Research outputs from Pure / Zinātniskās darbības rezultāti no ZDIS Pure

Permanent URI for this collection

http://hdl.handle.net/123456789/3714

Browse

Now showing 1 - 20 of 35

3D desekcijas galda loma anatomijas mācību procesā mūsdienās
(Rīgas Pedagoģijas un izglītības vadības akadēmija, 2017) Pilmane, Māra; Kažoka, Dzintra; Institute of Anatomy and Anthropology
Studiju kursa “Anatomija” apgūšana studentiem vienmēr ir bijusi saistīta ar īpašu specifiskumu, materiāla sarežģītību un nepieciešamību izprast dažādu struktūru telpiskās un topogrāfiskās attiecības. Interaktīvo mācību formu ieviešana ir viens no nozīmīgākajiem virzieniem mūsdienu augstskolas studentu sagatavošanas pilnveidošanā un ir papildu instruments mācību procesa optimizēšanā. Darba mērķis – noskaidrot 3D virtuālā desekcijas galda “Anatomage” iespējas un priekšrocības studiju kursa “Anatomija” īstenošanā un studentu zināšanu, prasmju līmeņa paaugstināšanā. Materiāli un metodes. Darbā tika analizēta studiju kursa “Anatomija” praktisko nodarbību norise Rīgas Stradiņa universitātes Morfoloģijas katedrā, izmantojot darbā ar studentiem 3D virtuālo desekcijas galdu “Anatomage”. Rezultāti. Desekcijas galds ļauj virtuāli atveidot cilvēka ķermeni dabīgā izmērā. To uz galda ekrāna var pārvietot, pagriezt ar pirkstiem un veikt griezumus jebkurā projekcijā. Izmantojot segmentācijas funkcijas, katras sistēmas tēma un anatomiskā struktūra var tikt apgūta atsevišķi. Struktūras tiek komentētas uz ekrāna ar nosaukumiem latīņu vai angļu valodā. Programmatūras nodrošinājums ļauj lejupielādēt cilvēka ķermeņu desekcijas bildes un griezumus, ļaujot vizualizēt audu un orgānu attiecības pa slāņiem, veikt dažādas virtuālas manipulācijas, izmantot dažādus bilžu formātus, dinamiskos un CT, MRI attēlus, pielietot un analizēt iekšējās bibliotēkas patoloģiskos gadījumus. Secinājumi: Desekcijas galda piedāvātās iespējas ir būtisks papildinājums praktiskajām nodarbībām, kas palīdz dziļāk apgūt studiju kursu, attīsta studentu iztēli, radošās spējas, veido plašu mācību materiālu klāstu, paaugstinot motivāciju mācīties un attīstot katra individuālās spējas un iemaņas. Balstoties uz iegūtajām zināšanām, studenti var pieņemt pārdomātus lēmumus, mācīties patstāvīgi un nepārtraukti papildināt savas zināšanas.
3D dissection tools in Anatomage supported interactive human anatomy teaching and learning
(EDP Sciences, 2019) Pilmane, Māra; Kažoka, Dzintra; Berķis, U.; Vilka, L.; Department of Morphology
The main aim of this study is to present the usage and importance of 3D dissection tools in the teaching and learning of Anatomy and to describe and explain our experience with Anatomage Table in Human Anatomy studies at Rīga Stradiņš University. In 2017–2018 two 3D dissection tools (scalpels) were used every week in work with Anatomage Table during the practical classes. As methods for collecting data were used discussions between students and teachers. Together 200 students of the Faculty of Medicine and Dentistry were involved in this study. It was possible to create incisions and cuts in order to remove and uncover different layers of organic tissues, to move deep inside step by step and find out which structures it was necessary to look for. Afterwards students showed that they were able to place the organs back and reattach the bones, muscles, blood vessels in the body and put the skin back on. Students enjoyed virtual tools in the practical classes and learned the material better. Virtual tools helped students and tutors to easily understand and memorize different anatomy structures. 3D scalpels were useful for different education activities, but the learning experience may be suitable further for the study of real materials.
