Mass Segmentation Research Articles

Entropy Based Segmentation Model for Kidney Stone and Cyst on Ultrasound Image

Segmentation of abnormal masses in kidney images is a tough task. One of the main challenges is the presence of speckle noise, which will restrain the valuable information for the medical practitioners. Hence, the detection and segmentation of the affected regions vary in accuracies. The proposed model includes pre-processing and segmentation of the diseased region. The pre-processing consists of Gaussian filtering and Contrast Limited Adaptive Histogram Equalization (CLHE) to improve the clarity of the images. Further, segmentation has been done based on the entropy of the image and gamma correction has been done to improve the overall brightness of the images. An optimal global threshold value is selected to extract the region of interest and measures the area. The model is analyzed with statistical parameters like Jaccard index and Dice coefficient and compared with the ground truth images. To check the accuracy of the segmentation, relative error is calculated. This framework can be used by radiologists in diagnosing kidney patients

СОЦИАЛЬНАЯ СПРАВЕДЛИВОСТЬ В МАССОВОМ ВОСПРИЯТИИ И ЦЕННОСТНЫХ ОРИЕНТАЦИЯХ РОССИЯН

Objective of the study is to identify ideas about social justice in the mass consciousness of Russians. The article provides a detailed analysis of how the multidimensional space of social inequalities is reflected in the mass perceptions and value consciousness of Russians, how it has changed in recent years, how it is differentiated in different groups, and what the normative representations of our fellow citizens about inequalities look like. The methodological basis of the research. The ideas of social justice in the mass consciousness of Russians in this article are measured using the following indicators: 1) the most painful, in the opinion of Russians, inequalities for society as a whole and for them personally; 2) the most painful inequalities for society as a whole in the views of different strata; 3) Russians' ideas about the factors of life success; 4) Russians' assessment of changes in inequality and equity over the past 5–7 years; 5) the principles of a fair society in the views of Russians; 6) the dynamics of choice in the dilemma “equality of opportunity – equality of income”. Research results. The problem of social inequalities is widespread for Russian society not only in terms of their objective depth, but also in terms of the perception of this problem by the population as particularly painful. Mass segments of the population see the state as the main factor in its solution. The dynamics of the situation shows that the potential for using inequalities as a productivity incentive is gradually decreasing: there is a decrease in tolerance both to those monetary inequalities that previously seemed to the population rather legitimate, and to various manifestations of non-monetary inequalities based on income inequality. On the other hand, some Russians, especially representatives of the upper stratum, still maintain tolerance to the manifestations of inequalities arising on just grounds, and also to a greater extent share the idea of meritocratic grounds for inequalities in modern Russian society. Thus, they continue to be the social base of support for the vector of development based on the principles of differentiation of labor results, but with the initial equality of opportunities and the stimulating role of inequalities. At the same time, in the lower and partly in the middle stratum of society, the willingness to support such a vector of development is decreasing. And this may have a negative impact on the ability to solve the strategic task set for the country – the task of “breakthrough” development.   Prospects of the study are related to further analysis of the perception of social inequalities by Russians and the dynamics of these perceptions, as well as their relationship with the socio-political attitudes of representatives of various social groups in modern Russian society.

A frequency split trimming technique for axisymmetric shell structures

Axisymmetric shell structures are characterized by the presence of flexural modes which occur in degenerate pairs. However, since no practically realized structure is perfectly axisymmetric, the frequencies constituting a mode pair become unequal and causes what is commonly termed as “frequency split” between the modes. In applications such as vibratory gyroscopes, it is desired that the frequencies of the working pair of modes be equal. This work proposes an easily implementable (particularly in the industry) technique which reduces frequency split of a target mode pair. To address the frequency split trimming problem, this work investigates a model that describes the planar dynamics of a vibrating ring (which is prototypical to axisymmetric shell structures), with added mass segments. The effects of mass, as well as span, of an added segment on the ring’s natural frequencies and mode shapes are brought out. Novelties of the proposed trimming technique are that it employs added mass in the form of segments and that it has a negligible effect on the axes of the structure’s mode shapes. The technique is extended to general axisymmetric bodies, and it is validated experimentally for the case of a hemispherical resonator.

Impact of gastrectomy on body composition within 1month in patients with gastric cancer.

