{"id":56678,"date":"2024-03-20T11:34:58","date_gmt":"2024-03-20T11:34:58","guid":{"rendered":"https:\/\/biomedpharmajournal.org\/?p=56678"},"modified":"2024-04-01T19:08:06","modified_gmt":"2024-04-01T19:08:06","slug":"sequence-of-simple-digital-technologies-for-detection-of-platelets-in-medical-images","status":"publish","type":"post","link":"https:\/\/biomedpharmajournal.org\/staging\/vol17no1\/sequence-of-simple-digital-technologies-for-detection-of-platelets-in-medical-images\/","title":{"rendered":"Sequence of Simple Digital Technologies for Detection of Platelets in Medical Images"},"content":{"rendered":"\n

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

Analysis, as a component of\nthe diagnostic process, plays an important role. Moreover, such an analysis\nshould be considered not only as an element of diagnosis, but also as an\nelement of research 1-3<\/sup>. This is most relevant for the medical field, when it is\nnecessary to make the most effective decisions without dramatically affecting\nthe human body. For these purposes, it is advisable to consider digital medical\nimages. These images allow us to explore the possible problems of the issue\nbased on non-contact analysis, considering the microcosm of a person.<\/p>\n\n\n\n

Blood is primarily considered\nas the object of such research. Blood, as a liquid and mobile connective tissue\nof the internal environment of the body, allows one to judge the possibility of\nthe development of many diseases 4-<\/sup>6<\/sup> . Blood consists of a liquid medium –\nplasma, and formed elements suspended in it: erythrocytes, leukocytes and\nplatelets7<\/sup>. There are many different works that study blood\ncomponents such as red blood cells and white blood cells based on medical\ndigital images 8-10<\/sup>. This is due to the relative simplicity of such\nanalysis compared to medical imaging of blood elements such as platelets. In\nparticular, this feature is the size of platelets.<\/p>\n\n\n\n

Platelets also called\nthrombocytes are the smallest blood component produced from the very large bone\nmarrow cells called megakaryocytes under controlling of thrombopoietin hormone\nand they play a fundamental role in thrombosis and hemostasis 11<\/sup>.\nPlatelets, which circulate within the blood, are the essential mediators that\ntrigger the mechanical pathway of the coagulation cascade upon encountering any\ndamage to the blood vessels. Platelets encourage primary hemostasis via three\nmajor processes: activation, adhesion, and aggregation. When the integrity of the\nvascular endothelium is interrupted, various macromolecular elements of the\nvascular subendothelium become exposed and readily accessible to platelets 12,13<\/sup>.\nPlatelets possess important secretory functions. During the process of\nactivation, platelets express internal membrane proteins and release adhesive\nproteins, coagulation and growth factors. Some of the proteins facilitate the\ncrosstalk of platelets with leukocytes and endothelial cells 14<\/sup>. The\nplatelets function depends on the number (quantity) and structure (quality) and\nwhen platelets do not function properly, people are at risk of excessive\nbleeding due to injuries or even spontaneous bleeding 15<\/sup>. The normal\nplatelet count in humans ranges from 150\u00d7109\/L to 400\u00d7109\/L. We take into\naccount that platelets have a circulating lifespan of around 10 days, and that\nabout one third of platelets are sequestered in the spleen. A constant balance\nis, therefore, required between thrombopoiesis, and platelet consumption and\nsenescence 16<\/sup>. Low platelet concentration is called thrombocytopenia\nand is due to either decreased production or increased destruction. Elevated\nplatelet concentration is called thrombocytosis, and is either congenital,\nreactive (to cytokines), or due to unregulated production 17<\/sup>.<\/p>\n\n\n\n

Therefore, platelet counting\nis an important task in blood analysis and diagnosis of possible disease 18<\/sup>.<\/p>\n\n\n\n

Now platelets are counting is\nincluded in a complete blood count (CBC), a panel of tests often performed as\npart of a general health exam by using hematology analyzer, this technique is\nbased on the modification of the impedance of calibrated aperture soaking in an\nelectrolyte and going through a constant course delivered by two electrodes\nlocated on both sides of the aperture then count sample are counted\nautomatically 18<\/sup>. Up to date, the only \u201cGold Standard\u201d in platelet\ncounting available to assess any degree of accuracy of the automated count has\nbeen the manual phase-contrast microscopic method. The manual method itself has\nsignificant limitations in terms of performance, particularly in the area of\nimprecision 19<\/sup>.<\/p>\n\n\n\n

Based on the discussion above,\nthe main purpose of this study is to review some procedure for platelet\nidentification in medical images. In the future, this procedure will be the\nbasis for automatic platelet counting. Therefore, the basics of platelet\nidentification using image processing technologies are discussed next, the\nprocedure is summarized, and the results of the related analysis are presented.<\/p>\n\n\n\n

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

In order to identify platelets in medical images, it is advisable\nto consider some approaches to medical image processing. It should be\nemphasized that in this case it is necessary to pay attention to the so-called\nsmall-sized objects. This is based on the fact that the image of platelets\nrefers to such objects.<\/p>\n\n\n\n

