BACKGROUND: The initial step in annotating an electrocardiogram is the evaluation of the patient's heart rhythm. In the presented study, a method has been developed to process the electrocardiographic signal and estimate the heart rhythm. The method is based on the application of a trained convolutional neural network, which will provide the physician with preliminary information about possible atrial fibrillation or the presence of other rhythm disturbances as soon as possible after receiving the electrocardiogram. Furthermore, such methodologies can be incorporated into telemedicine systems, thereby facilitating remote monitoring of cardiac status. AIM: The aim of the study was to develop an electrocardiography signal processing method for the classification of a patient’s heart rhythm into three classes: sinus rhythm, atrial fibrillation, and other arrhythmias. MATERIALS AND METHODS: The publicly available electrocardiograms of patients were selected for model training and testing. The software was written in the Python programming language using the TensorFlow framework. The training, validation, and test samples were formed with a ratio of 10:1:1:1, with a uniform distribution by classes. Three variants of data sets for each record were prepared: combining plots of all 12 leads of the electrocardiogram on one image, obtaining spectrograms of II and V1 leads using Gaussian wavelet, and representing the record as a vector cardiogram. The architecture of the convolutional neural network was based on the ResNet18 architecture, which was further modified, and a series of modifications were made for each of the input data representations. RESULTS: A serialized model was obtained with the following accuracy metrics: accuracy=43% for matching 12 electrocardiographic leads in the image; accuracy=43% for vector representation of the electrocardiogram; and accuracy=69% for wavelet transform of the electrocardiogram. In the case of a two-class problem involving sinus rhythm and atrial fibrillation, the accuracy metric for the wavelet transform reaches 93% with metrics recall, precision, and F1-score values of 93%, 94%, and 93%, respectively. CONSLUSIONS: The results demonstrate the potential of using convolutional neural networks to assess the heart rhythm of patients. Further development of the project involves the selection of the most effective machine learning algorithm, testing of this algorithm for the two-class problem, and expansion of the solution for other classes of rhythm disorders. Additionally, it is possible to improve classification results for the three-class problem by using a superior model and introducing additional clustering.
{"title":"Electrocardiography signal processing method for effective assessment of a patient's heart rate using a convolutional neural network","authors":"Daniel V. Gordienko, Artem O. Kravchenko","doi":"10.17816/dd627084","DOIUrl":"https://doi.org/10.17816/dd627084","url":null,"abstract":"BACKGROUND: The initial step in annotating an electrocardiogram is the evaluation of the patient's heart rhythm. In the presented study, a method has been developed to process the electrocardiographic signal and estimate the heart rhythm. The method is based on the application of a trained convolutional neural network, which will provide the physician with preliminary information about possible atrial fibrillation or the presence of other rhythm disturbances as soon as possible after receiving the electrocardiogram. Furthermore, such methodologies can be incorporated into telemedicine systems, thereby facilitating remote monitoring of cardiac status. \u0000AIM: The aim of the study was to develop an electrocardiography signal processing method for the classification of a patient’s heart rhythm into three classes: sinus rhythm, atrial fibrillation, and other arrhythmias. \u0000MATERIALS AND METHODS: The publicly available electrocardiograms of patients were selected for model training and testing. The software was written in the Python programming language using the TensorFlow framework. The training, validation, and test samples were formed with a ratio of 10:1:1:1, with a uniform distribution by classes. Three variants of data sets for each record were prepared: combining plots of all 12 leads of the electrocardiogram on one image, obtaining spectrograms of II and V1 leads using Gaussian wavelet, and representing the record as a vector cardiogram. The architecture of the convolutional neural network was based on the ResNet18 architecture, which was further modified, and a series of modifications were made for each of the input data representations. \u0000RESULTS: A serialized model was obtained with the following accuracy metrics: accuracy=43% for matching 12 electrocardiographic leads in the image; accuracy=43% for vector representation of the electrocardiogram; and accuracy=69% for wavelet transform of the electrocardiogram. In the case of a two-class problem involving sinus rhythm and atrial fibrillation, the accuracy metric for the wavelet transform reaches 93% with metrics recall, precision, and F1-score values of 93%, 94%, and 93%, respectively. \u0000CONSLUSIONS: The results demonstrate the potential of using convolutional neural networks to assess the heart rhythm of patients. Further development of the project involves the selection of the most effective machine learning algorithm, testing of this algorithm for the two-class problem, and expansion of the solution for other classes of rhythm disorders. Additionally, it is possible to improve classification results for the three-class problem by using a superior model and introducing additional clustering.","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elmira A. Gumerova, Svetlana N. Dubrovskikh, Alena V. Tatarina, Yulia A. Stepanova, Anna D. Koryagina
BACKGROUND: Considering the large number of limb amputations in war-related gunshot wounds, early diagnosis of terminal neuromas is important to provide appropriate limb replacement. AIM: The aim of this study was to determine the feasibility of ultrasound in evaluating peripheral nerve endings and detecting terminal neuromas in patients after limb amputation due to gunshot trauma. MATERIALS AND METHODS: A total of 71 patients (men aged 20–57 years old) underwent ultrasound examination of 179 peripheral nerves. The examination was conducted according to standard technique using the ACUSON S2000 scanner (Siemens Healthineers, Germany) with a linear transducer with a frequency of 7–17 MHz, after setting the program of musculoskeletal examination. The cause of amputation was gunshot trauma. The duration of gunshot trauma ranged from 11 to 362 days, while the period between surgical intervention and the examination ranged from 11 to 340 days. The indication for the examination was pain in the limb stumps. RESULTS: A comprehensive examination of 179 peripheral nerves revealed 149 injured endings that were subjected to further evaluation. The distribution of lesion frequency revealed that the shoulder level was the most affected area in the upper extremities, while the thigh was the most affected area in the lower extremities. Notably, lesions on