The present study examined the changes in and risk factors for body composition (BC) during the first postoperative month when dynamic biological reactions occur. We retrospectively assessed 202 patients who underwent gastrectomy. The BC was assessed using a bioelectrical impedance analysis and evaluated within 1month preoperatively, 1week postoperatively, and 1month postoperatively. Multiple regression analyses were performed to identify predictive factors for BC change. The mean reduction rate in BC at 1month postoperatively was - 6.0, - 10.5, - 5.6, - 1.1, - 10.1, and + 1.2% for body weight, body fat, skeletal muscle, bone mineral, extracellular water/total body water, and the whole-body phase angle, respectively. A multiple regression analysis revealed that independent risk factors for weight loss were complications, operative time, and type of gastrectomy (P = 0.004, 0.011, 0.015, respectively), and those for skeletal muscle loss were complications and gastrectomy type (P = 0.002, 0.010, respectively). A segmental lean mass analysis revealed that the lower limbs were markedly reduced at 1week postoperatively (- 8.0%), and these independent risk factors were the female sex and Stage II/III disease (P = 0.008, 0.036, respectively). Detailed analyses of BC might help elucidate the mechanisms underlying postoperative physical changes, which might be useful for perioperative management.

Composite landslide in the dynamic alpine conditions: a case study of Urbas landslide

The alpine environment is characterized by complex geology, high-energy terrain, deeply incised river valleys with high erosional potential, extreme weather conditions and dynamic geomorphic processes. Such settings provide favourable conditions for the formation of composite landslides rather than individual slope mass movement phenomena. As an example, we present the kinematics of the composite landslide Urbas in the North of Slovenia which developed in the complex geological and morphological settings characteristic of the alpine environment. The research combines several monitoring techniques and involves the integration of both surface and subsurface displacements measured in the landslide area. The results indicate that the composite sliding process consists of several simultaneous and interrelated types of movements occurring in different segments of the unstable mass that are governed by different mechanisms of displacements, such as rockfall, sliding and debris flow. The kinematic characteristics of a deep-seated landslide that formed in such conditions vary spatially, but is rather homogenuous vertically, indicating translational type of movement. Spatial kinematic heterogeneity is primarily related to the diverse terrain topography, reflecting in different displacement trends. Based on the revealed kinematic proprieties of the sliding material, the sediment discharge illustrates the sliding material balance which estimates the volume of the retaining material that represents the potential for slope mass movement events of larger scales.

Segmentation of Breast Masses in Digital Mammography Based on U-Net Deep Convolutional Neural Networks

Segmentation of Breast Masses in Digital Mammography Based on U-Net Deep Convolutional Neural Networks

Phase Angle Association with Dietary Habits and Metabolic Syndrome in Diabetic Hypertensive Patients: A Cross-Sectional Study.

Phase angle (PhA) levels are often lower than normal because both disease-specific parameters and disease-related inflammatory status, metabolic syndrome (MetS) included, can affect PhA. Therefore, the aim of this cross-sectional study was to compare body composition, metabolic profile and dietary patterns of participants with arterial hypertension (AH), type 2 diabetes mellitus (T2DM) and MetS with regard to PhA values. A total of 208 participants were included, of whom 53.6% were males. For each participant, data about body composition and anthropometric parameters, clinical and laboratory parameters, as well as food frequency questionnaire (FFQ) and Mediterranean Diet Serving Score (MDSS) were obtained. MC-780 Multi Frequency Segmental Body Mass Analyzer (Tanita) was used to assess body composition. Furthermore, waist-to-hip ratio (WHR) and waist-to-height ratio (WHtR) were calculated. The results showed that 75 (36.06%) participants had low PhA values and 133 (63.94%) had high PhA values. Participants with higher PhA values had significantly higher body fat percentage (p = 0.04), fat-free mass (kg; p < 0.001), muscle mass (kg; p < 0.001), skeletal muscle mass (% and kg; p < 0.001), sarcopenic index (SMI; p < 0.001) and mid-upper arm circumference (MUAC; p = 0.04), as well as lower fat mass percentage (p = 0.04). Regarding food frequency consumption, significantly higher intakes of red meat (p = 0.003), poultry (p = 0.02) and fast food (p = 0.003) were noticed in participants with higher PhA values. Adherence to the Mediterranean Diet (MeDi) was exceptionally low in both groups of participants, with significantly higher fish intake noticed in participants with high PhA (p = 0.03). In conclusion, our results showed that body composition could be the indicator of PhA in MetS as well as overall low adherence to the MeDi principles. These findings highlight the importance of adequate nutritional strategies and novel approaches to maintaining optimal body composition and adopting proper eating habits within the framework of one’s disease.

Auto-DenseUNet: Searchable neural network architecture for mass segmentation in 3D automated breast ultrasound.

