Перегляд за Автор "Ivanko, K. O."
Зараз показуємо 1 - 13 з 13
Результатів на сторінці
Налаштування сортування
Документ Відкритий доступ Advanced Edge Detection Techniques for Enhanced Diabetic Retinopathy Diagnosis Using Machine Learning(КПІ ім. Ігоря Сікорського, 2024) Basarab, M. R.; Ivanko, K. O.Diabetic retinopathy (DR) represents one of the most serious complications associated with diabetes mellitus, posing a significant threat to vision and leading to severe impairment and potential blindness if not diagnosed and treated promptly. The study investigates the integration of advanced edge detection techniques with machine learning algorithms to enhance the precision and effectiveness of DR diagnosis. By leveraging the APTOS 2019 Blindness Detection dataset, the research employs a combination of edge detection methods such as the Sobel operator and the Canny edge detector, alongside advanced preprocessing techniques and sophisticated feature extraction methods. The study reveals that the synergy between these edge detection techniques and machine learning significantly boosts the diagnostic accuracy of neural networks. Specifically, the accuracy for multiclass classification (spanning five categories: No diabetic retinopathy, Mild, Moderate, Severe, and Proliferative diabetic retinopathy) improved from 78.5% to an impressive 88.2%. This marked enhancement underscores the potential of these techniques in refining the diagnostic processes for early DR detection. By improving the accuracy of classification, this approach not only facilitates early intervention but also plays a crucial role in reducing the risk of severe vision loss among patients with diabetes. The findings of this study emphasize the importance of integrating advanced image processing techniques with machine learning frameworks in medical diagnostics. The improved outcomes demonstrated in this research highlight the potential for such technological advancements to contribute meaningfully to the field of ophthalmology, leading to better patient care and potentially transforming the standard of practice in DR diagnosis.Документ Відкритий доступ Classification of Structural and Functional Development Stage of Cardiomyocytes Using Machine Learning Techniques(КПІ ім. Ігоря Сікорського, 2024) Bondarev, V. R.; Ivanko, K. O.; Ivanushkina, N. G.The study is dedicated to the problem of classification of structural and functional development stage of cardiomyocytes derived from the induced pluripotent stem cells with application of the digital image processing methods and machine learning algorithms, in particular, neural networks. Cell regenerative therapy has become one of the most promising treatment options for patients with heart failure. But since cardiomyocytes are objects with a high level of complexity and have significant morphological variability, automatic classification is complicated by the lack of implemented methods. That's why researches in this area are a major global public health priority. The initial data set used in this study is a publicly open set of confocal microscopic images of cardiomyocytes which can be divided into five classes based on the morphological features (the structure of the transverse T-tubule). A small amount of input data leads to the need of using augmentation methods. Methods that prevent the alteration of the transverse T-tubule, which is an important parameter for correct classification of the development of cardiomyocytes, are used. Histogram equalization technique is used to enhance the contrast and dynamic range of the confocal microscopic images with the method of contrast-limited adaptive equalization. This helped to improve the local contrast of the analyzed images and highlight the main elements of the cardiomyocyte. Finally, Chan–Vese method, which belongs to the regional segmentation methods, is chosen for the image segmentation and removing artifacts and/or parts of other cells from the image. A pre-processed and augmented dataset is used for training of the convolutional neural network having an architecture with hierarchical structure and residual block usage. The model is evaluated based on the confusion matrix and the heat maps of different convolutional layers are analyzed. Images from the classes with a large number of mutual errors are also considered. Based on the analysis, several classes of structural and functional development of cardiomyocytes are combined. Final accuracy of the model for defining the cardiomyocytes maturation stage achieved 77%.Документ Відкритий доступ Deep Learning for the Detection and Classification of Diabetic Retinopathy Stages(КПІ ім. Ігоря Сікорського, 2024) Basarab, M. R.; Ivanko, K. O.The incidence of diabetic retinopathy (DR), a complication of diabetes leading to severe vision impairment and potential blindness, has surged worldwide in recent years. This condition is considered one of the leading causes of vision loss. To improve diagnostic accuracy for DR and reduce the burden on healthcare professionals, artificial intelligence (AI) methods are increasingly implemented in medical institutions. AI-based models, in particular, are integrating more algorithms to enhance the performance of existing neural network architectures that are commercially used for DR detection. However, these neural network models still exhibit limitations, such as the need for high computational power and lower accuracy in detecting early DR stages. To overcome these challenges, developing more advanced machine learning models for precise DR detection and classification of DR stages is essential, as it would aid ophthalmologists in making accurate diagnoses. This article reviews current research on the use of deep learning in diagnosing and classifying DR and related diseases, as well as the challenges ophthalmologists face in detecting this condition and potential solutions for early-stage DR detection. This review provides information on modern approaches to DR detection using deep learning applications and discusses the issues and limitations in this area.