the left side were more prevalent in both cases. All observed changes in the endings were classified into three distinct groups: Group 1 (60%) comprised structural changes without signs of terminal neuroma. Group 2 (25%) consisted of structural changes with terminal neuroma. Group 3 (15%) included structural changes with potential (forming) terminal neuroma. In the absence of a terminal neuroma, ultrasound findings may include thickening of the nerve ending with preserved fascicular structure, decreased echogenicity, and increased vascularization of the nerve ending in color Doppler mapping. The ultrasound findings suggestive of a potential terminal neuroma include the following: the same and the presence of a globular hypoechogenic mass emanating from the nerve ending, the absence of differentiation into fasciculi in the mass, the latter not occupying the entire cross-sectional area of the nerve ending, and the mass being avascular on color Doppler mapping. The ultrasound findings of a formed terminal neuroma include the following: a club-shaped or globular hypoechogenic mass exceeding the cross-sectional area of the nerve proximally by 2 or more times, emanating from the nerve ending; absence of differentiation into fasciculi in the formation; the formation occupying the entire cross-sectional area of the nerve ending and being avascular in color Doppler mapping. The timing of terminal neuroma formation was observed to occur on average 109.9 days (14–362) after gunshot trauma and 98.2 days (14–340) after surgical intervention. The formation of terminal neuromas was observed on average 153.3 days (31–3
{"title":"Ultrasound assessment of structural changes in peripheral nerves of extremities after amputation in case of gunshot injury","authors":"Elmira A. Gumerova, Svetlana N. Dubrovskikh, Alena V. Tatarina, Yulia A. Stepanova, Anna D. Koryagina","doi":"10.17816/dd626173","DOIUrl":"https://doi.org/10.17816/dd626173","url":null,"abstract":"BACKGROUND: Considering the large number of limb amputations in war-related gunshot wounds, early diagnosis of terminal neuromas is important to provide appropriate limb replacement. \u0000AIM: The aim of this study was to determine the feasibility of ultrasound in evaluating peripheral nerve endings and detecting terminal neuromas in patients after limb amputation due to gunshot trauma. \u0000MATERIALS AND METHODS: A total of 71 patients (men aged 20–57 years old) underwent ultrasound examination of 179 peripheral nerves. The examination was conducted according to standard technique using the ACUSON S2000 scanner (Siemens Healthineers, Germany) with a linear transducer with a frequency of 7–17 MHz, after setting the program of musculoskeletal examination. The cause of amputation was gunshot trauma. The duration of gunshot trauma ranged from 11 to 362 days, while the period between surgical intervention and the examination ranged from 11 to 340 days. The indication for the examination was pain in the limb stumps. \u0000RESULTS: A comprehensive examination of 179 peripheral nerves revealed 149 injured endings that were subjected to further evaluation. The distribution of lesion frequency revealed that the shoulder level was the most affected area in the upper extremities, while the thigh was the most affected area in the lower extremities. Notably, lesions on the left side were more prevalent in both cases. All observed changes in the endings were classified into three distinct groups: Group 1 (60%) comprised structural changes without signs of terminal neuroma. Group 2 (25%) consisted of structural changes with terminal neuroma. Group 3 (15%) included structural changes with potential (forming) terminal neuroma. \u0000In the absence of a terminal neuroma, ultrasound findings may include thickening of the nerve ending with preserved fascicular structure, decreased echogenicity, and increased vascularization of the nerve ending in color Doppler mapping. \u0000The ultrasound findings suggestive of a potential terminal neuroma include the following: the same and the presence of a globular hypoechogenic mass emanating from the nerve ending, the absence of differentiation into fasciculi in the mass, the latter not occupying the entire cross-sectional area of the nerve ending, and the mass being avascular on color Doppler mapping. \u0000The ultrasound findings of a formed terminal neuroma include the following: a club-shaped or globular hypoechogenic mass exceeding the cross-sectional area of the nerve proximally by 2 or more times, emanating from the nerve ending; absence of differentiation into fasciculi in the formation; the formation occupying the entire cross-sectional area of the nerve ending and being avascular in color Doppler mapping. \u0000The timing of terminal neuroma formation was observed to occur on average 109.9 days (14–362) after gunshot trauma and 98.2 days (14–340) after surgical intervention. The formation of terminal neuromas was observed on average 153.3 days (31–3","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"195 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
BACKGROUND: Ophthalmic tonometers are instruments used for the measurement of intraocular pressure in the diagnosis and monitoring of conditions in which the level of intraocular pressure deviates from the individual norm. One such tonometer is the iCare, which operates on the rebound principle [1]. A small rod is directed towards the cornea, the nature of its movement is analyzed, and the device calculates the intraocular pressure [1, 2]. The use of rebound technology for the advancement of a portable eye tonometer will facilitate the development of a convenient, accurate, and reliable device for the measurement of intraocular pressure. AIM: The aim of this study is to identify the principal advantages and disadvantages of the iCare ophthalmic tonometer, with a view to facilitating the further development of a Russian analogue. MATERIALS AND METHODS: The authors conducted a comprehensive literature review, searching for relevant publications in PubMed, Web of Science, Scopus, and eLibrary databases from 2005 to 2023. The search terms used were “rebound tonometry”, “iCare tonometry”, and “intraocular pressure”. A total of 17 scientific articles were analyzed. RESULTS: The main advantages of the iCare tonometer are highlighted: No patient discomfort due to minimal corneal contact time, no anesthesia required [1, 2]; The accuracy of the indicators measured by the iCare tonometer is comparable to the gold standard of intraocular pressure measurement, the Goldmann tonometer [3, 4, 6]; Portability and compactness of the tonometer, ability to measure pressure in a sitting or lying position [1, 2]; Intraocular pressure measurement takes little time [1, 16, 17]; The use of a disposable handpiece minimizes the risk of infectious disease transmission [16]; Possibility to measure intraocular pressure in eyes with various pathologies, such as glaucoma, keratoconus [9, 10], post-refractive surgery [11] and keratoplasty [8, 12, 13], vitreous cavity tamponade with silicone [14]; The iCare tonometer does not require regular maintenance and calibration, is easy to use, and can be used by other professionals and patients at home [16, 17]. Disadvantages include: High cost compared to other tonometers, requiring regular purchase of disposable probes [15, 17]; The limited use of the iCare tonometer in patients with corneal abnormalities, namely patients with an abnormal corneal resistance factor or corneal hysteresis [5, 7]. CONCLUSIONS: The iCare tonometer offers a number of advantages, including patient safety and comfort during the examination, accuracy, portability, quick results, and the ability to be used on healthy eyes as well as on eyes with various diseases or after surgery. However, it also has some limitations when used in certain clinical cases, as well as a high cost. Despite these limitations, the iCare tonometer remains a valuable tool for measuring intraocular pressure. Therefore, we propose to use the rebound technology employe