Accurate segmentation of breast mass in 3D automated breast ultrasound (ABUS) plays an important role in breast cancer analysis. Deep convolutional networks have become a promising approach in segmenting ABUS images. However, designing an effective network architecture is time-consuming, and highly relies on specialist's experience and prior knowledge. To address this issue, we introduce a searchable segmentation network (denoted as Auto-DenseUNet) based on the neural architecture search (NAS) to search the optimal architecture automatically for the ABUS mass segmentation task. Concretely, a novel search space is designed based on a densely connected structure to enhance the gradient and information flows throughout the network. Then, to encourage multiscale information fusion, a set of searchable multiscale aggregation nodes between the down-sampling and up-sampling parts of the network are further designed. Thus, all the operators within the dense connection structure or between any two aggregation nodes can be searched to find the optimal structure. Finally, a novel decoupled search training strategy during architecture search is also introduced to alleviate the memory limitation caused by continuous relaxation in NAS. The proposed Auto-DenseUNet method has been evaluated on our ABUS dataset with 170 volumes (from 107 patients), including 120 training volumes and 50 testing volumes split at patient level. Experimental results on testing volumes show that our searched architecture performed better than several human-designed segmentation models on the 3D ABUS mass segmentation task, indicating the effectiveness of our proposed method.

A novel approach reveals underestimation of productivity in the globally important macroalga, Ascophyllum nodosum

Ascophyllum nodosum (L.) Le Jolis (Fucales, Fucaceae) is a modular intertidal brown alga that has the particularity of forming an air bladder once a year at the apical tip of the growing shoots. This characteristic provides a means for aging and estimating the growth of individuals. While it has long been recognized that growth can occur in older parts of the frond, this has not been properly assessed until now and has largely been overlooked when calculating the productivity of the species. Recent studies have suggested that the growth and elongation of older segments is minimal and thus has been used to infer past environmental conditions. Here we assessed the length and mass of successive internodal segments from 25 sites spread over both sides of the North Atlantic, covering a wide portion of the distribution of the species. By calculating the ratio of the mass and length of a segment divided by the segment produced the following year, we established that internodal segments continue accumulating mass for 1–5 years and increase in length for 1–3 years at most sites. Segments can almost triple their mass during their second year and more than double their length. These results indicate that previous productivity and growth estimates for A. nodosum based on apical growth alone greatly underestimate the true productivity of the species and its role in coastal carbon cycling. Furthermore, because they grow over several years, internodal segments should not be used to infer past environmental conditions or to reconstruct growth patterns over time.

Segmentation of kidney mass using AgDenseU-Net 2.5D model

The Kidney and Kidney Tumor Segmentation Challenge 2021 (KiTS21) released a kidney CT dataset with 300 patients. Unlike KiTS19, KiTS21 provided a cyst category. Therefore, the segmentation of kidneys, tumors, and cysts will be able to assess the complexity and aggressiveness of kidney mass. Deep learning models can save medical resources, but 3D models still have some disadvantages, such as the high cost of computing resources. This paper proposes a scheme that saves computing resources and achieves the segmentation of kidney mass in two steps. First, we preprocess the kidney volume data using the automatic down-sampling method of 3D images, reducing the volume while preserving the feature information. Second, we finely segment kidneys, tumors, and cysts using the AgDenseU-Net (Attention gate DenseU-Net) 2.5D model. KiTS21 proposed using Hierarchical Evaluation Classes (HECs) to compute a metric for the superset: the HEC of kidney considers kidneys, tumors, and cysts as the foreground to compute segmentation performance; the HEC of kidney mass considers both tumor and cyst as the foreground classes; the HEC of tumor considers tumor as the foreground only. For KiTS21, our model achieved a dice score of 0.971 for the kidney, 0.883 for the mass, and 0.815 for the tumor. In addition, we also tested segmentation results without HECs, and our model achieved a dice score of 0.950 for the kidney, 0.878 for the tumor, and 0.746 for the cyst. The results demonstrate that the method proposed in this paper can be used as a reference for kidney tumor segmentation.