Adapting Classification Neural Network Architectures for Medical Image Segmentation Using Explainable AI
(2025-02-13) Nikulins, Arturs; Edelmers, Edgars; Sudars, Kaspars; Polaka, Inese; Faculty of Medicine
Segmentation neural networks are widely used in medical imaging to identify anomalies that may impact patient health. Despite their effectiveness, these networks face significant challenges, including the need for extensive annotated patient data, time-consuming manual segmentation processes and restricted data access due to privacy concerns. In contrast, classification neural networks, similar to segmentation neural networks, capture essential parameters for identifying objects during training. This paper leverages this characteristic, combined with explainable artificial intelligence (XAI) techniques, to address the challenges of segmentation. By adapting classification neural networks for segmentation tasks, the proposed approach reduces dependency on manual segmentation. To demonstrate this concept, the Medical Segmentation Decathlon ‘Brain Tumours’ dataset was utilised. A ResNet classification neural network was trained, and XAI tools were applied to generate segmentation-like outputs. Our findings reveal that GuidedBackprop is among the most efficient and effective methods, producing heatmaps that closely resemble segmentation masks by accurately highlighting the entirety of the target object.
Advanced Imaging in Dental Research : from Gene Mapping to AI Global Data
(2024) Graves, D T; Uribe, Sergio E.; Department of Conservative Dentistry and Oral Health
Advances in imaging technologies combined with artificial intelligence (AI) are transforming dental, oral, and craniofacial research. This editorial highlights breakthroughs ranging from gene expression mapping to visualizing the availability of global AI data, providing new insights into biological complexity and clinical applications.
AI-Assisted Detection and Localization of Spinal Metastatic Lesions
(2024-11) Edelmers, Edgars; Nikulins, Arturs; Sprudža, Klinta Luīze; Stapulone, Patrīcija; Saimons Pūce, Niks; Skrebele , Elizabete; Elīna Siņicina, Everita; Cīrule, Viktorija; Kazuša, Ance; Boločko, Katrina; Faculty of Medicine; Department of Radiology
Objectives: The integration of machine learning and radiomics in medical imaging has significantly advanced diagnostic and prognostic capabilities in healthcare. This study focuses on developing and validating an artificial intelligence (AI) model using U-Net architectures for the accurate detection and segmentation of spinal metastases from computed tomography (CT) images, addressing both osteolytic and osteoblastic lesions. Methods: Our methodology employs multiple variations of the U-Net architecture and utilizes two distinct datasets: one consisting of 115 polytrauma patients for vertebra segmentation and another comprising 38 patients with documented spinal metastases for lesion detection. Results: The model demonstrated strong performance in vertebra segmentation, achieving Dice Similarity Coefficient (DSC) values between 0.87 and 0.96. For metastasis segmentation, the model achieved a DSC of 0.71 and an F-beta score of 0.68 for lytic lesions but struggled with sclerotic lesions, obtaining a DSC of 0.61 and an F-beta score of 0.57, reflecting challenges in detecting dense, subtle bone alterations. Despite these limitations, the model successfully identified isolated metastatic lesions beyond the spine, such as in the sternum, indicating potential for broader skeletal metastasis detection. Conclusions: The study concludes that AI-based models can augment radiologists’ capabilities by providing reliable second-opinion tools, though further refinements and diverse training data are needed for optimal performance, particularly for sclerotic lesion segmentation. The annotated CT dataset produced and shared in this research serves as a valuable resource for future advancements.
Artificial intelligence chatbots and large language models in dental education : Worldwide survey of educators
(2024-11) Uribe, Sergio E; Maldupa, Ilze; Kavadella, Argyro; El Tantawi, Maha; Chaurasia, Akhilanand; Fontana, Margherita; Marino, Rodrigo; Innes, Nicola; Schwendicke, Falk; Department of Conservative Dentistry and Oral Health
INTRODUCTION: Interest is growing in the potential of artificial intelligence (AI) chatbots and large language models like OpenAI's ChatGPT and Google's Gemini, particularly in dental education. To explore dental educators' perceptions of AI chatbots and large language models, specifically their potential benefits and challenges for dental education. MATERIALS AND METHODS: A global cross-sectional survey was conducted in May-June 2023 using a 31-item online-questionnaire to assess dental educators' perceptions of AI chatbots like ChatGPT and their influence on dental education. Dental educators, representing diverse backgrounds, were asked about their use of AI, its perceived impact, barriers to using chatbots, and the future role of AI in this field. RESULTS: 428 dental educators (survey views = 1516; response rate = 28%) with a median [25/75th percentiles] age of 45 [37, 56] and 16 [8, 25] years of experience participated, with the majority from the Americas (54%), followed by Europe (26%) and Asia (10%). Thirty-one percent of respondents already use AI tools, with 64% recognising their potential in dental education. Perception of AI's potential impact on dental education varied by region, with Africa (4[4-5]), Asia (4[4-5]), and the Americas (4[3-5]) perceiving more potential than Europe (3[3-4]). Educators stated that AI chatbots could enhance knowledge acquisition (74.3%), research (68.5%), and clinical decision-making (63.6%) but expressed concern about AI's potential to reduce human interaction (53.9%). Dental educators' chief concerns centred around the absence of clear guidelines and training for using AI chatbots. CONCLUSION: A positive yet cautious view towards AI chatbot integration in dental curricula is prevalent, underscoring the need for clear implementation guidelines.