{"title":"Advantages and disadvantages of the iCare tonometer: prospects for medical use","authors":"Mariya A. Telelyasova, Anastasiia O. Ukina","doi":"10.17816/dd627017","DOIUrl":"https://doi.org/10.17816/dd627017","url":null,"abstract":"BACKGROUND: Ophthalmic tonometers are instruments used for the measurement of intraocular pressure in the diagnosis and monitoring of conditions in which the level of intraocular pressure deviates from the individual norm. One such tonometer is the iCare, which operates on the rebound principle [1]. A small rod is directed towards the cornea, the nature of its movement is analyzed, and the device calculates the intraocular pressure [1, 2]. The use of rebound technology for the advancement of a portable eye tonometer will facilitate the development of a convenient, accurate, and reliable device for the measurement of intraocular pressure. \u0000AIM: The aim of this study is to identify the principal advantages and disadvantages of the iCare ophthalmic tonometer, with a view to facilitating the further development of a Russian analogue. \u0000MATERIALS AND METHODS: The authors conducted a comprehensive literature review, searching for relevant publications in PubMed, Web of Science, Scopus, and eLibrary databases from 2005 to 2023. The search terms used were “rebound tonometry”, “iCare tonometry”, and “intraocular pressure”. A total of 17 scientific articles were analyzed. \u0000RESULTS: The main advantages of the iCare tonometer are highlighted: \u0000 \u0000No patient discomfort due to minimal corneal contact time, no anesthesia required [1, 2]; \u0000The accuracy of the indicators measured by the iCare tonometer is comparable to the gold standard of intraocular pressure measurement, the Goldmann tonometer [3, 4, 6]; \u0000Portability and compactness of the tonometer, ability to measure pressure in a sitting or lying position [1, 2]; \u0000Intraocular pressure measurement takes little time [1, 16, 17]; \u0000The use of a disposable handpiece minimizes the risk of infectious disease transmission [16]; \u0000Possibility to measure intraocular pressure in eyes with various pathologies, such as glaucoma, keratoconus [9, 10], post-refractive surgery [11] and keratoplasty [8, 12, 13], vitreous cavity tamponade with silicone [14]; \u0000The iCare tonometer does not require regular maintenance and calibration, is easy to use, and can be used by other professionals and patients at home [16, 17]. \u0000 \u0000Disadvantages include: \u0000 \u0000High cost compared to other tonometers, requiring regular purchase of disposable probes [15, 17]; \u0000The limited use of the iCare tonometer in patients with corneal abnormalities, namely patients with an abnormal corneal resistance factor or corneal hysteresis [5, 7]. \u0000 \u0000CONCLUSIONS: The iCare tonometer offers a number of advantages, including patient safety and comfort during the examination, accuracy, portability, quick results, and the ability to be used on healthy eyes as well as on eyes with various diseases or after surgery. However, it also has some limitations when used in certain clinical cases, as well as a high cost. Despite these limitations, the iCare tonometer remains a valuable tool for measuring intraocular pressure. Therefore, we propose to use the rebound technology employe","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"177 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141681951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Evgeniya A. Safyannikova, A. Kryukov, N. Kunel’skaya, P. Sudarev, S. Romanenko, D. I. Kurbanova, E. V. Lesogorova, E. N. Krasil’nikova, Anastasiya A. Ivanova, Anton P. Osadchiy, Natalya G. Shevyrina
BACKGROUND: Currently, artificial intelligence in the form of artificial neural networks is being actively implemented in a number of areas of our lives, including medicine. In particular, in otorhinolaryngology, artificial neural networks are used to analyze images obtained during endoscopic examinations of patients (e.g., videolaryngoscopy) [1–3]. The interpretation of laryngoscopic images often presents significant difficulties for practicing physicians, which reduces the frequency of detection of precancerous laryngeal diseases and contributes to the increase in the number of patients with stage III–IV laryngeal cancer [4, 5]. This underscores the significance of prompt performance and accurate interpretation of the findings of endoscopic examinations of patients with laryngeal disorders. Artificial neural networks can be employed to analyze the results of videolaryngoscopy, furnishing the physician with supplementary information that can enhance diagnostic accuracy and diminish the probability of error [6, 7]. AIM: The study aims to develop and train an artificial neural network for recognizing characteristic features of laryngeal neoplasms and variants of laryngeal normality. MATERIALS AND METHODS: The study was conducted under the grant of the Moscow Center for Innovative Technologies in Healthcare (grant No. 2112-1/22) entitled “Using Neural Networks (Artificial Intelligence Algorithms) for Control and Improving the Quality of Diagnosis and Treatment of Diseases of Laryngeal and Ear Structures through Digital Technologies”.The following methods were used during the course of the study: data collection for the creation of a photobank (dataset) of medical images obtained during videolaryngoscopy; data partitioning for the formation of datasets for individual nosologies and groups of diseases; the method of consilium; analysis of the accuracy of recognition and classification of digital endoscopic images; and training of classification neural networks. Consequently, a dataset comprising 1,471 laryngeal images in digital formats (JPEG, BMP) was assembled, labelled, and uploaded for the purpose of training the artificial neural network. Of the total number of images, 410 were classified as pertaining to laryngeal formation, while 1061 were classified as variants of normality. Subsequently, the neural network was trained and tested to identify the signs of normal and laryngeal masses. RESULTS: The results of the testing of the artificial neural network indicated the formation of an inaccuracy matrix, the calculation of the value of recognition accuracy, the calculation of the quality indicators of the model performance, and the construction of the ROC curve. The developed and trained artificial neural network demonstrated an accuracy of 86% in recognizing the signs of laryngeal masses and norms. CONCLUSIONS: This study demonstrates that a trained artificial neural network can successfully distinguish between signs of normal and laryngeal m