Volume-awareness and outlier-suppression co-training for weakly-supervised MRI breast mass segmentation with partial annotations

Segmenting breast mass from magnetic resonance imaging (MRI) scans is an important step in the breast cancer diagnostic procedure for physicians and computer-aided diagnosis systems. Sufficient high-quality annotation is essential for establishing an automatic segmentation model, particularly for MRI breast masses with complex backgrounds and various sizes. In this study, we have proposed a novel approach for training an MRI breast mass segmentation network with partial annotations and reinforcing it with two weakly supervised constraint losses. Specifically, following three user-friendly partial annotation methods were designed to alleviate annotation costs: single-slice, orthogonal slice, and interval slice annotations. With the guidance of partial annotations, we first introduced a volume awareness loss that supports the additional constraint for masses with various scales. Moreover, to reduce false-positive predictions, we proposed an end-to-end differentiable outlier-suppression loss to suppress noise activation outside the target during training. We validated our method on 140 patients. The Dice similarity coefficient (DSC) of the proposed three partial annotation methods are 0.674, 0.835, and 0.837 respectively. Quantitative and qualitative evaluations demonstrate that our method can achieve competitive performance compared to state-of-the-art methods with complete annotations.

A Case Report of an Advanced Stage Gastrointestinal Stromal Tumor Successfully Treated by Surgery and Imatinib

Background: The most prevalent gastrointestinal sarcoma is a gastrointestinal stromal tumor.It is frequently misdiagnosed due to its indolent symptoms, which only manifest at an advanced and potentially incurable stage.&#x0D; Case Report: This case report is that ofa recent case of a GIST of gastric origin. Itdiscusses the case of a 56-year-old, non-smoking male with no comorbiditieswho presented to the emergency department with severe colicky intermittent adnominal pain that had occurred over the past three days, approximately three years ago. On September3, 2019, the patient underwent laparotomy in which a mass and related small bowel segment (the part of the omentum) was removed. Later, the pathology profile revealed a neoplasm of the small bowel-Ileum, Gastrointestinal stromal tumor (GIST) with a high-risk tumor of stage 4 with no recorded nodular involvement and no recorded metastasis pT4 pNxpMx but with clear margins. Moreover, the tumor markers KIT (CD117), CD34, and DOG1 (ANO1) were found to be positive. Ki67 was noted up to 35%. However, S-100 and SMA were found to be negative. On gross examination, the lesion's greatest dimension was 11 cm, and other dimensions were 9x6 cm. The tumor had a spindle-shaped morphology. On the basis of these laboratory findings and pathology profile, the patient's diagnosis was a Gastrointestinal Stromal tumor thatwas managed viasurgery. At that time, the patient was also prescribed Imatinib 400 mg. It has been three years since then, our patient is still alive, and no cancer recurrence has been reported yet.&#x0D; Conclusion: This case report revealed that interventional radiology's early engagement with the surgical procedure was the cornerstone of our patient's effective treatment and should be investigated at different stages of the gastrointestinal tumor.

Breast Sentinel Lymph Node Cancer Detection from Mammographic Images Based on Quantum Wavelet Transform and an Atrous Pyramid Convolutional Neural Network

This study proposes an optimal approach to reduce noise in mammographic images and to identify salt-and-pepper, Gaussian, Poisson, and impact noises to determine the exact mass detection operation after these noise reductions. It therefore offers a method for noise reduction operations called quantum wavelet transform filtering and a method for precision mass segmentation called the image morphological operations in mammographic images based on the classification with an atrous pyramid convolutional neural network (APCNN) as a deep learning model. The hybrid approach called a QWT-APCNN is evaluated in terms of criteria compared with previous methods such as peak signal-to-noise ratio (PSNR) and mean-squared error (MSE) in noise reduction and accuracy of detection for mass area recognition. The proposed method presents more performance of noise reduction and segmentation in comparison with state-of-the-art methods. In this paper, we used the APCNN based on the convolutional neural network (CNN) as a new deep learning method, which is able to extract features and perform classification simultaneously, but it is intended as far as possible, empirically for the purpose of this research to be able to determine breast cancer and then identify the exact area of the masses and then classify them according to benign, malignant, and suspicious classes. The obtained results presented that the proposed approach has better performance than others based on some evaluation criteria such as accuracy with 98.57%, sensitivity with 90%, specificity with 85%, and also ROC and AUC with a rate of 86.77.

Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT.