Automatization of CT Annotation : Combining AI Efficiency with Expert Precision
(2024-01-15) Edelmers, Edgars; Kazoka, Dzintra; Bolocko, Katrina; Sudars, Kaspars; Pilmane, Mara; Institute of Anatomy and Anthropology
The integration of artificial intelligence (AI), particularly through machine learning (ML) and deep learning (DL) algorithms, marks a transformative progression in medical imaging diagnostics. This technical note elucidates a novel methodology for semantic segmentation of the vertebral column in CT scans, exemplified by a dataset of 250 patients from Riga East Clinical University Hospital. Our approach centers on the accurate identification and labeling of individual vertebrae, ranging from C1 to the sacrum–coccyx complex. Patient selection was meticulously conducted, ensuring demographic balance in age and sex, and excluding scans with significant vertebral abnormalities to reduce confounding variables. This strategic selection bolstered the representativeness of our sample, thereby enhancing the external validity of our findings. Our workflow streamlined the segmentation process by eliminating the need for volume stitching, aligning seamlessly with the methodology we present. By leveraging AI, we have introduced a semi-automated annotation system that enables initial data labeling even by individuals without medical expertise. This phase is complemented by thorough manual validation against established anatomical standards, significantly reducing the time traditionally required for segmentation. This dual approach not only conserves resources but also expedites project timelines. While this method significantly advances radiological data annotation, it is not devoid of challenges, such as the necessity for manual validation by anatomically skilled personnel and reliance on specialized GPU hardware. Nonetheless, our methodology represents a substantial leap forward in medical data semantic segmentation, highlighting the potential of AI-driven approaches to revolutionize clinical and research practices in radiology.
A brain-constrained deep neural-network model that can account for the readiness potential in self-initiated volitional action
(2024) Ušacka, Agnese; Schurger, Aaron; Garagnani, Max; Komunikācijas fakultāte
The readiness potential (RP) is a gradual buildup of negative electrical potential over the motor cortices prior to onset of a self-initiated movement. It is typically interpreted as having a goal-directed nature, whereby it signals movement planning and preparation. However, a similar buildup can also be observed by averaging continuous random neural fluctuations aligned to crests in their time series [1]. Therefore, an alternative account of the RP is that it reflects ongoing background neuronal noise that has at least a small influence on the precise time of movement onset [2]. While computational modelling studies were used in the past to adjudicate between these accounts, previous attempts did not employ a fully neuroanatomically and neurobiologically realistic architecture, hence falling short of providing a cortical-level mechanistic validation of either theory. Here, we investigated the stochastic origin of the RP by applying a fully brain-constrained deep neural-network model reproducing real cortical neurons dynamics and the structure and connectivity of relevant primary sensorimotor, secondary and association areas of the frontal and temporal lobes. This model has been previously used to account for the neuromechanistic origins and cortical topography of volitional decisions to speak and act [3]. We used the emergent feature of this neural architecture – its ability to exhibit noise-driven periodic spontaneous ignitions of previously learnt internal representations (cell assemblies, CAs, circuits of strongly and reciprocally connected cells distributed across the entire network) – to mimic spontaneous decisions to act as observed in the classical Libet experiment. Specifically, we recorded the network’s activity for 2,000 trials, each trial beginning with a network reset and lasting until the spontaneous ignition of one of the CAs occurred, and used the time interval between trial start and spontaneous CA ignition as a model correlate of waiting times. We found that the model data accounted well for the experimental waiting-time distribution. Furthermore, in line with the stochastic interpretation of the RP, appropriate calibration of the model parameters resulted in subthreshold reverberation of activity within CA circuits, and averaging across cell assemblies’ ignition episodes produced a curve that closely matched the gradual buildup of activity observed in the experimental RP and its onset time. There are various neurophysiological sources of ongoing noise that result from neural activity. Some of this noise might accumulate and reverberate within previously acquired perception-action circuits, and, hence, produce spontaneous action. The present simulation results, obtained with a fully brain-constrained neural architecture, provide further support for this alternative view, placing the classical explanation of the RP further under scrutiny.