Документ Відкритий доступ Estimation of Multiple Cardiac Cells’ Action Potentials From Extracellular Field Potentials(КПІ ім. Ігоря Сікорського, 2023) Shpotak, M. O.; Ivanushkina, N. H.; Ivanko, K. O.; Prokopenko, Y. V.Modern biomedical technologies use a combination of microelectrode array (MEA) systems and artificially grown cells to study disease mechanisms and test drug effects. MEA systems measure extracellular field potentials (FPs) of cell cultures or tissues, but they cannot record intracellular action potentials (APs) without some modifications or additional devices, limiting the depth of electrophysiological analysis. One of the possible solutions to the inability of MEA systems to measure APs is to mathematically reconstruct them using recorded FPs. However, accurately reconstructing APs of multiple cells is challenging task, which is complicated by many factors such as the number of cells, synchronicity of their APs, identification of their electrophysiological parameters, and noise. This paper aims to address the mathematical problem of AP synchronicity, asynchronicity and partial synchronicity between multiple cells. In this study, mathematical techniques were employed to derive a system of equations capable of reconstructing the APs of N cells simultaneously, using the FPs recorded with N + 1 electrodes. The equations take into account the number of cells, synchronicity and variation of their APs and specific electrical properties of the cells and the medium. In numerical experiments the equations were applied to reconstruct APs from FPs for cases with different types of synchronicity in noise-free and noisy conditions. The reconstructed APs, when combined with recorded FPs, expand the number of electrophysiological characteristics available for cardiotoxicity assessment in MEA systems.Документ Відкритий доступ Identification and Assessment of Electrocardiographic Markers of Cardiac Electrical Instability(КПІ ім. Ігоря Сікорського, 2017) Ivanko, K. O.; Ivanushkina, N. G.; Karplyuk, Y. S.; Іванько, Катерина Олегівна; Іванушкіна, Наталія Георгіївна; Карплюк, Євгеній Сергійович; Иванько, Екатерина Олеговна; Иванушкина, Наталья Георгиевна; Карплюк, Евгений СергеевичДокумент Відкритий доступ Investigation of fundus images for detection of diabetic retinopathy stage using deep learning(КПІ ім. Ігоря Сікорського, 2023) Basarab, M. R.; Ivanko, K. O.The study is dedicated to the investigation of diabetic retinopathy images by digital processing methods and further pathological outcome levels classification. The application of image processing methods to the problem of diabetic retinopathy (DR) analysis is considered in the paper. In order to investigate the possibilities of machine learning for the problem of classification of retinal images, the dataset of retinal images, which represent 5 classes: absence of DR, moderate, mild, proliferate stages, and severe DR, was used in this work. The aim of this study is to identify and compare the different image processing methods used for diabetic retinopathy detection, as well as to choose the classification method that provides the highest accuracy in the identification of the human retina condition. The convolutional neural networks with tuned parameters such as EfficientNet and ResNet were applied to determine the best classification models for computerized disease screening. The accuracy and losses of the different models were determined and compared. Based on this, a combination of image preprocessing steps and neural network models, which provide the highest accuracy of diabetic retinopathy condition recognition, reaching 91.4% for the task of recognition of 5 classes (absence of DR and 4 stages of DR) is proposed. Intermediate stages in the development of diabetic retinopathy are the most difficult to distinguish: the best model showed 85.2% of correctly defined cases of moderate stage of diabetic retinopathy and 83% of correctly defined cases of mild stage. Overall, this article highlights the significance of artificial intelligence (AI) and deep learning in the detection and classification of diabetic retinopathy. It underscores the need for improved screening methods, especially in underserved areas, and emphasizes the potential of these technologies in preserving vision, reducing healthcare professionals’ workload, and promoting widespread adoption in clinical practice. The article also acknowledges the challenges associated with image variability and the potential impact on AI model performance, calling for further research and improvement in image quality and consistency.Документ Відкритий доступ Investigation of Lung Sounds Features for Detection of Bronchitis and COPD Using Machine Learning Methods(КПІ ім. Ігоря Сікорського, 2021) Porieva, H. S.; Ivanko, K. O.; Semkiv, C. I.; Vaityshyn, V. I.