Background Adrenal masses are common, but radiology reporting and recommendations for management can be variable. Purpose To create a machine learning algorithm to segment adrenal glands on contrast-enhanced CT images and classify glands as normal or mass-containing and to assess algorithm performance. Materials and Methods This retrospective study included two groups of contrast-enhanced abdominal CT examinations (development data set and secondary test set). Adrenal glands in the development data set were manually segmented by radiologists. Images in both the development data set and the secondary test set were manually classified as normal or mass-containing. Deep learning segmentation and classification models were trained on the development data set and evaluated on both data sets. Segmentation performance was evaluated with use of the Dice similarity coefficient (DSC), and classification performance with use of sensitivity and specificity. Results The development data set contained 274 CT examinations (251 patients; median age, 61 years; 133 women), and the secondary test set contained 991 CT examinations (991 patients; median age, 62 years; 578 women). The median model DSC on the development test set was 0.80 (IQR, 0.78-0.89) for normal glands and 0.84 (IQR, 0.79-0.90) for adrenal masses. On the development reader set, the median interreader DSC was 0.89 (IQR, 0.78-0.93) for normal glands and 0.89 (IQR, 0.85-0.97) for adrenal masses. Interreader DSC for radiologist manual segmentation did not differ from automated machine segmentation (P = .35). On the development test set, the model had a classification sensitivity of 83% (95% CI: 55, 95) and specificity of 89% (95% CI: 75, 96). On the secondary test set, the model had a classification sensitivity of 69% (95% CI: 58, 79) and specificity of 91% (95% CI: 90, 92). Conclusion A two-stage machine learning pipeline was able to segment the adrenal glands and differentiate normal adrenal glands from those containing masses. © RSNA, 2022 Online supplemental material is available for this article.

Robust adaptive backstepping control for a lower-limb exoskeleton system with model uncertainties and external disturbances

ABSTRACT The main purpose of this work is to design a robust adaptive backstepping (RABS) control strategy for a pediatric exoskeleton system during passive-assist gait rehabilitation. The nonlinear dynamics of the exoskeleton system have ill-effects of uncertain parameters and external interferences. In this work, the designed robust control strategy is applied on the exoskeleton to assist children of 08–12 years, 25–40 kg weight, and 115–125 cm height. The dynamic model of the coupled human-exoskeleton system is established using the Euler–Lagrange principle. An appropriate Lyapunov function is selected to prove the uniform boundedness of the control signals. The “explosion of terms” is avoided by establishing a virtual control law without the dynamical system parameters. A Microsoft Kinect-LabVIEW experiment is carried out to estimate the desired gait trajectory. The robustness of the proposed control is validated by varying the limb segment masses and inducing the periodic external disturbances. The proposed control strategy is compared with the decentralized modified simple adaptive-PD (DMSA-PD) control strategy. From simulation results and performance improvement index, it is observed that RABS control outperforms the contrast control (DMSA-PD) to track the desired gait during passive-assist rehabilitation under the effect of model uncertainties and external disturbances.

Polyurethane Elastomer Layered Nanocomposite Material for Sports Grounds and the Preparation Method Thereof.

Polyurethane, as a rubber material, can relieve the load on the ground and provide seismic design for the venue, which is of great significance for sports venues. In order to improve the seismic resistance and abrasion resistance of materials for sports fields and reduce accidents in sports, this article has carried out research on the polyurethane elastomer layered nanocomposites for sports fields and their preparation. Today's world is a challenging era of science and technology. The fields of biotechnology, information, medicine, energy, environment, and national defense and security are closely related to the development of high tech, and the requirements for materials are becoming increasingly diversified. Polymer nanocomposite coating has the dual characteristics of organic and inorganic components. It not only retains the advantages of a polymer but also endows it with versatility. It meets the current application needs. It is a hot spot in today's research. Among them, there are two major problems in the composite process of nanomaterials and polymers: dispersion and compatibility. How to improve the dispersion of nanoparticles and enhance the compatibility between nanoparticles and polymers is an urgent problem to be solved. In the method part, this article introduces a small amount of polyurethane and polyurethane elastomers formed after polyurethane modification and introduces layered compounds and nanocomposites and introduces several models involved in nanomaterials in terms of algorithms. In the analysis part, this paper conducts a comprehensive analysis of the hard segment mass fraction, mechanical properties, thermal decomposition behavior, degradation mechanism, and dynamic mechanical properties. With the increase of GO content, the tensile strength increases significantly and the elongation at break becomes smaller and smaller. When the GO content increases from 0% to 2%, the tensile properties of the WPU film increase from 2.6 MPa to 7.9 MPa and the fracture of the elongation decreased from 201.7% to 62.8%. This shows that the increase in GO content will make the composite material harder and brittle. It can be seen from the experimental results that the preparation of the polyurethane elastomer layered nanocomposite material designed in this paper has a good application effect on sports venues.

Body composition and anthropometrics of young male swimmers in relation to the tethered swimming and kinematics of 100-m front crawl race.