A general technique for identifying objects in medical images is\nthe use of binarization of the original image. This is because the blood smear\nis usually stained for phase contrast microscopy. In this case, components of\nthe blood smear such as red blood cells, leukocytes and platelets differ\nsignificantly from the general background (plasma). Then it becomes possible to\nbinarize the image and isolate the main components of blood. An example of the\nuse of this approach is the study of M. Habibzadeh, A. Krzyzak, T. Fevens and\nA. Sadr 20 <\/sup>or B. Azam, R. J. Qureshi, Z. Jan and T. A. Khattak 21<\/sup>.\nBut in the simplest case, it is advisable to use conventional binarization by\nthreshold 22-24<\/sup>.<\/p>\n\n\n\n

However, for example, S. Rahman, B. Azam, S. U. Khan, M. Awais and\nI. Al note that for effective binarization it is necessary to normalize the\nintensity of the input image 25<\/sup>. However, even in this case it is\nimpossible to obtain an ideal resulting image. This is because many medical\nimaging devices experience non-linear brightness effects. Moreover, it can be\nenhanced as a result of uneven distribution of the coloring matter. Thus, some\ninterference occurs which introduces errors in the corresponding\nidentification. This problem can be solved by filtering the original image or processed\nimage. But then some data may be lost, as noted by various authors 26, 27<\/sup>.<\/p>\n\n\n\n

The complexity of solving the problem of binarization when\nisolating platelets in medical images is noted in 28<\/sup>. For these purposes, the\nauthors use the droplet detection method, which considers the quantitative\nassessment of clinically significant signs of such droplets.<\/p>\n\n\n\n

At the same time, the work 29<\/sup> uses segmentation and machine\nlearning procedures to solve binarization problems for medical images. For\nthese purposes, the authors pre-process the original images, removing duplicate\ndata and outliers. Ultimately, this simplifies platelet identification.\nHowever, in this case, the presence of a person is required to remove such\nunnecessary information.<\/p>\n\n\n\n

In this case, to solve the problem, various morphological\noperations are used: combining individual elements, filling empty space,\nclarifying the boundaries of objects, etc. These operations are also widely\nused in processing various medical images and more 30<\/sup>, <\/sup>31<\/sup>. In this context, we operate\nwith objects that are predominantly round or close to a circle, which makes it\neasier to use such operations for our research.<\/p>\n\n\n\n

The geometric dimensions of platelets should also be taken into\naccount. This will help separate them from the white blood cells and red blood\ncells. In general, the geometry of an object plays an important role in the\nstudy of medical images 32<\/sup>. It is also advisable to compare the obtained images at different\nstages of the study. This method can be viewed as a logical analysis of the\nrelationship between individual processing steps.<\/p>\n\n\n\n

Then, among the main stages of platelet identification one can\nhighlight: binarization, morphological analysis, taking into account the\ninfluence of the sizes of different objects and comparative analysis of images\nat intermediate stages of the study.<\/p>\n\n\n\n

Thus, a generalized algorithm for identifying platelets on digital images can be presented in accordance with Fig. 1.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 1: Generalized algorithm for platelet identification in digital medical images<\/strong><\/p>\n

<\/p>\n

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

The general mathematical formalization of the generalized algorithm for identifying platelets on digital images may be represented in next way:<\/p>\n\n\n\n

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

where<\/p>\n\n\n\n

Iv<\/sub><\/em>  \u2013 original image,<\/p>\n\n\n\n

Ib<\/sub><\/em>  \u2013 image after the binarization procedure,<\/p>\n\n\n\n

Ims<\/sub><\/em>  \u2013 image after morphological processing taking into account platelet sizes. This is an image where there are only platelets,<\/p>\n\n\n\n

   Ik<\/sub><\/em>  \u2013 comparative analysis, which allows platelets to be identified in the original image,<\/p>\n\n\n\n

   Ir<\/sub><\/em>  \u2013 the resulting image after all stages of processing.<\/p>\n\n\n\n

To implement the binarization procedure, a threshold (a<\/em>) is selected, which allows you to select only those points that belong to platelet images. This can be done based on a histogram of where the platelet images are the brightest. Then if such a threshold is reached, the point on the input image is designated 1, otherwise \u2013 0:<\/p>\n\n\n\n

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

where<\/p>\n\n\n\n

(i, j<\/em>)  \u2013 the current point of the image that is being examined.<\/p>\n\n\n\n

Morphological analysis is\nperformed based on standard image analysis techniques 21, 22, 27<\/sup>.<\/p>\n\n\n\n

At the same time, the image comparison procedure consists of comparing the original image and the image after morphological processing, taking into account the platelet size. Then the procedure for obtaining the resulting image can be expressed as follows:<\/p>\n\n\n\n

