ELARKHNU browse.title.page

Перегляд за Автор "Krak, Iurii"

Зараз показуємо 1 - 15 з 15

An approach to early diagnosis of pneumonia on individual radiographs based on the CNN information technology
(Bentham Open, 2021-11-19) Radiuk, Pavlo; Barmak, Olexander; Krak, Iurii
Aim: This study investigates the topology of convolutional neural networks and proposes an information technology for the early detection of pneumonia in X-rays. Background: For the past decade, pneumonia has been one of the most widespread respiratory diseases. Every year, a significant part of the world's population suffers from pneumonia, which leads to millions of deaths worldwide. Inflammation occurs rapidly and usually proceeds in severe forms. Thus, early detection of the disease plays a critical role in its successful treatment. Objective: The most operating means of diagnosing pneumonia is the chest X-ray, which produces radiographs. Automated diagnostics using computing devices and computer vision techniques have become beneficial in X-ray image analysis, serving as an ancillary decision-making system. Nonetheless, such systems require continuous improvement for individual patient adjustment to ensure a successful, timely diagnosis. Methods: Nowadays, artificial neural networks serve as a promising solution for identifying pneumonia in radiographs. Despite the high level of recognition accuracy, neural networks have been perceived as black boxes because of the unclear interpretation of their performance results. Altogether, an insufficient explanation for the early diagnosis can be perceived as a severe negative feature of automated decision-making systems, as the lack of interpretation results may negatively affect the final clinical decision. To address this issue, we propose an approach to the automated diagnosis of early pneumonia, based on the classification of radiographs with weakly expressed disease features. Results: An effective spatial convolution operation with several dilated rates, combining various receptive feature fields, was used in convolutional layers to detect and analyze visual deviations in the X-ray image. Due to applying the dilated convolution operation, the network avoids significant losses of objects' spatial information providing relatively low computational costs. We also used transfer training to overcome the lack of data in the early diagnosis of pneumonia. An image analysis strategy based on class activation maps was used to interpret the classification results, critical for clinical decision making. Conclusion: According to the computational results, the proposed convolutional architecture may be an excellent solution for instant diagnosis in case of the first suspicion of early pneumonia.
Analysis of deep learning methods in adaptation to the small data problem solving
(Springer Cham, 2022-09-14) Krak, Iurii; Kuznetsov, Vladyslav; Kondratiuk, Serhii; Azarova, Larisa; Barmak, Olexander; Radiuk, Pavlo
This paper discusses a specific problem in the study of deep neural networks – learning on small data. Such issue happens in situation of transfer learning or applying known solutions on new tasks that involves usage of particular small portions of data. Based on previous research, some specific solutions can be applied to various tasks related to machine learning, computer vision, natural language processing, medical data study and many others. These solutions include various methods of general purpose machine and deep learning, being successfully used for these tasks. In order to do so, the paper carefully studies the problems arise in the preparation of data. For benchmark purposes, we also compared “in wild” the methods of machine learning and identified some issues in their practical application, in particular usage of specific hardware. The paper touches some other aspects of machine learning by comparing the similarities and differences of singular value decomposition and deep constrained auto-encoders. In order to test our hypotheses, we carefully studied various deep and machine learning methods on small data. As a result of the study, our paper proposes a set of solutions, which include the selection of appropriate algorithms, data preparation methods, hardware optimized for machine learning, discussion of their practical effectiveness and further improvement of approaches and methods described in the paper. Also, some problems were discussed, which have to be addressed in the following papers.
Detection of early pneumonia on individual CT scans with dilated convolutions
(CEUR-WS, 2021-04-23) Krak, Iurii; Barmak, Olexander; Radiuk, Pavlo
Over the past decades, pneumonia has been considered one of the most dangerous diseases, leading to severe consequences in a short time. Without proper and timely treatment, pneumonia can lead to fatal consequences. Thus, early diagnosis and detection of this lung disease are crucial in successful treatment and constant monitoring. Indeed, there is a high demand for the development of medical image technologies for disease identification. In this paper, we propose a novel information technology for robust feature identification and early detection of pneumonia on computer tomography scans. We also propose a new modified convolutional neural network as a core feature extractor. An effective dilated convolution operation with different rates, combining features of various receptive fields, was utilized to detect and analyze visual deviations in targeted images. Due to applying the dilated convolutions, the network avoids significant losses of objects' spatial information while providing low computational losses. The investigated model classifies computed tomography images with a validation accuracy of up to 96.12%. Overall, our approach requires much fewer computing resources, proving its effectiveness for solving practical problems on available computing devices.
