is made. This\nsomewhat complicates the work results understanding. Our study describes in\ndetail the rationale for choosing the evaluations of the results such\nevaluations types comparison.<\/p>\n\n\n\n

The work by R. Garg, A. K.\nSandhu, B. Kaur, B. Goyal, and A. Dogra uses standard image description statistical\nparameters, which allows understanding the meaning of the corresponding scores 48<\/sup>.\nHowever, this work also does not provide a rationale for using the\ncorresponding scores. Moreover,\nstatistical estimates depend on the data type presented and their sample, which\ncomplicates comparative analysis. Our study provides specific measures of the results\nperception quality, which allows for comparison for the individual types of\nimages we study.<\/p>\n\n\n\n

K. A. Noman and A. S. Yaseen\ndescribe in detail in their study the selection of appropriate estimators for\nthe analysis of medical microscopic image processing 49<\/sup>. This helps\nto better understand the obtained results and evaluate them. In particular, the concepts of\nentropy and image quality assessment based on its perception were used as such\nassessments. Similar assessments were used in our study. However, it is\ninappropriate to compare such assessments values, since we use completely\ndifferent medical images.<\/p>\n\n\n\n

Thus, in general, the\npresented study corresponds to the main directions of analysis in the field of\nmegaloblastic anemia cell images. This confirms the appropriateness and\nsignificance of the analysis, and the possibility of its use in further work on\nmedical image research.<\/p>\n\n\n\n

Conclusion<\/strong><\/p>\n\n\n\n

The paper presents a comparative analysis of edge detection\nmethods in order to analyze digital medical images with megaloblastic anemia\ncells. Attention is paid to simple classical edge detection operators in\ncomparison with an approach based on wavelet ideology. Cases of edge detection\nwithout changing the original image contrast and taking into account its\ncontrasting are also considered. A number of no-reference quality metrics are\nused to evaluate the results obtained.<\/p>\n\n\n\n

The strong points of the issues considered are justification of\nthe obtained results estimates using; determination of the edge detection most\neffective method in a comparative aspect; characteristics description for the images\ntypes used in the study. Among the problematic aspects of the material\nconsidered, it is necessary to indicate the justification of the need for contrasting\nthe original image and the choice of the method for changing the contrast procedure.<\/p>\n\n\n\n

A series of experiments were conducted on real images. The results\nobtained are acceptable and can be used for blood smear analysis.<\/p>\n\n\n\n

As further research directions,\nit is advisable to highlight the creation of a basic set of images with\nmegaloblastic anemia cells in order to use reference quality metrics and\ncomparing them with no-reference quality metrics. No less important is the\nexpansion of such research: the study of various wavelets using for edge\ndetection, conducting the corresponding analysis in various color spaces.<\/p>\n\n\n\n

Acknowledgement<\/strong><\/p>\n\n\n\n

The authors are thankful to the Department of Media Systems and Technology,\nKharkiv National University of Radio Electronics, Kharkiv, Ukraine, and the\nDepartment of Medical Laboratory Sciences, College of Health Sciences, Gulf\nMedical University, Ajman, United Arab Emirates, for providing support and\nfacilities.<\/p>\n\n\n\n

Funding Source<\/strong><\/p>\n\n\n\n

The author(s) received no financial support for\nthe research, authorship, and\/or publication of this article<\/p>\n\n\n\n

Conflict of Interest<\/strong><\/p>\n\n\n\n

The author(s) do not have any conflict of\ninterest.<\/p>\n\n\n\n

Data\nAvailability Statement<\/strong><\/p>\n\n\n\n

This\nstatement does not apply to this article.<\/p>\n\n\n\n

Ethics approval<\/strong><\/p>\n\n\n\n

This\nresearch did not involve human participants, animal subjects, or any material\nthat requires ethical approval.<\/p>\n\n\n\n

Informed Consent Statement<\/strong><\/p>\n\n\n\n

This study did not involve human participants, and therefore, informed consent was not required<\/p>\n\n\n\n

Clinical Trial Registration<\/strong><\/p>\n\n\n\n

This research does not involve any clinical\ntrials<\/p>\n\n\n\n

Author Contributions<\/strong><\/p>\n\n\n\n

Vyacheslav Lyashenko and Asaad Babker: Conceptualization, Methodology, Writing and Original Draft.<\/p>\n\n\n\n

Vyacheslav Lyashenko and Asaad Babker: Data Collection, Analysis, Writing Review and Editing.<\/p>\n\n\n\n

Vyacheslav Lyashenko : Visualization, Supervision, Project Administration.<\/p>\n\n\n\n

Asaad Babker, Anass Abbas, Manar Shalabi  and Khalid Abdelsamea Mohamedahmed Funding Acquisition: Resources, Supervision.<\/p>\n\n\n\n