背景：目前，以人工神经网络为形式的人工智能正积极应用于我们生活的多个领域，包括医学。特别是在耳鼻喉科领域，人工神经网络被用于分析在对患者进行内窥镜检查（如视频喉镜检查）时获得的图像 [1-3]。喉镜图像的判读往往给执业医师带来很大困难，从而降低了喉癌前疾病的发现率，并导致 III-IV 期喉癌患者人数的增加 [4，5]。这凸显了对喉疾病患者及时进行内窥镜检查并准确解读检查结果的重要性。人工神经网络可用于分析视频喉镜检查的结果，为医生提供补充信息，从而提高诊断准确性并降低出错概率[6, 7]。目的：本研究旨在开发和训练一种人工神经网络，用于识别喉肿瘤和喉正常变异的特征。材料与方法：本研究在莫斯科医疗保健创新技术中心（Moscow Center for Innovative Technologies in Healthcare）的资助下进行（资助编号：2112-1/22），题为 "通过数字技术使用神经网络（人工智能算法）控制和提高喉与耳部结构疾病的诊断和治疗质量"。在研究过程中使用了以下方法：收集数据，建立视频喉镜检查过程中获得的医学影像图片库（数据集）；数据分区，形成单个病名和疾病组的数据集；会诊方法；分析数字内窥镜图像识别和分类的准确性；以及训练分类神经网络。因此，为了训练人工神经网络，我们收集、标注并上传了由 1,471 张数字格式（JPEG、BMP）喉部图像组成的数据集。在所有图像中，410 张被归类为与喉形成有关，1061 张被归类为正常变体。随后，对神经网络进行了训练和测试，以识别正常肿块和喉肿块的迹象。结果：人工神经网络的测试结果表明，形成了误差矩阵，计算了识别准确率值，计算了模型性能的质量指标，并构建了 ROC 曲线。经过开发和训练的人工神经网络在识别喉部肿块和正常体征方面的准确率为 86%。结论：本研究表明，经过训练的人工神经网络可以成功区分内窥镜照片中的正常肿块和喉肿块。随着神经网络的进一步训练和高精确度的实现，该技术可在临床实践中用作喉镜图像解读和喉肿块早期诊断的助手。它还可用于控制和提高初级保健医生对喉、鼻、耳疾病的诊断和治疗质量。
{"title":"Potential of a neural network in the diagnosis of laryngeal tumors","authors":"Evgeniya A. Safyannikova, A. Kryukov, N. Kunel’skaya, P. Sudarev, S. Romanenko, D. I. Kurbanova, E. V. Lesogorova, E. N. Krasil’nikova, Anastasiya A. Ivanova, Anton P. Osadchiy, Natalya G. Shevyrina","doi":"10.17816/dd627076","DOIUrl":"https://doi.org/10.17816/dd627076","url":null,"abstract":"BACKGROUND: Currently, artificial intelligence in the form of artificial neural networks is being actively implemented in a number of areas of our lives, including medicine. In particular, in otorhinolaryngology, artificial neural networks are used to analyze images obtained during endoscopic examinations of patients (e.g., videolaryngoscopy) [1–3]. The interpretation of laryngoscopic images often presents significant difficulties for practicing physicians, which reduces the frequency of detection of precancerous laryngeal diseases and contributes to the increase in the number of patients with stage III–IV laryngeal cancer [4, 5]. This underscores the significance of prompt performance and accurate interpretation of the findings of endoscopic examinations of patients with laryngeal disorders. Artificial neural networks can be employed to analyze the results of videolaryngoscopy, furnishing the physician with supplementary information that can enhance diagnostic accuracy and diminish the probability of error [6, 7]. \u0000AIM: The study aims to develop and train an artificial neural network for recognizing characteristic features of laryngeal neoplasms and variants of laryngeal normality. \u0000MATERIALS AND METHODS: The study was conducted under the grant of the Moscow Center for Innovative Technologies in Healthcare (grant No. 2112-1/22) entitled “Using Neural Networks (Artificial Intelligence Algorithms) for Control and Improving the Quality of Diagnosis and Treatment of Diseases of Laryngeal and Ear Structures through Digital Technologies”.The following methods were used during the course of the study: data collection for the creation of a photobank (dataset) of medical images obtained during videolaryngoscopy; data partitioning for the formation of datasets for individual nosologies and groups of diseases; the method of consilium; analysis of the accuracy of recognition and classification of digital endoscopic images; and training of classification neural networks. \u0000Consequently, a dataset comprising 1,471 laryngeal images in digital formats (JPEG, BMP) was assembled, labelled, and uploaded for the purpose of training the artificial neural network. Of the total number of images, 410 were classified as pertaining to laryngeal formation, while 1061 were classified as variants of normality. Subsequently, the neural network was trained and tested to identify the signs of normal and laryngeal masses. \u0000RESULTS: The results of the testing of the artificial neural network indicated the formation of an inaccuracy matrix, the calculation of the value of recognition accuracy, the calculation of the quality indicators of the model performance, and the construction of the ROC curve. The developed and trained artificial neural network demonstrated an accuracy of 86% in recognizing the signs of laryngeal masses and norms. \u0000CONCLUSIONS: This study demonstrates that a trained artificial neural network can successfully distinguish between signs of normal and laryngeal m","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"75 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. Frolova, U. N. Tumanova, Viktorya A. Sakalo, Kristina A. Gladkova, V. Bychenko, A. I. Shchegolev
BACKGROUND: Twin pregnancies compared to singleton pregnancies are characterized by a higher incidence of complications, particularly fetal growth retardation [1]. The main causes of discordance and fetal growth retardation are considered to be differences in the size of placental sites, leading to uneven metabolism of substances and blood, as well as disorders of fetal blood supply caused by vascular anastomoses in the placenta [2, 3]. Computed tomography with the administration of contrast agents can be an effective method to assess the angioarchitectonics and vascularization of the placenta after delivery [4]. AIM: The aim of this study is to conduct a comprehensive computed tomography and morphological evaluation of the vascularization features of monochorionic diamniotic placentas with discordant neonatal weight. MATERIALS AND METHODS: This study was based on the analysis of 33 monochorionic diamniotic placentas obtained after delivery at 27–37 weeks of gestation using the original complex computed tomography and morphological method of investigation [5]. Upon obtaining the placenta, its mass and size of placental sites were determined, as well as the type of attachment, length, diameter, and degree of cord tortuosity. Prior to the computed tomography examination, the umbilical cord and its major branches were cleared of blood clots. The placenta was then immersed in a 10% hypertonic sodium chloride solution and placed on hygroscopic material. Subsequently, contrast dye mixtures of varying colors and concentrations were gradually injected into the unpaired umbilical vein, followed by the umbilical arteries in a sequential manner. The contrast dye mixtures consisted of a water-soluble radiopaque contrast agent, iodixanol, in an aqueous solution of gouache dye. The concentration of the contrast agent in the mixture for injection into the umbilical arteries was 70%, while in the vein it was 15%. The first and second placentae were injected with red and yellow gouache dyes, respectively, into the arteries of the umbilical cord, while blue and green gouache dyes were used for the veins. Following each injection of the contrast dye mixture into the umbilical cord vessel, a visual assessment of the vessel’s branching was conducted, followed by computed tomography on a Toshiba Aquilion ONE 640 (Pediatric 0.5 software package according to the Abdomen Baby study protocol). The final stage involved a traditional macroscopic and microscopic examination of the placenta [6]. RESULTS: The study revealed that the mean value of birth weight discordance in twins was 22.7 ± 2.1%, while placental site discordance was 26.6 ± 5.0%. Vascular anastomoses were identified in 74.2% of twin placentas. Of these, 19 cases exhibited one anastomosis, three cases demonstrated two anastomoses, and one case exhibited five anastomoses. Arterio-arterial anastomoses were observed with greater frequency, while veno-venous and arteriovenous anastomoses were observed with less f