ECG Arrhythmia Classification and Interpretation using Convolutional Networks for Intelligent IoT Healthcare System
(CEUR-WS.org, 2024-07-29) Kovalchuk, Oleksii; Barmak, Olexander; Radiuk, Pavlo; Krak, Iurii
In modern healthcare, timely and precise diagnosis of arrhythmias can significantly impact patient outcomes, as arrhythmias are indicative of various cardiac disorders that require immediate attention. The classification of these irregular heartbeats based on electrocardiogram (ECG) signals is essential for the development of intelligent healthcare systems that can provide real-time monitoring and diagnosis, integrating seamlessly into smart city infrastructures and IoT-enabled smart homes. In this paper, we propose novel methods to enhance the classification and interpretation of arrhythmia by ECG signals based on convolutional neural network (CNN). Leveraging the MIT-BIH Arrhythmia Database, which includes 48 recordings from 47 patients, the proposed approach involved preprocessing the ECG signals into fragments and enhancing the CNN architecture with Batch Normalization layers and an additional convolutional layer. The network was trained and validated using statistical metrics namely accuracy, precision, recall, and F1-scores. The results demonstrated an overall classification accuracy of 99.43%, with particularly high precision and recall for Normal beats, Right bundle branch block beats, and Left bundle branch block beats, achieving F1-scores close to 100%. The introduced CNN showed superior performance in distinguishing between nine types of arrhythmias. However, the study highlighted the limitation of relying on clinical features for decision justification, especially in cases of overlapping pathologies. Overall, the findings suggest that the proposed approach can serve as a reliable supporting tool for arrhythmia diagnosis, offering high accuracy and potential integration into real-time monitoring systems.
Explainable Artificial Intelligence: Transitioning DL Model Decisions to User-Understandable Features in Healthcare
(CEUR-WS.org, 2024-10-05) Radiuk, Pavlo; Barmak, Oleksander; Manziuk, Eduard; Krak, Iurii
Modern artificial intelligence (AI) solutions often face problems of the “black box” nature of deep learning (DL) models, which limits their transparency and trustworthiness in critical medical applications. In this study, we propose and evaluate a scalable approach for enhancing the interpretability of DL models in medical signal and image processing by translating complex model decisions into features that are understandable to healthcare professionals. The proposed approach was tested on two medical datasets: ECG signals for arrhythmia detection and MRI scans for heart disease classification. The performance of the DL models was compared with expert annotations, using Cohen’s Kappa coefficient as the primary metric to assess agreement. The study found strong agreement between DL model predictions and expert annotations, with Cohen’s Kappa coefficients of 0.89 for the ECG dataset and 0.80 for the MRI dataset, demonstrating the usefulness of the approach in providing reliable and interpretable results. In sum, the proposed scalable approach significantly improves the interpretability of DL models in medical applications.
Human-in-the-Loop Approach Based on MRI and ECG for Healthcare Diagnosis
(CEUR-WS, 2022-12-14) Radiuk, Pavlo; Kovalchuk, Oleksii; Slobodzian, Vitalii; Manziuk, Eduard; Barmak, Oleksander; Krak, Iurii
The presented study investigates a human-centric approach to implementing human-in-the-loop models for healthcare diagnostics. The following tasks were considered and addressed in this work: a) identify the features necessary for future healthcare diagnosis based on electrocardiogram signals in the human-in-the-loop model: P, T-peaks, QRS-complex, PQ and ST segments, and b) detect inflammatory processes in the heart muscle (myocardium) based on cardiac magnetic resonance imaging. As a result of our investigation, a novel approach was proposed for embedding (integrating) clinical knowledge about the nature of these phenomena into the electrocardiogram signal and magnetic resonance imaging. Domain knowledge about the sample’s nature is encoded similarly to the input information. Moreover, the convolution operation within our approach serves as an embedding mechanism. The results presented in the article are a starting point for using the models obtained by the proposed approach (human-in-the-loop models) for classification problems using deep learning and convolutional neural networks. Also, visual analysis shows the proposed approaches’ ability to solve practical clinical problems. It also ensures transparent interpretation of the obtained results as the human-in-the-loop model, which, in turn, is built according to the human-centric approach. Overall, our contribution allows the implementation of a scheme for obtaining artificial intelligence solutions based on the principles of trust in them.