The final manuscript was read and approved by all authors.<\/p>\n\n\n\n

References<\/strong><\/p>\n\n\n\n

    \n
  1. Obeagu EI, Babar Q, Obeagu GU. Megaloblastic anaemia-a review. Int J Curr Res Med Sci. 2021;7(5):17-24.<\/li>\n\n\n\n
  2. Dutta TK. Megaloblastic Anemia. Ann Clin Med Case Rep. 2023;10(15):1-5.<\/li>\n\n\n\n
  3. Khajuria A, Sehrawat R. Megaloblastic anemia: An updated review. DY Patil J Health Sci. 2022;10(2):63-66.
     CrossRef <\/a><\/li>\n\n\n\n
  4. Ghafoor MB, Sarwar F, Khan S, Majeed S, Yasmeen F, Ashraf M, Abbasi S, Sami A, Riyaz N. Study of clinico-pathological profile in patients with megaloblastic anemia. Prof Med J. 2023;30(10):1270-1274.
     CrossRef <\/a><\/li>\n\n\n\n
  5. Tr\u00fceb RM, Tr\u00fceb RM. Nutritional disorders of the hair and their management. In: Nutrition for Healthy Hair: Guide to Understanding and Proper Practice. 2020:111-223.
     CrossRef <\/a><\/li>\n\n\n\n
  6. Brittenham GM, Moir-Meyer G, Abuga KM, Datta-Mitra A, Cerami C, Green R, Pasricha S-R, Atkinson SH. Biology of anemia: a public health perspective. J Nutr. 2023; 153:S7-S28.
    CrossRef <\/a><\/li>\n\n\n\n
  7. Anand I, Gupta P. How I treat anemia in heart failure. Blood. 2020;136(7):790-800.
    CrossRef <\/a><\/li>\n\n\n\n
  8. Ta\u0142asiewicz K, Kapa\u0142a A. Anemia in cancer patients: addressing a neglected issue\u2013diagnostics and therapeutic algorithm. Nowotwory J Oncol. 2023;73(5):309-316.
     CrossRef <\/a><\/li>\n\n\n\n
  9. Babker AMAA, Gameel FEMH. Molecular Characterization of Prothrombin G20210A gene Mutations in pregnant Sudanese women with spontaneous recurrent abortions. Rawal Med J. 2015;40(2):207-209.<\/li>\n\n\n\n
  10. Safiri S, Kolahi AA, Noori M, Nejadghaderi SA, Karamzad N, Bragazzi NL, Sullman MJ, Abdollahi M, Collins GS, Kaufman JS, Grieger JA. Burden of anemia and its underlying causes in 204 countries and territories, 1990\u20132019: results from the Global Burden of Disease Study 2019. J Hematol Oncol. 2021;14(1):1-16.
     CrossRef <\/a><\/li>\n\n\n\n
  11. Rabotiahov A, Kobylin O, Dudar Z, Lyashenko V. Bionic image segmentation of cytology samples method. In: 2018 14th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET). IEEE; 2018:665-670
     CrossRef <\/a><\/li>\n\n\n\n
  12. Mousavi SMH, Victorovich LV, Ilanloo A, Mirinezhad SY. Fatty Liver Level Recognition Using Particle Swarm optimization (PSO) Image Segmentation and Analysis. In: 2022 12th International Conference on Computer and Knowledge Engineering (ICCKE). IEEE; 2022:237-245.
     CrossRef <\/a><\/li>\n\n\n\n
  13. Orobinskyi P, Petrenko D, Lyashenko V. Novel Approach to Computer-Aided Detection of Lung Nodules of Difficult Location with Use of Multifactorial Models and Deep Neural Networks. In: 2019 IEEE 15th International Conference on the Experience of Designing and Application of CAD Systems (CADSM). IEEE; 2019:1-5.
    CrossRef <\/a><\/li>\n\n\n\n
  14. \u00c7al\u0131\u015fkan A. Diagnosis of malaria disease by integrating chi-square feature selection algorithm with convolutional neural networks and autoencoder network. Transactions of the Institute of Measurement and Control. 2023;45(5):975-985.
    CrossRef <\/a><\/li>\n\n\n\n
  15. \u00c7al\u0131\u015fkan A. Finding complement of inefficient feature clusters obtained by metaheuristic optimization algorithms to detect rock mineral types. Transactions of the Institute of Measurement and Control. 2023;45(10):1815-1828.
     CrossRef <\/a><\/li>\n\n\n\n
  16. Hoffbrand AV. Megaloblastic anaemia. In: Postgraduate Haematology. 2015:53-71.
     CrossRef <\/a><\/li>\n\n\n\n
  17. Wu Q, Liu J, Xu X, Huang B, Zheng D, Li J. Mechanism of megaloblastic anemia combined with hemolysis. Bioengineered. 2021;12(1):6703-6712.
     CrossRef <\/a><\/li>\n\n\n\n
  18. Chen HM, Tsao YT, Tsai SC. Automatic image segmentation scheme for counting the blood cell nuclei with megaloblastic anemia. J Med Imaging Health Inform. 2016;6(1):102-107.