Документ Відкритий доступ Myocardial Ischemia Detection Using a Reduced Number of ECG Leads(КПІ ім. Ігоря Сікорського, 2022) Mnevets, A. V.; Ivanushkina, N. G.; Ivanko, K. O.The study is devoted to the investigation of the electrocardiographic (ECG) features to distinguish norm and myocardial ischemia in reduced set of electrocardiographic leads. In particular, for myocardial ischemia detection the spectral features of the electrocardiographic signal and characteristics of the shape of ECG waves are considered. The main features commonly used for myocardial ischemia detection are described in the paper, as well as more reliable analogs are proposed for the considered task. The approach for ECG signal preprocessing, identification of the necessary signal segments and subsequent calculation of features is described in detail. The considered features are based on the areas under the characteristic waves of the ECG signal and the spectral distribution of these waves. The most informative features for myocardial ischemia detection are identified and selected from the initial set of parameters which led to a two-fold reduction in number of ECG leads comparing to the standard 12-lead electrocardiogram. The techniques for determining the proposed features, namely the ratio of the area under T wave to the area under the P wave, as well as the ratio of the area under T wave to the area of the entire cardiac cycle, are considered. These features together with other calculated parameters are assumed to describe the majority of pathology cases and gave a high accuracy of the classification ECG to norm and ischemic myocardial diseasesince they reflect the bioelectrical processes that occur in the presence of myocardial ischemia and manifest themselves on the surface ECG. Based on the analysis of principal components and the method t-distributed stochastic neighbor embedding, the distribution of data in the space of features that characterize the classes of norm and pathology was shown. Raw ECG data in norm and with cases of myocardial ischemia were obtained from the ”PTB Diagnostic ECG Database” used in ”The PhysioNet/Computing in Cardiology Challenge 2020”. This database contains 22353 ECG records from 290 persons with 12 ECG leads (I, II, III, aVR, aVL, aVF, and V1–V6). The database contains the high-resolution ECG signals, which enabled to obtain 10,000 cardio cycles presenting norm and myocardial ischemia pathology for the subsequent training the machine learning algorithms. Based on the obtained features, various machine learning algorithms were trained and the accuracy was compared on different combinations of ECG leads. Аs a result of cross-validation, the accuracy of myocardial ischemia detection was 99% with a standard deviation of 0.4% for 6 leads (I, II, III, AVR, AVL, AVF) and 93% with a standard deviation of 0.12% for one lead (I). Thus, it was shown, that with machine learning methods it is possible to recognize ischemic myocardial disease with high accuracy and stability using six standard ECG leads or only one ECG lead.Документ Відкритий доступ Permutation entropy of fetal heart rate with extraction of maternal heartbeats(НТУУ "КПИ", 2013) Avilov, O. О.; Borovskyi, I. I.; Zhukov, M. A.; Ivanko, K. O.; Popov, A. A.; Fesechko, V. A.; Авілов, О. О.; Боровський, І. І.; Іванько, К. О.; Жуков, М. А.; Попов, А. О.; Фесечко, В. А.; Авилов, А. А.; Боровский, И. И.; Жуков, М. А.; Иванько, Е. О.; Попов, А. А.; Фесечко, В. А.Документ Відкритий доступ Prediction of the Development of Gestational Diabetes Mellitus in Pregnant Women Using Machine Learning Methods(КПІ ім. Ігоря Сікорського, 2021) Basarab, M. R.; Ivanko, K. O.; Vishwesh KulkarniДокумент Відкритий доступ Solving the Inverse Problem of Relationship Between Action Potentials and Field Potentials in Cardiac Cells(КПІ ім. Ігоря Сікорського, 2021) Ivanushkina, N. G.; Ivanko, K. O.; Shpotak, M. O.; Prokopenko, Y. V.Multiple electrode array (MEA) systems are the instrument platforms being used for cardiac extracellular electrophysiology investigation. Key applications of MEA technology are disease modeling and screening of drug effects. To solve these problems the efforts of many scientists are directed to signal processing and analysis of field potentials (FP) measured with MEA systems. However, it should be noted the complexity of interpretation of MEA information in non-invasive field potentials measurements of cardiac cells compared to invasive action potential (AP) recordings obtained using patch clamp technology. This study is devoted to the mathematical determination of the relationship between the signals of the electrical activity of cardiomyocytes: internal AP and external FP. Derivation of equations for transfer functions between AP and FP is based on field theory. This article provides a solution to the inverse problems of the relationship between AP and FP. Numerical experiments demonstrate the results of the inverse transformation of simulated field potentials signals. To denoise the potentials of the extracellular field of cardiomyocytes, the method combining wavelet transform and processing in eigensubspaces of cardiac cycles is used. The proposed method, based on transfer functions, can be used to determine AP parameters and expand the capabilities of data analysis in MEA systems for diagnosing heart disease and assessing cardiac toxicity during drug development.Документ Відкритий доступ Комплексный метод для выделения электрокардиосигналов плода из абдоминальных сигналов матери(НТУУ "КПИ", 2014) Боровский, И. И.; Иванушкина, Н. Г.; Иванько, Е. О.; Лысенко, Э. Р.; Панасюк, Е. В.; Боровський, І. І.; Іванушкіна, Н. Г.; Іванько, К. О.; Лисенко, Е. Р.; Панасюк, О. В.; Borovskyi, I. I.; Ivanushkina, N. G.; Ivanko, K. O.; Lysenko, E. R.; Panasiuk, O. V.Документ Відкритий доступ Нейронные сети для распознавания образов поздних потенциалов предсердий(НТУУ "КПИ", 2013) Иванушкина, Н. Г.; Иванько, Е. О.; Матвеева, Н. А.; Іванушкіна, Н. Г.; Іванько, Є. О.; Матвеева, Н. О.; Ivanushkina, N. G.; Ivanko, K. O.; Matveeva, N. A.