Information technology for early diagnosis of pneumonia on individual radiographs
(CEUR-WS, 2020-12-01) Krak, Iurii; Barmak, Oleksander; Radiuk, Pavlo
Nowadays, pneumonia remains a disease with one of the highest death rates around the world. The ailment’s pathogen instantly causes a large amount of fluid into the lungs, leading to acute exacerbation. Without preliminary examination and timely treatment, pneumonia can result in severe pulmonary complications. Consequently, early diagnosis of pneumonia becomes a decisive factor in treatment and monitoring the disease. Therefore, information systems that can identify early pneumonia on the Chest X-ray images are becoming more demanding nowadays. An individual approach to a person might be a promising way of early diagnosis. The presented study considers an approach to feature extraction of the early stage of pneumonia and identifying the disease using a relatively simple convolutional neural network. With only three convolutional and two linearization layers, the proposed architecture classifies radiographs with 90.87% accuracy, approaching the results of deep multilayer and resource-intensive architectures in classification accuracy and exceeding them in time efficiency. Our approach requires relatively fewer computing resources, confirming its efficiency in solving practical tasks on available computing devices.
Integration of Contextual Descriptors in Ontology Alignment for Enrichment of Semantic Correspondence
(IEEE, Inc., 2024-12-02) Manziuk, Eduard; Barmak, Oleksander; Radiuk, Pavlo; Kuznetsov, Vladislav; Krak, Iurii; Yakovlev, Sergiy
This paper proposes a novel approach to semantic ontology alignment using contextual descriptors. A formalization was developed that enables the integration of essential and contextual descriptors to create a comprehensive knowledge model. The hierarchical structure of the semantic approach and the mathematical apparatus for analyzing potential conflicts between concepts, particularly in the example of "Transparency" and "Privacy" in the context of artificial intelligence, are demonstrated. Experimental studies showed a significant improvement in ontology alignment metrics after the implementation of contextual descriptors, especially in the areas of privacy, responsibility, and freedom & autonomy. The application of contextual descriptors achieved an average overall improvement of approximately 4.36%. The results indicate the effectiveness of the proposed approach for more accurately reflecting the complexity of knowledge and its contextual dependence.
Interpretable deep learning method for medical image diagnosis
(ФОП Вишемирський В.С., 2024-06-23) Manziuk, Eduard; Barmak, Oleksandr; Krak, Iurii; Petliak, N.; Jin, Zh.; Radiuk, Pavlo
Incorporating artificial intelligence into the medical field holds immense potential, but it also raises significant challenges that must be addressed to ensure patient safety and ethical practices. While AI can enhance efficiency and support decision-making processes, its application in healthcare demands utmost caution and rigorous safeguards.
Myocardium Segmentation using Two-Step Deep Learning with Smoothed Masks by Gaussian Blur
(CEUR.org, 2023-01-07) Slobodzian, Vitalii; Radiuk, Pavlo; Zingailo, Anastasiia; Barmak, Olexander; Krak, Iurii
Nowadays, cardiac magnetic resonance images face challenges in distinguishing between inflamed and non-inflamed tissues due to subtle color variations rather than clear density distinctions. Pixel values in these images vary based on individual subjects and the MRI equipment, making them inconsistent across different training datasets. Thus, detecting inflamed tissues in MRIs largely depends on the expertise of interpreting physicians, making it time-consuming and complicating the training of accurate classifiers. To address this issue, in this study, we propose a novel approach for myocardium segmentation on MRI images utilizing a two-stage neural network process coupled with mask refinement. The initial network outlines the myocardium, which is then fine-tuned by the second network for precise myocardium segmentation. A key enhancement involves mask post-processing via Gaussian blur, where the blur coefficient is automatically adjusted. Experimental outcomes demonstrated an increase in the Dice coefficient from 0.889 to 0.894 upon removing non-essential labels. Moreover, using a dual-model approach for myocardium localization and contour definition elevated the coefficient to 0.938. Employing the Gaussian blur during mask resizing culminated in an impressive average Dice coefficient of 0.955.