{"title":"Complex morphological and computed tomographic characteristics of vascularization of monochorionic diamniotic placentas with discordant weight of newborns","authors":"E. Frolova, U. N. Tumanova, Viktorya A. Sakalo, Kristina A. Gladkova, V. Bychenko, A. I. Shchegolev","doi":"10.17816/dd626043","DOIUrl":"https://doi.org/10.17816/dd626043","url":null,"abstract":"BACKGROUND: Twin pregnancies compared to singleton pregnancies are characterized by a higher incidence of complications, particularly fetal growth retardation [1]. The main causes of discordance and fetal growth retardation are considered to be differences in the size of placental sites, leading to uneven metabolism of substances and blood, as well as disorders of fetal blood supply caused by vascular anastomoses in the placenta [2, 3]. Computed tomography with the administration of contrast agents can be an effective method to assess the angioarchitectonics and vascularization of the placenta after delivery [4]. \u0000AIM: The aim of this study is to conduct a comprehensive computed tomography and morphological evaluation of the vascularization features of monochorionic diamniotic placentas with discordant neonatal weight. \u0000MATERIALS AND METHODS: This study was based on the analysis of 33 monochorionic diamniotic placentas obtained after delivery at 27–37 weeks of gestation using the original complex computed tomography and morphological method of investigation [5]. Upon obtaining the placenta, its mass and size of placental sites were determined, as well as the type of attachment, length, diameter, and degree of cord tortuosity. Prior to the computed tomography examination, the umbilical cord and its major branches were cleared of blood clots. The placenta was then immersed in a 10% hypertonic sodium chloride solution and placed on hygroscopic material. Subsequently, contrast dye mixtures of varying colors and concentrations were gradually injected into the unpaired umbilical vein, followed by the umbilical arteries in a sequential manner. The contrast dye mixtures consisted of a water-soluble radiopaque contrast agent, iodixanol, in an aqueous solution of gouache dye. The concentration of the contrast agent in the mixture for injection into the umbilical arteries was 70%, while in the vein it was 15%. The first and second placentae were injected with red and yellow gouache dyes, respectively, into the arteries of the umbilical cord, while blue and green gouache dyes were used for the veins. Following each injection of the contrast dye mixture into the umbilical cord vessel, a visual assessment of the vessel’s branching was conducted, followed by computed tomography on a Toshiba Aquilion ONE 640 (Pediatric 0.5 software package according to the Abdomen Baby study protocol). The final stage involved a traditional macroscopic and microscopic examination of the placenta [6]. \u0000RESULTS: The study revealed that the mean value of birth weight discordance in twins was 22.7 ± 2.1%, while placental site discordance was 26.6 ± 5.0%. Vascular anastomoses were identified in 74.2% of twin placentas. Of these, 19 cases exhibited one anastomosis, three cases demonstrated two anastomoses, and one case exhibited five anastomoses. Arterio-arterial anastomoses were observed with greater frequency, while veno-venous and arteriovenous anastomoses were observed with less f","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":" 48","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141680993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Danila V. Yudakov, A. A. Trukhin, M. S. Sheremeta, Anatoliy S. Makeev, V. D. Yartsev
BACKGROUND: Lacrimal glands and lacrimal pathways are one of the main undesirable targets during radionuclide therapy using I-131, namely, in 24% of cases, secondary lacrimal pathways obliteration occurs [1]. In the legislation of the Russian Federation in the field of atomic energy use, there are a number of administrative documents obliging to keep records and control of individual radiation doses with the provision of data to the unified system for monitoring individual radiation doses of citizens. At the same time, statistical analysis does not include systematic accounting and control of individual doses of internal radiation to patients, in particular, to the lacrimal apparatus, when using nuclear medicine methods for therapeutic purposes. AIM: To develop a software and hardware preventive complex — a system for accounting and monitoring dose loads on lacrimal pathways during radioiodotherapy. MATERIALS AND METHODS: GE Discovery NM/CT 670 imaging systems, GE Discovery NM 630, the Xeleris 4 DR Workstation nuclear Medicine Workstation and the I-131-based radioisotope were used. To exclude the ingress of radioisotope into lacrimal pathways, the use of vasoconstrictive drugs and the use of tear point obturators were considered. The client part of the web service was implemented based on the React JavaScript library. The development of the Backend component was carried out in the Python programming language. RESULTS: To assess the risk of complications, a method was developed that takes into account the following parameters: age, gender, total administered activity to the patient, the presence of current lacrimation at the time of hospitalization, the presence of menopause (for women) and the accumulation index I-131 in lacrimal pathways. The primary data (anamnesis and prescribed treatment) are entered by the patient's attending physician in the questionnaire during the initial examination. At 72 hours after the introduction of radioisotope, using a molecular imaging system, a medical physicist determines the index of accumulation of radioisotope in lacrimal pathways. Based on the data obtained, the overall risk level of secondary obliteration of the lacrimal tract is determined and, depending on the result obtained, appropriate recommendations are made to the patient. Since the described process is quite time-consuming in a clinical setting, an intelligent medical decision support system has been developed that allows automating the process and minimizing the likelihood of errors. CONCLUSION: The development of a software and hardware preventive complex will make it possible to prescribe preventive methods with greater efficiency at all stages of the course of treatment in order to minimize the occurrence of adverse events (such as secondary obliteration of the tear ducts), which in turn will improve the quality of life of patients.