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

It is also important to\nemphasize that generalized result issues are also discussed here. This result\nwas obtained based on the analysis of at least 30 different images where\nplatelets are present. One of the typical such images is presented below. Thus,\nthe platelet identification procedure for a certain class of medical images is\nactually considered. It should be emphasized that this work does not use any\nmethods of statistical analysis and inference. The effectiveness of the\nproposed approach is determined by the sequence of implementation of known\nalgorithms, which are themselves reliable. The performance of the procedure\nconsidered is also determined by the level of platelet identification and\ncomparison of this result with known approaches (see the \u201cDiscussion\u201d section).\nAdditional research is also being carried out in the form of superimposing\nvarious noises (a few words about this below).<\/p>\n\n\n\n

At the same time, the study\nnoted the percentage of false detection of platelets and the percentage of\nmissed platelets. In general, this gives a general picture of the performance\nof the considered procedure for identifying objects such as platelets.<\/p>\n\n\n\n

To extend the related research, noisy images are also\nconsidered. To do this, various types of noise are superimposed on the original\nimages. Moreover, this overlay of noise on an image is a standard procedure\nthat is used in the development and analysis of various image processing\nprocedures. In fact, this is an artificial distortion of real images. This\nallows one to understand the limits and reliability of some image analysis\nprocedure, in this case platelet detection. However, such noise may not occur\nin real practice.<\/p>\n\n\n\n

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

Fig. 2 shows a typical image where platelets can be seen as round blue objects 33, 34<\/sup>. To the right is the original image, and to the left is part of it, as indicated by the corresponding arrow. These objects have different sizes and their colors also vary from light blue to dark blue.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 2: Example of original image with platelets.<\/strong><\/p>\n

<\/p>\n

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

The figure below shows the results of binarization of the original image Fig. 2 (for the data in the picture to the right). This binarization is carried out based on the data of the corresponding histogram. This data can be unified and generalized to automatically binarize the original image. Here, the binarization threshold is selected in such a way that all elements of the blood smear except the background (plasma) are visible in the field of view.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 3: Results of binarization of the original image.<\/strong><\/p>\n

<\/p>\n

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

The image after binarization\nhas many errors in the form of empty areas in areas of interest, as well as\nmany edge objects that may not be accurately identified. Therefore,\nmorphological operations are used to eliminate such defects (see Fig. 4, cleaned binary\nimage of blood smear). This identification\nstep can also be automated.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 4: Original image after binarization and morphological operations<\/strong><\/p>\n

<\/p>\n

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

Image in Fig. 4 includes all\nmajor blood smear objects except plasma. However, only platelets need to be isolated.\nThis sequence is implemented in two stages. First, the platelet size data in\nthe image was used (see Fig. 5a), and then compared Fig. 4 and Fig. 5a, only\nplatelets are highlighted (see Fig. 5b). This procedure can be fully automated.\nAt the same time, it is important to know the geometric dimensions of the\nplatelets in the image.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 5: Isolation of platelets<\/strong><\/p>\n

<\/p>\n

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

Platelets can now be identified in the original image. To do this,\na logical comparison of the data is made Fig. 2 (for the data in the picture to\nthe right) and Fig. 5b. The result\nis presented in Fig. 6.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 6: Platelet identification result for original image<\/strong><\/p>\n

<\/p>\n

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

It should be noted that in\nthis case, almost all platelets were identified with the exception of one,\nwhich has a non-standard geometric size. This confirms the fact that taking\ninto account platelet size geometry is one of the key factors. However, no\nfalse platelets were detected in this case.<\/p>\n\n\n\n

An analysis of the\neffectiveness of the considered procedure for identifying platelets in images\nthat are subject to various types of noise was also carried out. The final\nresults of such identification for this example are presented in Fig. 7. Here\nwe consider such noise as: Gaussian white noise with zero mean value and\nvariance 0.01; Poisson noise; multiplicative noise, with mean 0 and variance\n0.05.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 7: Results of identifying platelets in an image that are subject
to various types of noise<\/strong><\/p>\n

<\/p>\n

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

Overall, the results are satisfactory. There is some degradation in the proposed platelet identification procedure. But this deterioration is not critical, as will be shown below. Moreover, the likelihood of exposure to such noise is unknown. This is artificial noise (see comments in the previous section). In this case, a violation of the geometric dimensions of platelets was also detected. But this violation is not significant (no more than 1.3% of such distortions from the total number of platelets). There was no statistical significance between size distortion and the number of false platelet detections or platelet identification in general. These results are presented in more detail in Tabl. 1 (summarized data for all images that were considered in the work).<\/p>\n\n\n\n

Table 1: Platelet identification results based on the procedure reviewed <\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n
\n

Image type<\/strong><\/p>\n<\/td>\n

\n

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

\n

False platelet isolation, %<\/strong><\/p>\n<\/td>\n

\n

Missed platelets, %<\/strong><\/p>\n<\/td>\n

\n

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

\n

Images without noise<\/p>\n<\/td>\n

\n

less than 0.1%<\/p>\n<\/td>\n

\n

within 2-2.5%<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n<\/tr>\n

\n

Images with Gaussian white noise<\/p>\n<\/td>\n

\n

within 1.5-2%<\/p>\n<\/td>\n

\n

no more than 6.2%<\/p>\n<\/td>\n

\n

Some areas of platelets are distorted: reduced or enlarged. No more than 1%<\/p>\n<\/td>\n<\/tr>\n