     CrossRef <\/a><\/li>\n\n\n\n
  19. Abdulhay EW, Allow AG, Al-Jalouly ME. Detection of Sickle Cell, Megaloblastic Anemia, Thalassemia, and Malaria through Convolutional Neural Network. In: 2021 Global Congress on Electrical Engineering (GC-ElecEng). IEEE; 2021:21-25.
     CrossRef <\/a><\/li>\n\n\n\n
  20. Y\u0131ld\u0131z TK, Yurtay N, \u00d6ne\u00e7 B. Classifying anemia types using artificial learning methods. Eng Sci Technol Int J. 2021;24(1):50-70.
     CrossRef <\/a><\/li>\n\n\n\n
  21. Balochian S, Baloochian H. Edge detection on noisy images using Prewitt operator and fractional order differentiation. Multimed Tools Appl. 2022;81(7):9759-9770.
    CrossRef <\/a><\/li>\n\n\n\n
  22. Vajpayee P, Panigrahy C, Kumar A. Medical image fusion by adaptive Gaussian PCNN and improved Roberts operator. Signal Image Video Process. 2023;17(7):3565-3573.
     CrossRef <\/a><\/li>\n\n\n\n
  23. Trung NT, Ngan TT, Tuan TM, Nguyen TH. Combining Entropy Optimization and Sobel Operator for Medical Image Fusion. Comput Syst Sci Eng. 2023;44(1):535-544
     CrossRef <\/a><\/li>\n\n\n\n
  24. Anand A, Tripathy SS, Kumar RS. An improved edge detection using morphological Laplacian of Gaussian operator. In: 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN). IEEE; 2015:532-536.
     CrossRef <\/a><\/li>\n\n\n\n
  25. Xu Z, Ji X, Wang M, Sun X. Edge detection algorithm of medical image based on Canny operator. In: Journal of Physics: Conference Series. Vol 1955. IOP Publishing; 2021:012080.
    CrossRef <\/a><\/li>\n\n\n\n
  26. Lyashenko VV, Babker AMAA, Kobylin OA. The methodology of wavelet analysis as a tool for cytology preparations image processing. Cukurova Med J. 2016;41(3):453-463.
     CrossRef <\/a><\/li>\n\n\n\n
  27. Abu-Jassar AT, Al-Sharo YM, Lyashenko V, Sotnik S. Some Features of Classifiers Implementation for Object Recognition in Specialized Computer Systems. TEM J Technol Educ Manag Inform. 2021;10(4):1645-1654.
     CrossRef <\/a><\/li>\n\n\n\n
  28. Al-Sharo YM, Abu-Jassar AT, Sotnik S, Lyashenko V. Neural networks as a tool for pattern recognition of fasteners. Int J Eng Trends Technol. 2021;69(10):151-160.
     CrossRef <\/a><\/li>\n\n\n\n
  29. Ahmad MA, Baker JH, Tvoroshenko I, Lyashenko V. Modeling the structure of intellectual means of decision-making using a system-oriented NFO approach. Int J Emerg Trends Eng Res. 2019;7(11):460-465.
     CrossRef <\/a><\/li>\n\n\n\n
  30. Jenkin R. Contrast signal to noise ratio. Electron Imaging. 2021;33:1-6.
    CrossRef <\/a><\/li>\n\n\n\n
  31. Ortiz-Jaramillo B, Kumcu A, Platisa L, Philips W. Content-aware contrast ratio measure for images. Signal Process Image Commun. 2018;62:51-63.
    CrossRef <\/a><\/li>\n\n\n\n
  32. Khlamov S, Tabakova I, Trunova T, Deineko Z. Machine Vision for Astronomical Images Using the Canny Edge Detector. In: IX International Scientific Conference \u201cInformation Technology and Implementation” (IT&I-2022). Ceur-Ws; 2022:1-10.
     CrossRef <\/a><\/li>\n\n\n\n
  33. Khlamov S, Tabakova I, Trunova T. Recognition of the astronomical images using the Sobel filter. In: 2022 29th International Conference on Systems, Signals and Image Processing (IWSSIP). IEEE; 2022:1-4.
    CrossRef <\/a><\/li>\n\n\n\n
  34. Mittal A, Soundararajan R, Bovik AC. Making a \u201ccompletely blind\u201d image quality analyzer. IEEE Signal Process Lett. 2012;20(3):209-212
     CrossRef <\/a><\/li>\n\n\n\n
  35. Mittal A, Moorthy AK, Bovik AC. No-reference image quality assessment in the spatial domain. IEEE Trans Image Process. 2012;21(12):4695-4708
     CrossRef <\/a><\/li>\n\n\n\n
  36. Venkatanath, Narasimhan, D. Praneeth, Maruthi Chandrasekhar Bh, Sumohana S. Channappayya, and Swarup S. Medasani. Blind image quality evaluation using perception based features. In: 2015 Twenty First National Conference on Communications (NCC). IEEE; 2015:1-6.
    CrossRef <\/a><\/li>\n\n\n\n