Combination of new, innovative and demonstrative 3D elements with classical learning methods in Human Anatomy course
(2019) Kažoka, Dzintra; Pilmane, Māra; Department of Morphology; Institute of Anatomy and Anthropology
The aim of this work was to study, compare and summarize our experience in combination of innovative and demonstrative 3D elements with classical learning methods in Human Anatomy course. In practical classes 100 students of the 1st study year of the Faculty of Medicine used the virtual dissection Anatomage Table and/or their own prepared anatomical models by 3D printer. 100 students of the 2nd study year used the classical human cadaveric dissections. All participants were asked to discuss about these used teaching methods and complete an anonymous feedback questionnaire. 70% of students were satisfied with the virtual dissection and/or their own prepared anatomical 3D models in group 1, but they liked to highlight the role and necessity of real dissection. Some students were satisfied with the classical learning and teaching of human anatomy when associated it with the use of different 3D elements. 90% of students considered that virtual elements and models were useful in learning the study course outside the practical classes. In group 2 more than 95% of participants indicated that dissections should be regular. There classical learning of anatomical structures obtained better results than only in the innovations supported group. In human anatomy 3D elements together with classical learning methods can motivate students to study the morphological disciplines, increase their interest and the effectiveness of studies.
A comparative analysis of the social performance of global and local berry supply chains
(2016-06-07) Grivins, Mikelis; Tisenkopfs, Talis; Stojanovic, Zaklina; Ristic, Bojan
The goal of this paper is twofold: to comparatively analyze the social performance of global and local berry supply chains and to explore the ways in which the social dimension is embedded in the overall performance of food supply chains. To achieve this goal, the social performance of five global and local food supply chains in two countries are analyzed: wild blueberry supply chains in Latvia and cultivated raspberry supply chains in Serbia. The study addresses two research questions: (1) What is the social performance of the local and global supply chains? (2) How can references to context help improve understanding of the social dimension and social performance of food supply chains? To answer these questions, two interlinked thematic sets of indicators (attributes) are used-one describing labor relations and the other describing power relations. These lists are then contextualized by examining the micro-stories of the actors involved in these supply chains. An analysis of the chosen attributes reveals that global chains perform better than local chains. However, a context-sensitive analysis from the perspective of embedded markets and communities suggests that the social performance of food chains is highly context-dependent, relational, and affected by actors' abilities to negotiate values, norms, and the rules embedded within these chains, both global and local. The results illustrate that the empowerment of the chains' weakest actors can lead to a redefining of the meanings that performance assessments rely on.
Computer Analysis of Knee by Magnetic Resonance Imaging Data
(2016-12-01) Suponenkovs, Artjoms; Markovics, Zigurds; Platkajis, Ardis; Rīga Stradiņš University
The examination of knee cartilage degradation by magnetic resonance imaging (MRI) data is essential due to the reduction in physical activity of the population and a rising number of patients with osteoarthritis(OA). The main aim of this publication is to show a new approach for analyzing knee tissue by MRI data. The present paper investigates the problems of relaxation times calculation, medical image segmentation and statistical texture features calculation. Proposed paper describes an approach for medical image segmentation, relaxation times calculation and statistical texture features calculation. An important aspect of analysis of articular cartilage relaxation times changing is illustrated in the experimental part. The experimental part of the publication also describes the dependence between organic structure and relaxation times. The proposed approach the obtained results can be useful for early OA diagnostics.
Corpus Based Self-Assessment Platform for Latvian Language Learners
(2022) Darģis, Roberts; Auziņa, Ilze; Kaija, Inga; Levāne-Petrova, Kristīne; Pokratniece, Kristīne; Rīga Stradiņš University
This paper presents a self-assessment platform for Latvian language learners in the breakthrough (A1) and Waystage (A2) levels. The self-assessment platform contains three types of exercises (typing, inflection and gap filling) based on error analysis of the Latvian Language Learner corpus (LaVA). All exercises are automatically generated based on data from multiple corpora. The automatically generated exercises are useful not only for learners outside of classroom or even outside of any formal education setting, but also for educators and authors of learning aids. Currently the self-assessment platform is tailored for language learners at the beginner level, but it can be easily extended for more advanced levels. The self-assessment platform is freely available online (http://uzdevumi.riks.korpuss.lv/en/) and the interface is translated in two language – Latvian and English.