\n

Images with Poisson noise<\/p>\n<\/td>\n

\n

no more than  0.5%<\/p>\n<\/td>\n

\n

no more than 6.5%<\/p>\n<\/td>\n

\n

Some areas of platelets are distorted: reduced or enlarged. No more than 1.3%<\/p>\n<\/td>\n<\/tr>\n

\n

Images with multiplicative noise<\/p>\n<\/td>\n

\n

within 10%<\/p>\n<\/td>\n

\n

within 7.5-8%<\/p>\n<\/td>\n

\n

Some areas of platelets are distorted: reduced or enlarged. No more than 1.2%<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n\n\n

From the above data it is\nclear that the main problem is missed platelets. This problem is solved at the\nstage of image processing, taking into account the geometric dimensions of\nplatelets. In particular, it is possible to isolate different groups of\nplatelets, and then, after identifying them, combine everything into one.\nHowever, platelet size and its correct accounting is one of the factors that\ndetermines the scope of application of the proposed approach. Next we will also\ndiscuss other aspects of what was discussed above.<\/p>\n\n\n\n

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

As already noted, blood smear\nanalysis and platelet identification in particular are the basis of many\nstudies.<\/p>\n\n\n\n

For example, work 35<\/sup>\nconsiders the possibility of classifying platelets based on a combination of\ntheir statistical characteristics. This approach can be used as a basis when\nimage analysis is performed taking into account the geometric dimensions of\nplatelets. But here it should be taken into account that the accuracy of such\nclassification, according to the authors, does not exceed 83.67% 35<\/sup>.\nThus, this approach may introduce errors in platelet identification.<\/p>\n\n\n\n

Study 36 <\/sup>describes\na generalized automated procedure for counting platelets in a blood smear. For\nthese purposes, platelet identification is based on the application of a\nsegmentation procedure. However, such segmentation must take into account the\ncolor conditions of the blood smear, as well as the geometric dimensions of the\nplatelets. Thus, the authors also face a number of problematic issues, which we\nalso highlight. The authors offer their own solution to such issues, which in\ngeneral does not contradict our approach.<\/p>\n\n\n\n

The paper 37 <\/sup>considered\nthe possibility of automating the counting of platelets in a blood smear to\nidentify cases of dengue. This shows the importance of the problem we examined\nin our study. The authors justify simple solutions for such analysis. The work\nnoted that the system they proposed in 11 cases out of 19 gave 100% results.\nBut this result applies only to 59% of cases. In this regard, our result is\nmore effective.  At the same time,\nplatelet skipping in other cases is 3-4%. However, the paper notes that automatic\nand manual platelet counting does not have statistical significance with a\nkappa coefficient of 0.6 3<\/sup>5<\/sup>.<\/p>\n\n\n\n

The study 38 <\/sup>focused\non platelet detection and counting. This platelet identification is based on\nmodels such as Single Shot Multibox Detector (SSD), RetinaNet, Faster_rcnn and\nYou Only Look Once_v3 (YOLO_v3). However, the authors pay attention to the\nYOLO_v3 model. As a result, more efficient platelet detection algorithms have\nbeen obtained. The modified YOLO_v3 model showed 1.8% higher average accuracy.\nThe generalized efficiency of such identification is at the level of 86%. But\nthere also remain issues of platelet false detection and missed detection.<\/p>\n\n\n\n

The work 39<\/sup>\ndiscusses platelet detection based on deep neural networks. The accuracy of\nthis detection is about 86.7-91.2%, which is a pretty good result. In this\ncase, an essential aspect of such an analysis is the possibility of overlapping\nindividual elements of a blood smear. We did not consider such aspects in our\nstudy.<\/p>\n\n\n\n

The works 28<\/sup> and 29<\/sup>\naddressed the issues of platelet detection in medical images. In 28<\/sup>\nthe authors use a droplet detection method based on clinically relevant\nfeatures. This method allows for platelet detection at a level of 96.4%. The\nbasis of such a calculation is a comparison with a similar calculation with the\nparticipation of an experienced laboratory assistant. The study 29<\/sup>\nuses various classifiers, which provide an accuracy of identification of blood\nsmear components at the level of 97-98%.<\/p>\n\n\n\n

Y. K. A. A. Atmanto, A. A.\nAbdullah, D. Muhadi and M. Arif propose a method for determining the platelet\ncount coefficient, which is analogous to the detection rate of such blood\ncomponents 40<\/sup>. This ratio is the overall ratio divided by the sample\nsize 40<\/sup>. The authors note that the total ratio of 254 samples was\n4.086. This is a significant indicator. However, such data are difficult to\ncompare with traditional platelet count summaries.<\/p>\n\n\n\n

G. Dra\u0142us, D. Mazur and A.\nCzmil use the training method using deep learning networks RetinaNet 41<\/sup>\nfor platelet recognition purposes. The accuracy of platelet recognition is at\nthe level of 92.5-97.36% (confidence threshold 0.35) 41<\/sup>. As the\nthreshold increases, the accuracy of platelet identification decreases.<\/p>\n\n\n\n