  37. Gonzalez RC, Woods RE, Eddins SL. Digital Image Processing Using MATLAB. New Jersey: Prentice Hall; 2003.<\/li>\n\n\n\n
  38. Babker AM, Suliman RS, Elshaikh RH, Boboyorov S, Lyashenko V. Sequence of Simple Digital Technologies for Detection of Platelets in Medical Images. Biomed Pharmacol J. 2024;17(1):141-152.
     CrossRef <\/a><\/li>\n\n\n\n
  39. Navya KT, Prasad K, Singh BMK. Analysis of red blood cells from peripheral blood smear images for anemia detection: a methodological review. Med Biol Eng Comput. 2022;60(9):2445-2462.
    CrossRef <\/a><\/li>\n\n\n\n
  40. Ballar\u00f2 B, Florena AM, Franco V, Tegolo D, Tripodo C, Valenti C. An automated image analysis methodology for classifying megakaryocytes in chronic myeloproliferative disorders. Med Image Anal. 2008;12(6):703-712.
     CrossRef <\/a><\/li>\n\n\n\n
  41. Elsalamony HA. Healthy and unhealthy red blood cell detection in human blood smears using neural networks. Micron. 2016;83:32-41.
     CrossRef <\/a><\/li>\n\n\n\n
  42. Dhar P, Suganya Devi K, Satti SK, Srinivasan P. A hybrid soft attention based XGBoost model for classification of poikilocytosis blood cells. Evolving Syst. 2024;15(2):523-539.
     CrossRef <\/a><\/li>\n\n\n\n
  43. Mitra S, Das N, Dey S, Chakraborty S, Nasipuri M, Naskar MK. Cytology image analysis techniques toward automation: systematically revisited. ACM Comput Surv. 2021;54(3):1-41.
    CrossRef <\/a><\/li>\n\n\n\n
  44. Hortinela CC, Balbin JR, Fausto JC, Divina PD C, Felices JPT. Identification of abnormal red blood cells and diagnosing specific types of anemia using image processing and support vector machine. In 2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM). IEEE; 2019:1-6.
     CrossRef <\/a><\/li>\n\n\n\n
  45. Yadav V, Ganesh P, Thippeswamy G. Determination and categorization of Red Blood Cells by Computerized framework for diagnosing disorders in the blood. J Intell Fuzzy Syst. 2023;Preprint:1-13.
    CrossRef <\/a><\/li>\n\n\n\n
  46. Acharya V, Kumar P. Identification and red blood cell classification using computer aided system to diagnose blood disorders. In: 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE; 2017:2098-2104.
     CrossRef <\/a><\/li>\n\n\n\n
  47. Swaroopa HN, Jagadale BN, Farhan OAM, Alnaggar VH, Abhisheka TE. Human Epithelial Cell Image Analysis and Segmentation using Threshold Based Fusion Technique. Biomed Pharmacology J. 2024;17(1):443-452.
     CrossRef <\/a><\/li>\n\n\n\n
  48. Garg R, Sandhu AK, Kaur B, Goyal B, Dogra A. Design of Filtration Approach for Image Quality Improvement in Mango Leaf Disease Detection and Pharmaceutical Treatment. Biomed Pharmacology J. 2024;17(1):341-358.
     CrossRef <\/a><\/li>\n\n\n\n
  49. Noman KA, Yaseen AS. Microscopic Images Improvement Depending on Dark Channel Prior and Adaptive Histogram Equalization Based on the Lab Colour Model. Adv Sci Technol Res J. 2024;18(4):128-136.
    CrossRef <\/a><\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"

    Introduction Megaloblastic anemia is one of the diseases types that […]<\/p>\n","protected":false},"author":15,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[119],"tags":[],"class_list":["post-62153","post","type-post","status-publish","format-standard","hentry","category-vol17no4"],"_links":{"self":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/62153","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/users\/15"}],"replies":[{"embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/comments?post=62153"}],"version-history":[{"count":5,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/62153\/revisions"}],"predecessor-version":[{"id":63524,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/62153\/revisions\/63524"}],"wp:attachment":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/media?parent=62153"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/categories?post=62153"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/tags?post=62153"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}