Representation of trustworthiness components in AI systems: A formalized approach considering interconnections and overlap
(CEUR-WS.org, 2024-10-05) Manziuk, Eduard; Barmak, Oleksandr; Radiuk, Pavlo; Kuznetsov, Vladislav; Krak, Iurii
The study addresses the problem of integrating trustworthiness components into artificial intelligence (AI) systems. A new method is proposed to determine the interdependence and intersection of concepts in the field of trustworthy AI. The approach provides a structured way to assess the interconnections and overlaps between different trustworthiness concepts, offering a more complete understanding of their complex interaction. A method for assessing the degree of coincidence between different trustworthiness components is proposed, which allows for a more accurate analysis of their interconnections. The results of experimental studies have shown the level of interconnection between the concepts, with an average level of overlap of about 67%. A formal model for integrating trustworthiness components into AI systems has also been developed. This model provides a framework for evaluating the actions of an AI agent against several trustworthiness criteria simultaneously. The approach takes into account different contexts and scenarios, providing a more robust and flexible assessment of trustworthy AI. By bridging the gap between theoretical concepts and practical implementation, this work contributes to the development of trustworthy AI systems. The proposed work also provides a more structured and formalized approach to understanding and implementing trustworthy AI. Furthermore, this research aims to contribute to the development of AI systems that are built on ethical principles and societal values.
Representation of Trustworthiness Components in AI Systems: A Formalized Approach Considering Interconnections and Overlap
(2024-10-05) Manziuk, Eduard; Barmak, Oleksandr; Radiuk, Pavlo; Kuznetsov, Vladislav; Krak, Iurii
The study addresses the problem of integrating trustworthiness components into artificial intelligence (AI) systems. A new method is proposed to determine the interdependence and intersection of concepts in the field of trustworthy AI. The approach provides a structured way to assess the interconnections and overlaps between different trustworthiness concepts, offering a more complete understanding of their complex interaction. A method for assessing the degree of coincidence between different trustworthiness components is proposed, which allows for a more accurate analysis of their interconnections. The results of experimental studies have shown the level of interconnection between the concepts, with an average level of overlap of about 67%. A formal model for integrating trustworthiness components into AI systems has also been developed. This model provides a framework for evaluating the actions of an AI agent against several trustworthiness criteria simultaneously. The approach takes into account different contexts and scenarios, providing a more robust and flexible assessment of trustworthy AI. By bridging the gap between theoretical concepts and practical implementation, this work contributes to the development of trustworthy AI systems. The proposed work also provides a more structured and formalized approach to understanding and implementing trustworthy AI. Furthermore, this research aims to contribute to the development of AI systems that are built on ethical principles and societal values.
Robust R-peak Detection using Deep Learning based on Integrating Domain Knowledge
(CEUR.org, 2023-01-07) Kovalchuk, Oleksii; Radiuk, Pavlo; Barmak, Olexander; Krak, Iurii
Electrocardiography (ECG) is a pivotal clinical technique for assessing heart function by recording its electrical activity. However, accurate processing and analysis of ECG signals, particularly the detection of R-peaks, remains challenging. Any inaccuracies in R-peak detection can significantly impact subsequent stages of analysis, potentially leading to incorrect diagnoses and treatment decisions. Therefore, in this study, we aim to refine the approach to identifying R-peaks in ECG signals by integrating knowledge of a reference ECG signal into the input signal, addressing the critical need for accurate R-peak detection in diagnosing various cardiac pathologies. The authors propose a novel method involving the integration of knowledge into the ECG signal, processing this information using a convolutional neural network, and post-processing the CNN model's results to identify R-peaks. The method was evaluated using various four well-known ECG databases. Comparative results, with an error margin of +-25 ms, revealed that the proposed approach was the top performer across almost all metrics and databases, frequently achieving accuracy scores of 0.9999 and demonstrating high precision, recall, and F1-score. Based on the investigation findings, the proposed approach is robust and reliable, with the best performance achieved on the QT database test set, offering a balanced and dependable solution for R-peak detection in ECG signals.