C. Briggs, P. Harrison, and S. J. Machin provide a\ncomprehensive review of various platelet counting methods 4<\/sup>2<\/sup>. In this case,\nspecial attention is paid to problematic aspects. In particular, the authors\nnote that a decrease in the number of platelets in a blood smear leads to a\ndecrease in the level of their identification. It is noted that the most\ninaccurate is the manual counting method, which leads to errors of various\nkinds at the level of 10-25%. It also talks about the influence of platelet\nsize on the level of their detection in a blood smear. The main message of the\nstudy is that platelets are more difficult to count than red or white blood\ncells 4<\/sup>2<\/sup>.<\/p>\n\n\n\n

The study 4<\/sup>3<\/sup> examines the\nreference platelet count method. The authors note that this approach showed\nacceptable identification accuracy. No exact data is provided. However, it\nshould be noted that this approach cannot be compared with our method. This is\ndue to the fact that we do not use a reference image of platelets, but\nmorphological and geometric features of platelets.<\/p>\n\n\n\n

B. Mohamed-Rachid, A. F. Raya, A. H. Sulaiman and A.\nK. Salam compare and analyze different platelet counting methods 4<\/sup>4<\/sup>. Among these methods\nare considered: optical, impedance, immunological and manual methods of\nplatelet counting. The results showed that the reliability of similarity\nbetween such methods ranges from 0.49 to 0.9 4<\/sup>4<\/sup>. The worst result is\ngiven by the impedance method, which overestimates the platelet count and at\nthe same time does not give any result in 15% of samples (in other words, the\noverall platelet detection accuracy is below the 80% level). It is also noted\nthat other authors note such a large error in the impedance method.<\/p>\n\n\n\n

The work 4<\/sup>5<\/sup> discusses the\nprocess of selecting methods for automatic platelet counting. It is noted that\nthe impedance detection method (PLT-I) can erroneously reduce platelet counts\nby as much as 23.6% 4<\/sup>5<\/sup>. Then the level of platelet\ndetection decreases to 76.4% or lower. However, it is also emphasized that\nthere are few studies comparing the accuracy of platelet counts.<\/p>\n\n\n\n

A generalized comparison of our platelet identification approach with several other methods is also presented below.<\/p>\n\n\n\n

Table 2: Comparison of platelet identification results presented on a medical image.<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

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

\n

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

\n

False platelet isolation, %<\/strong><\/p>\n<\/td>\n

\n

Missed platelets, %<\/strong><\/p>\n<\/td>\n

\n

Generalized identification accuracy, %<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Proposed approach<\/p>\n<\/td>\n

\n

less than 0.1%<\/p>\n<\/td>\n

\n

within 2-2.5%<\/p>\n<\/td>\n

\n

97.4%<\/p>\n<\/td>\n<\/tr>\n

\n

From [35]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

83.67%<\/p>\n<\/td>\n<\/tr>\n

\n

From [37]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

3-4%<\/p>\n<\/td>\n

\n

59%<\/p>\n<\/td>\n<\/tr>\n

\n

From [38]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

4-5%<\/p>\n<\/td>\n

\n

86%<\/p>\n<\/td>\n<\/tr>\n

\n

From [39]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

86.7-91.2%<\/p>\n<\/td>\n<\/tr>\n

\n

From [29]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

97-98%<\/p>\n<\/td>\n<\/tr>\n

\n

From [41]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

92.5-97.36%<\/p>\n<\/td>\n<\/tr>\n

\n

Manual counting method from [42]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

75-90%<\/p>\n<\/td>\n<\/tr>\n

\n

Impedance method from [44]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

under 80%<\/p>\n<\/td>\n<\/tr>\n

\n

Impedance method (PLT-I) from [45]\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

\u2013<\/p>\n<\/td>\n

\n

76.4% or lower<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n\n\n

Tabl. 2 shows that the\nproposed approach is one of the top three methods for identifying platelets in\nmedical images. Also noteworthy is the effectiveness of platelet detection\nunder various interference conditions (see Tabl. 1). At the same time, the\nconsidered approach is distinguished by the simplicity of its implementation.<\/p>\n\n\n\n

First of all, our approach when working with original\nimages (where we do not artificially degrade such images with noise for\nresearch purposes) is at the level of developments that are presented in 29,41<\/sup>.\nOur result with such studies is at the level of 97.4% platelet identification.<\/p>\n\n\n\n

In the case of various interferences, we obtain a\nplatelet detection result of at least 82%. This result is comparable to the\nresults from 35<\/sup>. The result obtained is also better than the manual\ncounting method and impedance method (see Tabl. 2), which give less\nthan 82% detection of platelets.<\/p>\n\n\n\n

Thus, in general, it should be noted that our results\nare acceptable and allow us to create an automated system for identifying and\ncounting platelets.<\/p>\n\n\n\n