The aim was to analyze the relationship of body mass and predicted muscle mass of body segments on swimming kinematics and tethered swimming indices, and further assess the influence of those indices on 100-m front crawl performance of adolescent male swimmers. In 19 volunteer swimmers (age: 13.5±0.44 years, height: 168.6±7.77 cm, body mass: 56.9±10.57 kg), the predicted muscle mass of body segments was assessed with bioelectrical impedance analysis. The kinematic indices of swimming (stroke rate - SR, stroke length - SL, and stroke index - SI) were calculated from a video recording of a 100-m front crawl race. The strength indices (maximum and average value of force, average impulse per single cycle, force decline) were collected in a 30-second front crawl tethered swimming test. The average tethered swimming force was positively correlated with surface swimming speed (0.505; P≤0.05). Indices of SL, SI were influenced by average impulse per single cycle (0.58, 0.55; P≤0.05), and further the SI was strongly correlated with most specified speed indices of the 100-m race (0.59; P≤0.05). It can be stated that the ability of force development in a single stroke, owing to strong interrelation with SI, is a good predictor in talent identification among young swimmers.

Mechanisms of Landslide Destabilization Induced by Glacier‐Retreat on Tungnakvíslarjökull Area, Iceland

AbstractThe massive worldwide deglaciation leads to more frequent slope instabilities in mountainous terrains. The physical processes leading to such destabilizations are poorly constrained due to little monitoring of dynamic parameters at the local scale. Here we study a very large slow‐moving landslide (∼0.8 km2), on the flank of Tungnakvíslarjökull glacier in Iceland. Based on a combination of remote sensing images, we monitor the landslide and glacier kinematics over 75 years, with a focus over the period 1999–2019 when rapid glacier wastage has been observed. The landslide accelerates from 2 to 45 m/yr in the 6 years following a sudden increase in glacier mass loss. This acceleration coincides with intense quake activity (Mℓ &lt; 2.8), recorded by a regional seismic network. We show that this seismicity is caused by the landslide sliding on a rough surface. The evolution of the quake magnitudes suggests a progressive segmentation of the landslide mass during its acceleration.

Breast Masses Detection and Segmentation in Full-Field Digital Mammograms using Unified Convolution Neural Network.

Breast Cancer has been the primary reason for mortality in women of age between twenties and sixties worldwide; moreover early detection and treatment provides patients to get absolute treatment and decrease the mortality rate. Furthermore, recent research indicates that most experienced physicians have plenty of limitations, hence the plethora of work has been carried out to develop an automated mechanism of segmentation and classification of affected area and type of cancer; however, it is still considered to be highly challenging due to the variability of tumor in shape, low signal to noise ratio, shape, size and location of tumor. Furthermore, mammographic mass segmentation and detection are performed as a separate task and a convolution neural network is a highly adopted architecture for the same. In this research, we have designed and developed unified CNN architecture to perform the segmentation and detection of a breast mass. The unified-CNN architecture comprises a novel module for convolution which is combined through additional offset. Further RRS aka Random Region Selection mechanism is applied for data augmentation approach and high-level feature map is implied to achieve the high prediction. Furthermore, unified-CNN is evaluated using the metrics like true positive Rate at FPI (False Positive per Image) and Dice Index on INBreast dataset, also comparative analysis is out carried with various existing methodology. Unified-CNN is developed through improvising CNN. It introduces a novel module at the convolution layer to aim for a high-level feature map in order to get a high prediction. RRS (Random Region Selection) algorithm is used as the data augmentation approach to select the boundary region of the affected area; further robust model training is designed and optimized for process to make optimal. Unified-CNN introduces novel module at the convolution layer to aim for high level feature map in order to get high prediction; further ROI pooling is utilized for boundary detection in images.

Premium Car Brands Strategies and Regulator’s Actions in Russia (2009–2021)

This article analyses the premium segment of the Russian automotive market from 2009 to 2021 based on data from the Association of European Businesses. The authors conducted a comparative analysis of trends in the Russian automotive market with trends in its premium segment and found significant differences in the market cycles. The analysis of the main periods of the studied market was based on the SV matrix (strength/variety). The article also discusses the main external and internal factors that influenced the competition level in the periods under review. As the main conclusion of the study, it was noted that while in the mass segment of cars, the strength of companies and dominant groups is highly dependent on external factors, then in the premium segment the main driving forces for changing the market situation are the actions of the companies themselves, their competitive strategy, as well as adaptation to current market trends. The article also provides comments on the impact of economic events from February 24, 2022 on the market situation.