Semantic alignment of ontologies meaningful categories with the generalization of descriptive structures
(Publishing house "Academperiodika", 2023-01-23) Manziuk, Eduard; Barmak, Olexander; Krak, Iurii; Pasichnyk, Olexander; Radiuk, Pavlo; Mazurets, Olexander
The presented work addresses the issue of semantic alignment of ontology components with a generalized structured corpus. The field of research refers to the sphere of determining the features of trust in artificial intelligence. An alignment method is proposed at the level of semantic components of the general alignment system. The method is a component of a broader alignment system and compares entities at the level of meaningful correspondence. Moreover, only the alignment entities’ descriptive content is considered within the proposed technique. Descriptive contents can be represented by variously named id and semantic relations. The method defines a fundamental ontology and a specific alignment structure. Semantic correspondence in the form of information scope is formed from the alignment structure. In this way, an entity is formed on the side of the alignment structure, which would correspond in the best meaningful way to the entity from the ontology in terms of meaningful descriptiveness. Meaningful descriptiveness is the filling of information scope. Information scopes are formed as a final form of generalization and can consist of entities, a set of entities, and their partial union. In turn, entities are a generalization of properties that are located at a lower level of the hierarchy and, in turn, are a combination of descriptors. Descriptors are a fundamental element of generalization that represent principal content. Descriptors can define atomic content within a knowledge base and represent only a particular aspect of the content. Thus, the element of meaningfulness is not self-sufficient and can manifest as separate meaningfulness in the form of a property, as a minimal representation of the meaningfulness of an alignment. Descriptors can also supplement the content at the level of information frameworks, entities, and properties. The essence of the alignment in the form of information scope cannot be represented as a descriptor or their combination. It happens because the descriptive descriptor does not represent the content in the completed form of the correspondence unit. The minimum structure of representation of information scope is in the form of properties. This form of organization of establishing the correspondence of the semantic level of alignment allows you to structure and formalize the information content for areas with a complex form of semantic mapping. The hierarchical representation of the generalization not only allows simplifying the formalization of semantic alignment but also enables the formation of information entities with the possibility of discretization of content at the level of descriptors. In turn, descriptors can expand meaningfulness at an arbitrary level of the generalization hierarchy. This provides quantization of informational content and flexibility of the alignment system with discretization at the level of descriptors. The proposed method is used to formalize the semantic alignment of ontology entities and areas of structured representation of information.
Toward explainable deep learning in healthcare through transition matrix and user-friendly features
(Frontiers Media SA, 2024-11-25) Barmak, Oleksander; Krak, Iurii; Yakovlev, Sergiy; Manziuk, Eduard; Radiuk, Pavlo; Kuznetsov, Vladislav
Modern artificial intelligence (AI) solutions often face challenges due to the “black box” nature of deep learning (DL) models, which limits their transparency and trustworthiness in critical medical applications. In this study, we propose and evaluate a scalable approach based on a transition matrix to enhance the interpretability of DL models in medical signal and image processing by translating complex model decisions into user-friendly and justifiable features for healthcare professionals. The criteria for choosing interpretable features were clearly defined, incorporating clinical guidelines and expert rules to align model outputs with established medical standards. The proposed approach was tested on two medical datasets: electrocardiography (ECG) for arrhythmia detection and magnetic resonance imaging (MRI) for heart disease classification. The performance of the DL models was compared with expert annotations using Cohen’s Kappa coefficient to assess agreement, achieving coefficients of 0.89 for the ECG dataset and 0.80 for the MRI dataset. These results demonstrate strong agreement, underscoring the reliability of the approach in providing accurate, understandable, and justifiable explanations of DL model decisions. The scalability of the approach suggests its potential applicability across various medical domains, enhancing the generalizability and utility of DL models in healthcare while addressing practical challenges and ethical considerations.

Перегляд за Автор "Krak, Iurii"

Результатів на сторінці

Налаштування сортування