If we talk about the basics of\nsuch automation, we should note the possibility of its implementation based on\nthe simplicity of the proposed approach. It should also be noted that our\napproach is clearly structured, which is based on the appropriate mathematical\nformalization. This allows us to apply different levels of automation. Such\naspects will be considered in more detail in our further studies.<\/p>\n\n\n\n

As for other problematic aspects in platelet\nidentification, the following should be said. First of all, this concerns the\nproblem of geometric dimensions of platelets. In this case, a preliminary\nprocedure for analyzing platelet geometry and morphology can be introduced.\nThen, at the stage of applying platelet identification algorithms based on\ntheir geometry, it is possible to reduce the number of false results and\nincrease the overall detection accuracy. The number of false results can also\nbe reduced by creating a platelet bank for their subsequent identification with\nreal data. You can also use algorithms based on the theory of fuzzy sets. This\nwill speed up the platelet identification process and improve overall results.\nThe use of fuzzy set theory approaches will facilitate the consideration of\nvarious types of images, the selection of the necessary steps to generate a\ngeneral platelet detection procedure. To implement a friendly platelet\ndetection procedure, it is proposed to use a potential communication interface\nin the implementation of such an analysis. This will allow us to understand and\nidentify bottlenecks in the proposed approach and eliminate them.<\/p>\n\n\n\n

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

The paper examines various problematic aspects of platelet\nidentification in digital medical images. Particular attention is paid to\nsimple methods of digital image processing. A sequence of actions has been\nproposed that allows for effective identification of platelets. The strength of the\nproposed approach is its simplicity and high efficiency in detecting platelets\nunder various interferences that are possible in digital images. Among the\nproblematic aspects of the proposed approach is the need to clearly take into\naccount the geometric dimensions of platelets. A number of experiments were\ncarried out on real images. The results obtained are acceptable and can be used\nas the basis for an automated blood smear analysis system.<\/p>\n\n\n\n

At the same time, among\nthe potential directions of this research and areas for improving the proposed\nprocedure, we highlight:<\/p>\n\n\n\n

Ddevelopment of a preliminary procedure for automatically determining platelet size in each series of corresponding input medical images;<\/p>\n\n\n\n