{"title":"The system of accounting and control of dose loads on the lacrimal apparatus during radiotherapy of thyroid cancer","authors":"Danila V. Yudakov, A. A. Trukhin, M. S. Sheremeta, Anatoliy S. Makeev, V. D. Yartsev","doi":"10.17816/dd626191","DOIUrl":"https://doi.org/10.17816/dd626191","url":null,"abstract":"BACKGROUND: Lacrimal glands and lacrimal pathways are one of the main undesirable targets during radionuclide therapy using I-131, namely, in 24% of cases, secondary lacrimal pathways obliteration occurs [1]. In the legislation of the Russian Federation in the field of atomic energy use, there are a number of administrative documents obliging to keep records and control of individual radiation doses with the provision of data to the unified system for monitoring individual radiation doses of citizens. At the same time, statistical analysis does not include systematic accounting and control of individual doses of internal radiation to patients, in particular, to the lacrimal apparatus, when using nuclear medicine methods for therapeutic purposes. \u0000AIM: To develop a software and hardware preventive complex — a system for accounting and monitoring dose loads on lacrimal pathways during radioiodotherapy. \u0000MATERIALS AND METHODS: GE Discovery NM/CT 670 imaging systems, GE Discovery NM 630, the Xeleris 4 DR Workstation nuclear Medicine Workstation and the I-131-based radioisotope were used. To exclude the ingress of radioisotope into lacrimal pathways, the use of vasoconstrictive drugs and the use of tear point obturators were considered. The client part of the web service was implemented based on the React JavaScript library. The development of the Backend component was carried out in the Python programming language. \u0000RESULTS: To assess the risk of complications, a method was developed that takes into account the following parameters: age, gender, total administered activity to the patient, the presence of current lacrimation at the time of hospitalization, the presence of menopause (for women) and the accumulation index I-131 in lacrimal pathways. The primary data (anamnesis and prescribed treatment) are entered by the patient's attending physician in the questionnaire during the initial examination. At 72 hours after the introduction of radioisotope, using a molecular imaging system, a medical physicist determines the index of accumulation of radioisotope in lacrimal pathways. Based on the data obtained, the overall risk level of secondary obliteration of the lacrimal tract is determined and, depending on the result obtained, appropriate recommendations are made to the patient. Since the described process is quite time-consuming in a clinical setting, an intelligent medical decision support system has been developed that allows automating the process and minimizing the likelihood of errors. \u0000CONCLUSION: The development of a software and hardware preventive complex will make it possible to prescribe preventive methods with greater efficiency at all stages of the course of treatment in order to minimize the occurrence of adverse events (such as secondary obliteration of the tear ducts), which in turn will improve the quality of life of patients.","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"108 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Valeria G. Logunkova, Mahmud M. Mazlum, Alexander V. Kuznetsov
BACKGROUND: Complete prosthetics employs the use of collapsible navigable surgical templates, which can effectively mitigate the complications associated with dental implantation at each stage of the process [1–3]. The correct positioning of the implant is of paramount importance, as it directly influences the success of subsequent prosthetics. This is because the planning of the surgical template is conducted simultaneously, taking into account the subsequent prosthetic construction [4–6]. AIM: The study aimed to compare the technique of using collapsible surgical templates versus simple ones in complete dentures. MATERIALS AND METHODS: The main group consisted of 15 patients, aged 52–70 years, with four women and 11 men. Half of the patients exhibited marked atrophy of the maxilla, while the other half exhibited atrophy of the mandible. All patients underwent the technique of using collapsible surgical templates in full dentures with immediate loading. The control group consisted of 15 patients aged 50–67 years, 6 men and 9 women. They underwent surgery with the use of a conventional surgical navigation template and in whom fixation of the prosthetic structure was performed by the classical method. RESULTS: In the primary group, the initial two components of the collapsible template are fixed to the teeth. The template structures are connected to each other with pins, which eliminates micro-vibrations of the initial component. The second template element is then removed. Following the removal of the teeth, the third component of the surgical template is fixed to the pins of the initial component. Following the placement of dental implants, the temporary prosthetic construction is also fixed using a special template. The control group underwent standard surgical technique with a simple surgical template. In the main group, the accuracy of implant positioning, reduction of the risk of complications, and reduction of the operation time were observed. One-stage fixation of the temporary prosthetic structure did not cause aesthetic and functional inconvenience to the patients. In the control group, errors in implant placement were observed in 34% of cases, and intraoperative complications related to neuralgia developed. CONCLUSIONS: The use of advanced technology enhances the effectiveness of dental implantation.
{"title":"Use of collapsible surgical templates in full dentures with immediate loading","authors":"Valeria G. Logunkova, Mahmud M. Mazlum, Alexander V. Kuznetsov","doi":"10.17816/dd626183","DOIUrl":"https://doi.org/10.17816/dd626183","url":null,"abstract":"BACKGROUND: Complete prosthetics employs the use of collapsible navigable surgical templates, which can effectively mitigate the complications associated with dental implantation at each stage of the process [1–3]. The correct positioning of the implant is of paramount importance, as it directly influences the success of subsequent prosthetics. This is because the planning of the surgical template is conducted simultaneously, taking into account the subsequent prosthetic construction [4–6]. \u0000AIM: The study aimed to compare the technique of using collapsible surgical templates versus simple ones in complete dentures. \u0000MATERIALS AND METHODS: The main group consisted of 15 patients, aged 52–70 years, with four women and 11 men. Half of the patients exhibited marked atrophy of the maxilla, while the other half exhibited atrophy of the mandible. All patients underwent the technique of using collapsible surgical templates in full dentures with immediate loading. The control group consisted of 15 patients aged 50–67 years, 6 men and 9 women. They underwent surgery with the use of a conventional surgical navigation template and in whom fixation of the prosthetic structure was performed by the classical method. \u0000RESULTS: In the primary group, the initial two components of the collapsible template are fixed to the teeth. The template structures are connected to each other with pins, which eliminates micro-vibrations of the initial component. The second template element is then removed. Following the removal of the teeth, the third component of the surgical template is fixed to the pins of the initial component. Following the placement of dental implants, the temporary prosthetic construction is also fixed using a special template. \u0000The control group underwent standard surgical technique with a simple surgical template. \u0000In the main group, the accuracy of implant positioning, reduction of the risk of complications, and reduction of the operation time were observed. One-stage fixation of the temporary prosthetic structure did not cause aesthetic and functional inconvenience to the patients. In the control group, errors in implant placement were observed in 34% of cases, and intraoperative complications related to neuralgia developed. \u0000CONCLUSIONS: The use of advanced technology enhances the effectiveness of dental implantation.","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"111 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nikita E. Levashov, A. Oleynikov, Sergey A. Romanov
