Deep Learning Application in Leukemia Diagnosis

Cancer is an aggressive disease with a low median survival rate. Technically, the cost of the treatment is high due to its high recurrence and mortality rates. Accurate and early diagnosis is needed to cure cancer. Even though, there is a lot of applications in the field of medical by using Artificial Intelligence. Artificial Intelligence (AI), especially machine learning and deep learning, has found as popular application in clinical cancer researches in recent years. The prediction of cancer cells has been reached new heights, as the technology is improved day-by-day and lots of devices are invented to detect and to cure cancer cells. Artificial Intelligence (AI)assist cancer diagnosis and prognosis, specifically with regards with unprecedented accuracy, which is even higher than that of general statistical applications in Oncology. There are different types of cancer cells and to destroy these cells, humans required certain technologies to locate and identify the type of cancer. It is very complicated to cure the cancer if it is not found in the early days. This article is about the LEUKEMIA (Blood cancer) and the technologies used for curing Leukemia. The opportunities and the challenges faced in the clinical implementation of Artificial Intelligence (AI).Machine Learningis used to save a life in advance by the early cancer diagnosis and prognosis in the present and in future too.

Instruments for implementing China's economic interests in the developing countries on the example of Sub-Saharan Africa

The article examines Chinas foreign economic policy in the developing countries of Sub-Saharan Africa. The purpose of the study is to determine what financial and nonfinancial instruments the PRC uses to implement its economic interests in the region. The relevance of the study is due to the increased role of China in the economies of the region, its active investment and lending policy, which in theory can lead to the emergence of debt traps, and the spread of soft power. To determine the scale of interaction, a general statistical analysis of trade and economic cooperation between the PRC and the countries of the region is provided, and its structure is determined. The institutional framework is studied, for example, the China - Africa Cooperation Forum, and the main instruments which are used to implement the economic interests of the PRC are given, such as the Belt and Road Initiative and investments within its framework, credit policy, assistance in the creation of SEZ, individual elements of soft power. The systematization of such instruments makes it possible to assess Chinas place in the region in more detail and identify potential risks for developing countries. The implications of the utilization of such instruments in the context of the economic development and economic security of African countries are determined based on the results of the study.

Diagnostic signifcance of new hematological parameters in coronavirus infection

Bacterial infection, and as a result, sepsis is a formidable complication in patients with new coronavirus infection, and one of the leading factors in hospital mortality. In the context of the COVID-19 pandemic, the economic costs of health care for biochemical monitoring have increased signifcantly. There is a need for a new approach to the analysis and, possibly, structuring of the results of routine studies obtained through a general blood test. The aim of the work is to assess the diagnostic capabilities of the new hematological parameters NEUT-RI – neutrophil reactivity and NEUT-GI – neutrophil granularity obtained using the Sysmex XN hematological analyzer from the standpoint of sepsis diagnostics. We analyzed laboratory data from a sample of patients with coronavirus infection (n = 449). Subsequently, the general statistical population was divided into two groups according to the level of procalcitonin – PCT (cut off = 0.5 ng/ml). With PCT < 0.5 ng/ml, the presence of sepsis was considered as ‘unlikely’, with PCT > 0.5 ng/ml as ‘highly likely’ event. For mathematical data processing, traditional statistical analysis, ROC analysis and the author’s ‘probabilistic approach’ were used. According to the data obtained, at PCT < 0.5 ng/ml, there is a correlation of average strength between C-reactive protein and procalcitonin (r = 0.49, p < 0.05). In the range of high concentrations of procalcitonin (PCT > 0.5 ng/ml), the mathematical relationship between similar biochemical markers is lost. The absence of the informative value of lactate dehydrogenase in terms of the diagnosis of sepsis has been established. According to the research results, NEUT-RI ≥ 56.9 Fl with a probability of 72% (specifcity 62.0%, sensitivity 83.5%) indicates the presence of sepsis. The probability of an alternative prognosis (presence or absence of sepsis) in one or another interval of the NEUT-RI and NEUT-GI values was calculated. The narrow quantitative ranges of the NEUT-RI parameter were identifed, in which the probability of sepsis is absent – 0% (35–45 Fl) and very high – 77% (65–75 Fl).