Adaptation of the proposed approach to other types of input images.<\/p>\n\n\n\n

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

None<\/p>\n\n\n\n

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

There is no conflict of\ninterest.<\/p>\n\n\n\n

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

There are no funding Sources.<\/p>\n\n\n\n

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

  1. Rajula, H. S. R., Verlato, G., Manchia, M., Antonucci, N., & Fanos, V. (2020). Comparison of conventional statistical methods with machine learning in medicine: diagnosis, drug development, and treatment. Medicina, 56(9), 455.
    CrossRef<\/a><\/li>
  2. Schubert, C. (2011). Making sure. A comparative micro-analysis of diagnostic instruments in medical practice. Social science & medicine, 73(6), 851-857.
     CrossRef <\/a><\/li>
  3. Tsuneki, M. (2022). Deep learning models in medical image analysis. Journal of Oral Biosciences, 64(3), 312-320.
    CrossRef <\/a><\/li>
  4. Aitekenov, S., Sultangaziyev, A., Abdirova, P., Yussupova, L., Gaipov, A., Utegulov, Z., & Bukasov, R. (2023). Raman, Infrared and Brillouin spectroscopies of biofluids for medical diagnostics and for detection of biomarkers. Critical Reviews in Analytical Chemistry, 53(7), 1561-1590.
     CrossRef <\/a><\/li>
  5. Babker, A. M. (2020). The role of Inherited Blood Coagulation Disorders in Recurrent Miscarriage Syndrome. Journal of Critical Reviews, 7(1), 16-20.<\/li>
  6. Rabotiahov, A., Kobylin, O., Dudar, Z., & Lyashenko, V. (2018, February). Bionic image segmentation of cytology samples method. In 2018 14th International Conference on Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET) (pp. 665-670). IEEE.
     CrossRef <\/a><\/li>
  7. Reece, W. O. (2015). The composition and functions of blood. Reece, WO; Erickson, HH; Goff, JP; Uemura, EE Duckes\u2019 Physiology of Domestic Animals 13th Edition, Wiley Blackwell, OX, UK, 114-136.<\/li>
  8. Rahadi, I., Choodoung, M., & Choodoung, A. (2020, May). Red blood cells and white blood cells detection by image processing. In Journal of Physics: Conference Series, 1539(1), 012025.
     CrossRef <\/a><\/li>
  9. Da Costa, L. (2015). Digital image analysis of blood cells. Clinics in laboratory medicine, 35(1), 105-122.
     CrossRef <\/a><\/li>
  10. Lyashenko, V. V., Babker, A. M. A. A., & Kobylin, O. A. (2016). The methodology of wavelet analysis as a tool for cytology preparations image processing. Cukurova Medical Journal, 41(3), 453-463.
     CrossRef <\/a><\/li>
  11. Periayah, Mercy Halleluyah et al. (2017). Mechanism Action of Platelets and Crucial Blood Coagulation Pathways in Hemostasis. International journal of hematology-oncology and stem cell research, 11(4), 319-327.<\/li>
  12. Zhang, Y., Ehrlich, S. M., Zhu, C., & Du, X. (2022). Signaling mechanisms of the platelet glycoprotein Ib-IX complex. Platelets, 33(6), 823-832.
     CrossRef <\/a><\/li>
  13. Rolling, C. C., & et al.. (2023). P2Y12 Inhibition Suppresses Proinflammatory Platelet\u2013Monocyte Interactions. Thrombosis and Haemostasis, 123(02), 231-244.
    CrossRef <\/a><\/li>
  14. Schrottmaier, W. C., Mussbacher, M., Salzmann, M., & Assinger, A. (2020). Platelet-leukocyte interplay during vascular disease. Atherosclerosis, 307, 109-120.
     CrossRef <\/a><\/li>
  15. Haley, K. M. (2020). Platelet disorders. Pediatrics in review, 41(5), 224-235.
     CrossRef <\/a><\/li>
  16. Daly, M. E. (2011). Determinants of platelet count in humans. Haematologica, 96(1), 10. 10-3.
     CrossRef <\/a><\/li>
  17. Assinger, A. (2014). Platelets and infection\u2013an emerging role of platelets in viral infection. Frontiers in immunology, 5, 649.
     CrossRef <\/a><\/li>
  18. Mustafa, M. E., Mansoor, M. M., Mohammed, A., & Babker, A. A. (2015). Evaluation of platelets count and coagulation parameters among patients with liver disease. World Journal of Pharmaceutical Research, 4(10), 360-368.<\/li>
  19. Bakhubaira S (2013) Automated Versus Manual Platelet Count in Aden. J Clin Exp Pathol 3: 149.
     CrossRef <\/a><\/li>
  20. Habibzadeh, M., Krzyzak, A., Fevens, T., & Sadr, A. (2011, March). Counting of RBCs and WBCs in noisy normal blood smear microscopic images. In Medical Imaging 2011: Computer-Aided Diagnosis, 7963, 1009-1019.
     CrossRef <\/a><\/li>
  21. Azam, B., Qureshi, R. J., Jan, Z., & Khattak, T. A. (2014). Color based segmentation of white blood cells in blood photomicrographs using image quantization. Res J Recent Sciences, 2277, 2502-9.<\/li>
  22. Lyashenko, V., Kobylin, O., & Baranchykov, Y. (2018, October). Ideology of Image Processing in Infocommunication Systems. In 2018 International Scientific-Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T) (pp. 47-50). IEEE.
     CrossRef <\/a><\/li>
  23. Savanevych, V., Khlamov, S., Briukhovetskyi, O., Trunova, T., & Tabakova, I. (2023). Mathematical Methods for an Accurate Navigation of the Robotic Telescopes. Mathematics, 11(10), 2246.
     CrossRef <\/a><\/li>
  24. Rajendran, S., & Kumar, E. S. (2019, July). Leukocytes Classification and Segmentation in Microscopic Blood Smear Image. In 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) (Vol. 1, pp. 1064-1068). IEEE.
     CrossRef <\/a><\/li>
  25. Rahman, S., Azam, B., Khan, S. U., Awais, M., & Ali, I. (2021). Automatic identification of abnormal blood smear images using color and morphology variation of RBCS and central pallor. Computerized Medical Imaging and Graphics, 87, 101813.
     CrossRef <\/a><\/li>
  26. Romero-Rond\u00f3n, M. F., Sanabria-Rosas, L. M., Bautista-Rozo, L. X., & Mendoza-Castellanos, A. (2016). Algorithm for detection of overlapped red blood cells in microscopic images of blood smears. Dyna, 83(198), 187-194.
     CrossRef <\/a><\/li>