BACKGROUND: Modern dentistry is not without advanced technologies, and intraoral scanning is becoming an increasingly important element of diagnosis and treatment. This technology is constantly evolving, offering new possibilities. The fundamental principles underlying the functionality of the intraoral scanner are light-measuring technology and photogrammetry. Light-emitting diodes integrated into the scanner body emit light onto the surface of the teeth, and sensors subsequently record the reflected signals, thereby creating an accurate three-dimensional model. The data is then processed by software that generates detailed digital models of the patient's jaws that are compatible with 3D CT data [1]. AIM: The study aimed to assess the potential of three-dimensional scanning for the planning and implementation of a single-stage dental implant protocol. MATERIALS AND METHODS: Patient M., aged 41, presented to the dental clinic with complaints of a fractured tooth on the upper jaw (1.2). A decision was made to perform a single-stage implantation with the extraction of tooth 1.2 and the placement of a temporary crown based on the results of the examination. Intraoral scanning of the jaws was performed for the fabrication of the crown, as the cutting edge of the tooth was destroyed by two-thirds and the tooth fragment was lost. In order to create a model of the crown, the horizontal inversion technique was used. Tooth 2.2 was extracted from the scan of the upper jaw and inverted horizontally, resulting in a copy of tooth 1.2 in the expanded state. This was done to reproduce the exact shape of the future crown. The design of the crown was modeled in the program in conjunction with the loaded model of the temporary abutment (implant suprastructure for the fixation of the artificial crown). This approach enabled the accurate contour of the crown eruption and correct positioning relative to the gingival cuff and the abutment shaft to be obtained. RESULTS: The implementation of the technique permitted the creation of an accurate and anatomically correct model of the crown of the replaced tooth without its introduction into occlusion, thereby reducing the risk of functional overload of the implant during the period of osseointegration (engraftment) [2]. The applied method enables the exclusion of the stage of crown correction at the moment of its fixation and the combination of 3D scans with data from computed tomography for the detailed planning of the surgery. Furthermore, the use of 3D scans permitted the visualization of the projected position of the future temporary crown, thereby enabling the precise positioning of the implant in an anatomically correct location. CONCLUSIONS: This case study illustrates the efficacy of planning and implementing single-stage implantation with the aid of intraoral jaw scanning, as it reduces treatment duration, eliminates the necessity for implant loading, and ensures the attainment of a predictable treatment outco
{"title":"3D scanning possibilities in modern dentistry","authors":"Nikita E. Levashov, A. Oleynikov, Sergey A. Romanov","doi":"10.17816/dd625965","DOIUrl":"https://doi.org/10.17816/dd625965","url":null,"abstract":"BACKGROUND: Modern dentistry is not without advanced technologies, and intraoral scanning is becoming an increasingly important element of diagnosis and treatment. This technology is constantly evolving, offering new possibilities. The fundamental principles underlying the functionality of the intraoral scanner are light-measuring technology and photogrammetry. Light-emitting diodes integrated into the scanner body emit light onto the surface of the teeth, and sensors subsequently record the reflected signals, thereby creating an accurate three-dimensional model. The data is then processed by software that generates detailed digital models of the patient's jaws that are compatible with 3D CT data [1]. \u0000AIM: The study aimed to assess the potential of three-dimensional scanning for the planning and implementation of a single-stage dental implant protocol. \u0000MATERIALS AND METHODS: Patient M., aged 41, presented to the dental clinic with complaints of a fractured tooth on the upper jaw (1.2). A decision was made to perform a single-stage implantation with the extraction of tooth 1.2 and the placement of a temporary crown based on the results of the examination. Intraoral scanning of the jaws was performed for the fabrication of the crown, as the cutting edge of the tooth was destroyed by two-thirds and the tooth fragment was lost. In order to create a model of the crown, the horizontal inversion technique was used. Tooth 2.2 was extracted from the scan of the upper jaw and inverted horizontally, resulting in a copy of tooth 1.2 in the expanded state. This was done to reproduce the exact shape of the future crown. The design of the crown was modeled in the program in conjunction with the loaded model of the temporary abutment (implant suprastructure for the fixation of the artificial crown). This approach enabled the accurate contour of the crown eruption and correct positioning relative to the gingival cuff and the abutment shaft to be obtained. \u0000RESULTS: The implementation of the technique permitted the creation of an accurate and anatomically correct model of the crown of the replaced tooth without its introduction into occlusion, thereby reducing the risk of functional overload of the implant during the period of osseointegration (engraftment) [2]. The applied method enables the exclusion of the stage of crown correction at the moment of its fixation and the combination of 3D scans with data from computed tomography for the detailed planning of the surgery. Furthermore, the use of 3D scans permitted the visualization of the projected position of the future temporary crown, thereby enabling the precise positioning of the implant in an anatomically correct location. \u0000CONCLUSIONS: This case study illustrates the efficacy of planning and implementing single-stage implantation with the aid of intraoral jaw scanning, as it reduces treatment duration, eliminates the necessity for implant loading, and ensures the attainment of a predictable treatment outco","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"78 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alexey V. Kokukhin, Mikhail N. Zhuravlev, Elena A. Ponomareva, Railya F. Bakieva, Ekaterina P. Stremaus, Evgenia L. Zhigalova, Sergey A. Murunov, Yana V. Yatsenko
Transient global amnesia (TGA) is considered as one of the variants of transient ischemic attack (TIA). Unlike the diagnosis of cerebral infarction, the definition of TIA presupposes not only the reversibility of neurological symptoms, but also the absence of morphological signs of cerebral infarction detected by imaging methods. While the clinical diagnosis of TGA is not difficult, there is no clear opinion regarding changes on MRI. The use of high-field MRI devices (3T, 7T) shows a fairly high frequency of detecting point DWI changes in the hippocampal projection (up to 50%), which can be used as one of the objective criteria for the diagnosis of TGA