Predictive Processing and Some Disillusions about Illusions

A number of perceptual (exteroceptive and proprioceptive) illusions present problems for predictive processing accounts. In this chapter we’ll review explanations of the Müller-Lyer Illusion (MLI), the Rubber Hand Illusion (RHI) and the Alien Hand Illusion (AHI) based on the idea of Prediction Error Minimization (PEM), and show why they fail. In spite of the relatively open communicative processes which, on many accounts, are posited between hierarchical levels of the cognitive system in order to facilitate the minimization of prediction errors, perceptual illusions seemingly allow prediction errors to rule. Even if, at the top, we have reliable and secure knowledge that the lines in the MLI are equal, or that the rubber hand in the RHI is not our hand, the system seems unable to correct for sensory errors that form the illusion. We argue that the standard PEM explanation based on a short-circuiting principle doesn’t work. This is the idea that where there are general statistical regularities in the environment there is a kind of short circuiting such that relevant priors are relegated to lower-level processing so that information from higher levels is not exchanged (Ogilvie and Carruthers, Review of Philosophy and Psychology 7:721–742, 2016), or is not as precise as it should be (Hohwy, The Predictive Mind, Oxford University Press, Oxford, 2013). Such solutions (without convincing explanation) violate the idea of open communication and/or they over-discount the reliable and secure knowledge that is in the system. We propose an alternative, 4E (embodied, embedded, extended, enactive) solution. We argue that PEM fails to take into account the ‘structural resistance’ introduced by material and cultural factors in the broader cognitive system.

The Credit Problem in parametric stress: A probabilistic approach

In this paper, we introduce a novel domain-general, statistical learning model for P&P grammars: the Expectation Driven Parameter Learner (EDPL). We show that the EDPL provides a mathematically principled solution to the Credit Problem (Dresher 1999). We present the first systematic tests of the EDPL and an existing and closely related model, the Naïve Parameter Learner (NPL), on a full stress typology, the one generated by Dresher & Kaye’s (1990) stress parameter framework. This framework has figured prominently in the debate about the necessity of domain-specific mechanisms for learning of parametric stress. The essential difference between the two learning models is that the EDPL incorporates a mechanism that directly tackles the Credit Problem, while the NPL does not. We find that the NPL fails to cope with the ambiguity of this stress system both in terms of learning success and data complexity, while the EDPL performs well on both metrics. Based on these results, we argue that probabilistic inference provides a viable domain-general approach to parametric stress learning, but only when learning involves an inferential process that directly addresses the Credit Problem. We also present in-depth analyses of the learning outcomes, showing how learning outcomes depend crucially on the structural ambiguities posited by a particular phonological theory, and how these learning difficulties correspond to typological gaps.

Enhanced Kozai–Lidov Eccentricity Oscillations in Nuclear Star Clusters

Stellar motions in the innermost parts of galactic nuclei, where the gravity of a supermassive black hole dominates, follow Keplerian ellipses to the first order of approximation. These orbits may be subject to periodic (Kozai–Lidov) oscillations of their orbital elements if some nonspherically distributed matter (e.g., a secondary massive black hole, coherent stellar subsystem, or large-scale gaseous structure) perturbs the gravity of the central supermassive black hole. These oscillations are, however, affected by the overall potential of the host nuclear star cluster. In this paper, we show that its influence strongly depends on the properties of the particular system, as well as the considered timescale. We demonstrate that for systems with astrophysically relevant parameters, the Kozai–Lidov oscillations of eccentricity can be enhanced by the extended potential of the cluster in terms of reaching significantly higher maximal values. In a more general statistical sense, the oscillations of eccentricity are typically damped. The efficiency of the damping, however, may be small to negligible for the suitable parameters of the system. This applies, in particular, in the case when the perturbing body is on an eccentric orbit.

Clipper: p-value-free FDR control on high-throughput data from two conditions

High-throughput biological data analysis commonly involves identifying features such as genes, genomic regions, and proteins, whose values differ between two conditions, from numerous features measured simultaneously. The most widely used criterion to ensure the analysis reliability is the false discovery rate (FDR), which is primarily controlled based on p-values. However, obtaining valid p-values relies on either reasonable assumptions of data distribution or large numbers of replicates under both conditions. Clipper is a general statistical framework for FDR control without relying on p-values or specific data distributions. Clipper outperforms existing methods for a broad range of applications in high-throughput data analysis.

Image coding by count sample, motivated by the mechanisms of light perception in the human visual system.

The paper presents the results of a study of input video data adequate formation/coding in modern imaging systems. Adequacy is understood here as the maximal correspondence between the ways of the radiation registration by material detectors and the ways of data coding in the retina of the human visual system. In this connection, the paper discusses general statistical issues of (photo) counts photoelectric detection and, on this basis, formalizes the concept of an ideal image formation by (ideal) visualization device. The problems arising in practice when working directly with ideal images are discussed and a method of their reduction to count sample of fixed (controllable) size, which, in fact, constitute the representation (coding) of registered data, is proposed. Results of illustrative computational experiments on count coding of the common digital images given by pixel data are presented. Examples of count samples of different sizes generated for the tested digital image are given. Based on the given results, the dependence of characteristics of sampling representations on the parameter of sample size is discussed.