  27. Mohammed, E. A., Mohamed, M. M., Far, B. H., & Naugler, C. (2014). Peripheral blood smear image analysis: A comprehensive review. Journal of Pathology Informatics, 5(1), 9.
     CrossRef <\/a><\/li>
  28. Mayrose, H., Niranjana, S., Bairy, G. M., Edwankar, H., Belurkar, S., & Saravu, K. (2021, July). Computer Vision Approach for the detection of Thrombocytopenia from Microscopic Blood Smear Images. In 2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) (pp. 1-5). IEEE.
     CrossRef <\/a><\/li>
  29. Kovalenko, S., Kovalenko, S., Mikhnova, O., Kovalenko, A., Pelikh, D., & Severin, V. (2023, October). An Approach to Blood Cell Classification Based on Object Segmentation and Machine Learning. In 2023 IEEE 4th KhPI Week on Advanced Technology (KhPIWeek) (pp. 1-6). IEEE.
     CrossRef <\/a><\/li>
  30. Firoz, R., Ali, M. S., Khan, M. N. U., Hossain, M. K., Islam, M. K., & Shahinuzzaman, M. (2016). Medical image enhancement using morphological transformation. Journal of Data Analysis and Information Processing, 4(1), 1-12.
     CrossRef <\/a><\/li>
  31. Mousavi, S. M. H., & Lyashenko, V. (2017, November). Extracting old persian cuneiform font out of noisy images (handwritten or inscription). In 2017 10th Iranian Conference on Machine Vision and Image Processing (MVIP) (pp. 241-246). IEEE.
     CrossRef <\/a><\/li>
  32. Mittal, A., Dhalla, S., Gupta, S., & Gupta, A. (2022). Automated analysis of blood smear images for leukemia detection: a comprehensive review. ACM Computing Surveys (CSUR), 54(11s), 1-37.
     CrossRef <\/a><\/li>
  33. Mousavi, S. M. H., Victorovich, L. V., Ilanloo, A., & Mirinezhad, S. Y. (2022, November). Fatty Liver Level Recognition Using Particle Swarm optimization (PSO) Image Segmentation and Analysis. In 2022 12th International Conference on Computer and Knowledge Engineering (ICCKE) (pp. 237-245). IEEE.
     CrossRef <\/a><\/li>
  34. Uchqun o\u2018g\u2018li, B. S., Valentin, L., & Vyacheslav, L. (2023). Pre-processing of digital images to improve the efficiency of liver fat analysis. Multidisciplinary Journal of Science and Technology, 3(1), 107-114.<\/li>
  35. Fitri, Z. E., Purnama, I. K. E., Pramunanto, E., & Pumomo, M. H. (2017, August). A comparison of platelets classification from digitalization microscopic peripheral blood smear. In 2017 International Seminar on Intelligent Technology and Its Applications (ISITIA) (pp. 356-361). IEEE.
     CrossRef <\/a><\/li>
  36. Dey, R., Roy, K., Bhattacharjee, D., Nasipuri, M., & Ghosh, P. (2015, September). An automated system for segmenting platelets from microscopic images of blood cells. In 2015 International Symposium on Advanced Computing and Communication (ISACC) (pp. 230-237). IEEE.
     CrossRef <\/a><\/li>
  37. Lazuardi, L., Sanjaya, G. Y., Candradewi, I., & Holmner, \u00c5. (2013). Automatic platelets counter for supporting dengue case detection in primary health care in indonesia. In 14th World Congress on Medical and Health Informatics (MEDINFO), AUG 20-23, 2013, Copenhagen, DENMARK (pp. 585-588). IOS Press.<\/li>
  38. Liu, R., Ren, C., Fu, M., Chu, Z., & Guo, J. (2022). Platelet Detection Based on Improved YOLO_v3. Cyborg and Bionic Systems (Washington, DC), 2022, 9780569-9780569.
     CrossRef <\/a><\/li>
  39. Lee, S. J., Chen, P. Y., & Lin, J. W. (2022). Complete blood cell detection and counting based on deep neural networks. Applied Sciences, 12(16), 8140.
     CrossRef <\/a><\/li>
  40. Atmanto, Y. K. A. A., Abdullah, A. A., Muhadi, D., & Arif, M. (2022). Determination of Platelet Count Estimation Factor on Peripheral Blood Smear Confirmation Using Field Number 22 Microscope. Indonesian journal of clinical pathology and medical laboratory, 29(1), 24-28.
     CrossRef <\/a><\/li>
  41. Dra\u0142us, G., Mazur, D., & Czmil, A. (2021). Automatic detection and counting of blood cells in smear images using retinanet. Entropy, 23(11), 1522.
     CrossRef <\/a><\/li>
  42. Briggs, C., Harrison, P., & Machin, S. J. (2007). Continuing developments with the automated platelet count 1. International journal of laboratory hematology, 29(2), 77-91.
     CrossRef <\/a><\/li>
  43. Harrison, P., Ault, K. A., Chapman, S., Charie, L., Davis, B., Fujimoto, K., … & International Society of Laboratory Hematology Task Force for the Reference Platelet Count. (2001). An interlaboratory study of a candidate reference method for platelet counting. American journal of clinical pathology, 115(3), 448-459.
     CrossRef <\/a><\/li>
  44. Mohamed-Rachid, B., Raya, A. F., Sulaiman, A. H., & Salam, A. K. (2015). Comparative analysis of four methods for enumeration of platelet counts in thrombocytopenic patients. Journal of Applied Hematology, 6(3), 119-124.
     CrossRef <\/a><\/li>
  45. Wang, Z., Jin, X., Wang, S., You, Q., Wang, J., & Xu, D. (2023). Selection of Automated Platelet Counting Methods Based on Mean Platelet Volume (MPV). Clinical Laboratory, 69(5), 906.
     CrossRef <\/a><\/li><\/ol>\n","protected":false},"excerpt":{"rendered":"

    Introduction Analysis, as a component of the diagnostic process, plays […]<\/p>\n","protected":false},"author":15,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[113],"tags":[],"class_list":["post-56678","post","type-post","status-publish","format-standard","hentry","category-vol17no1"],"_links":{"self":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/56678","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=56678"}],"version-history":[{"count":5,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/56678\/revisions"}],"predecessor-version":[{"id":57402,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/56678\/revisions\/57402"}],"wp:attachment":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/media?parent=56678"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/categories?post=56678"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/tags?post=56678"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}