{"title":"CHANGES ON DIFFUSION-WEIGHTED MRT (DWI) IN THE HIPPOCAMPUS IN TRANSIENT GLOBAL AMNESIA","authors":"Alexey V. Kokukhin, Mikhail N. Zhuravlev, Elena A. Ponomareva, Railya F. Bakieva, Ekaterina P. Stremaus, Evgenia L. Zhigalova, Sergey A. Murunov, Yana V. Yatsenko","doi":"10.17816/dd627030","DOIUrl":"https://doi.org/10.17816/dd627030","url":null,"abstract":"Transient global amnesia (TGA) is considered as one of the variants of transient ischemic attack (TIA). Unlike the diagnosis of cerebral infarction, the definition of TIA presupposes not only the reversibility of neurological symptoms, but also the absence of morphological signs of cerebral infarction detected by imaging methods. While the clinical diagnosis of TGA is not difficult, there is no clear opinion regarding changes on MRI. The use of high-field MRI devices (3T, 7T) shows a fairly high frequency of detecting point DWI changes in the hippocampal projection (up to 50%), which can be used as one of the objective criteria for the diagnosis of TGA","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":" 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141680766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mark G. Kosenko, G. B. Nemkovskiy, Olesya Yu. Tsvetkova, Ivan D. Akinfeev, V. A. Dolgova
BACKGROUND: The application of videofixation technologies in embryology is developing significantly. These technologies permit the objective analysis of the process of early embryogenesis of each cultured embryo without the necessity of removing the culture cup from the incubator. Timelapse technologies in routine practice allow for the guaranteed detection of embryo developmental pathologies that are inaccessible to traditional developmental monitoring methods [1, 2]. Nevertheless, the annotation and manual evaluation of all frames captured during the cultivation process can be a time-consuming process. Furthermore, video fixation itself does not eliminate the issue of objectivizing the quality of interpretation of the obtained images [3]. Intelligent technologies, in particular, solutions developed with the use of machine learning, are successfully employed in the resolution of such problems. AIM: The aim of this study is to develop a system for the automated analysis of the morphokinetic state of the human embryo with the aim of assessing its capacity for implantation. MATERIALS AND METHODS: The data were collected at the Family Medical Center (Ufa, Russia) and the Clinical Hospital IDK of the Mother and Child Group of Companies (Samara, Russia). Digital images of the period of preimplantation development of human embryos up to the blastocyst stage (days 0–6 from insemination) were obtained using an incubator for in vitro fertilization laboratories, the EmbryoVisor, with a timelapse (hyperlapse) video fixation system. Embryos were cultured individually in special micro-well WOW dishes (Vitrolife, Sweden). The data set was labelled using Label Studio Community Edition software. A recurrent convolutional neural network was selected to analyse the data and trained using multiple images. RESULTS: The development of the automatic analysis system is based on the classification of the morphokinetic state of the embryo according to the stages of embryogenesis: fertilization, fragmentation, morula formation, and blastocyst formation. Segmentation of multiple objects, such as pronuclei and polar bodies at the fertilization stage or blastomeres at the fragmentation stage, will be performed depending on a certain stage of development. We plan to build a binary classification of the presence of additional features (multinucleation, heterogeneity of the endoplasmic network), classification/regression of additional features (so, fragmentation can be estimated as discrete ranges or absolute values). The result is a system for labeling the morphodynamic profile of an embryo using deep learning. This method automates and accelerates the analysis process, which previously required significant time and human resources. CONCLUSIONS: It is anticipated that the developed system of automatic analysis of morphokinetic state of embryos will simplify the process of evaluating the quality of human embryos in in vitro fertilization laboratories, reducing the time and
背景：视频固定技术在胚胎学中的应用正在蓬勃发展。这些技术可对每个培养胚胎的早期胚胎发育过程进行客观分析，而无需将培养杯从培养箱中取出。在常规实践中，延时技术可确保检测到传统发育监测方法无法检测到的胚胎发育病理现象 [1，2]。然而，对培养过程中捕捉到的所有帧进行注释和人工评估是一个耗时的过程。此外，视频固定本身并不能消除客观解释所获图像质量的问题 [3]。智能技术，尤其是利用机器学习技术开发的解决方案，在解决此类问题方面取得了成功。目的：本研究旨在开发一套自动分析人类胚胎形态动力学状态的系统，以评估其植入能力。材料与方法：数据在家庭医疗中心（俄罗斯乌法）和母婴集团公司临床医院 IDK（俄罗斯萨马拉）收集。人类胚胎植入前发育至囊胚期（授精后第 0-6 天）的数字图像是使用体外受精实验室培养箱 EmbryoVisor 和延时（超延时）视频固定系统获得的。胚胎在特制的微孔培养皿（Vitrolife，瑞典）中单独培养。数据集使用 Label Studio Community Edition 软件进行标记。选择了一个递归卷积神经网络来分析数据，并使用多张图像进行训练。结果：自动分析系统的开发基于胚胎形态动力学状态的分类，按照胚胎发生的各个阶段：受精、破碎、蜕膜形成和囊胚形成。多个对象（如受精阶段的前核和极体或破碎阶段的胚泡）的分割将根据特定的发育阶段进行。我们计划对是否存在其他特征（多核、内质网的异质性）进行二元分类，对其他特征进行分类/回归（因此，可按离散范围或绝对值估算破碎程度）。最终形成了一个利用深度学习标记胚胎形态动力学特征的系统。这种方法自动化并加快了分析过程，而这在以前需要大量的时间和人力资源。结论：预计所开发的胚胎形态动力学状态自动分析系统将简化体外受精实验室评估人类胚胎质量的过程，减少这一过程所花费的时间和资源。此外，它还将提高评估胚胎植入能力的准确性和可靠性，并有可能成为开发胚胎学医疗决策支持系统的基础。
{"title":"Development of a system for automatic analysis of the morphokinetic state of the human embryo","authors":"Mark G. Kosenko, G. B. Nemkovskiy, Olesya Yu. Tsvetkova, Ivan D. Akinfeev, V. A. Dolgova","doi":"10.17816/dd627040","DOIUrl":"https://doi.org/10.17816/dd627040","url":null,"abstract":"BACKGROUND: The application of videofixation technologies in embryology is developing significantly. These technologies permit the objective analysis of the process of early embryogenesis of each cultured embryo without the necessity of removing the culture cup from the incubator. Timelapse technologies in routine practice allow for the guaranteed detection of embryo developmental pathologies that are inaccessible to traditional developmental monitoring methods [1, 2]. Nevertheless, the annotation and manual evaluation of all frames captured during the cultivation process can be a time-consuming process. Furthermore, video fixation itself does not eliminate the issue of objectivizing the quality of interpretation of the obtained images [3]. Intelligent technologies, in particular, solutions developed with the use of machine learning, are successfully employed in the resolution of such problems. \u0000AIM: The aim of this study is to develop a system for the automated analysis of the morphokinetic state of the human embryo with the aim of assessing its capacity for implantation. \u0000MATERIALS AND METHODS: The data were collected at the Family Medical Center (Ufa, Russia) and the Clinical Hospital IDK of the Mother and Child Group of Companies (Samara, Russia). Digital images of the period of preimplantation development of human embryos up to the blastocyst stage (days 0–6 from insemination) were obtained using an incubator for in vitro fertilization laboratories, the EmbryoVisor, with a timelapse (hyperlapse) video fixation system. Embryos were cultured individually in special micro-well WOW dishes (Vitrolife, Sweden). The data set was labelled using Label Studio Community Edition software. A recurrent convolutional neural network was selected to analyse the data and trained using multiple images. \u0000RESULTS: The development of the automatic analysis system is based on the classification of the morphokinetic state of the embryo according to the stages of embryogenesis: fertilization, fragmentation, morula formation, and blastocyst formation. Segmentation of multiple objects, such as pronuclei and polar bodies at the fertilization stage or blastomeres at the fragmentation stage, will be performed depending on a certain stage of development. We plan to build a binary classification of the presence of additional features (multinucleation, heterogeneity of the endoplasmic network), classification/regression of additional features (so, fragmentation can be estimated as discrete ranges or absolute values). The result is a system for labeling the morphodynamic profile of an embryo using deep learning. This method automates and accelerates the analysis process, which previously required significant time and human resources. \u0000CONCLUSIONS: It is anticipated that the developed system of automatic analysis of morphokinetic state of embryos will simplify the process of evaluating the quality of human embryos in in vitro fertilization laboratories, reducing the time and ","PeriodicalId":34831,"journal":{"name":"Digital Diagnostics","volume":"88 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141683860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：