Current options and limits of digital technologies and artificial intelligence in social work
(EDP Sciences, 2024) Markovič, Daniel; Vilka, Lolita; Krūmiņa, Justīne
At the end of the second decade of the 21st century, it was accepted that robots and technology would replace mainly blue-collar and routine jobs, while professionals in human well-being and creativity would be needed in greater numbers. New tools like AI large language models, which are at the beginning of an exponential trajectory of their development, have changed the way digitization is viewed; people employed in activities such as writing as well as administrative and clerical work have started to lose their jobs. Will technologies become aids and supplements to services, or can they replace social workers? The paper aims to analyse the current limits of artificial intelligence in social work and summarize digital platforms useful for social work practice. The methods used are the analysis of literature and statistics and an experiment with artificial intelligence. Language model Chat GPT passed the state final examination for the bachelor’s degree in social work in Slovakia. It received a grade of B on the ECTS grading scale.
Databases for biomass and waste biorefinery - a mini-review and SWOT analysis
(2023-11-29) Mukamwi, Morgen; Somorin, Tosin; Soloha, Raimonda; Dace, Elina; Politikas zinātnes katedra
The world is facing problems of the increasing amount of resources wasted as the world population grows. Biowaste streams form a significant part of the overall waste generation, and a circular economy utilizing this biowaste will significantly reduce waste whilst lowering the anthropogenic carbon footprint. Due to their energy content and high concentration of hydrocarbon molecules, bio-based waste streams have the potential to be transformed into valorized products (energy, fuels, and chemicals) using biorefinery technologies. In this work, a mini-review has been conducted on available, mostly European databases on existing biomass types and biorefinery technologies to provide a framework for a desirable, comprehensive database connecting bio-based waste streams, biorefinery technologies and bioproducts, as well as the geographical distribution of feedstocks and biorefineries. The database assessment utilized the SWOT (strengths, weakness, opportunities, threats) methodology to support benchmark analysis and to identify critical gaps in underlying data structures that could be included in a single database. The results show that current databases are useful but insufficient for waste biorefineries due to limited quality and quantity as well as the usability of data. A comprehensive database or improved database cluster would be necessary, not only for technology development but for better investment and policy decisions. The development of the new database architecture would need to incorporate the aspects: expansion of database scope and content depth, improved usability, accessibility, applicability, update frequency, openness to new contributions, process descriptions and parameters, and technology readiness level.
Digital social work or e-social work? : Towards social work in a digital environment
(EDP Sciences, 2024) Markovič, Daniel; Vilka, Lolita; Krūmiņa, Justīne
The goal of this paper is to summarise and remark on contemporary issues of emerging social work in the digital environment, which were accelerated by social distancing during the COVID-19 pandemic. We discuss the concepts of e-social work and digital social work. We debate where the boundaries of social work in the digital environment are and whether it constitutes a new, distinct branch of social work. We investigate the process and barriers to enhancing social workers’ digital capabilities (using the Technology Acceptance Model, SAMR theory, and Digital Natives-Digital Immigrants contexts). We analyse the key advantages and disadvantages of social work in the online setting.
Discourse on safety/security in the parliamentary corpus of latvian saeima
(2020) Skulte, Ilva; Kozlovs, Normunds; Komunikācijas fakultāte
The discourse on (individual and public) safety and (social) security in the political communication has an impact on community feelings through the ideas of risk and emergency. Indeed, the many aspects of insecurity / un-safety make this to be elaborated in speeches as a rather manifold and complex concept. How is this conceptual nexus used and perceived in the speeches of MP's of Latvian parliament, and what impact it may have had on political discourse in general and construction of identities and power relations between political elites and the people in this discourse? These are the main issues addressed in this research that combines critical discourse analysis and corpus analysis tool created for Corpus of Debates in Latvian parliament - Saeima (1993 - 2017) (http://saeima.korpuss.lv/)). Findings show that the discourse on safety and security is provided by Latvian MP's mainly from protectionist point of view. The main stream of discourse indicate the uses of the meaning of 'security' or “the state of being free from danger or threat”; this is why it is sometimes referred to as taken for granted or the term is often used in Saeima debates in both administrative and populist contexts.
The Face of Early Cognitive Decline? Shape and Asymmetry Predict Choice Reaction Time Independent of Age, Diet or Exercise
(2019) Brown, William; Ušacka, Agnese
Slower reaction time is a measure of cognitive decline and can occur as early as 24 years of age. We are interested if developmental stability predicts cognitive performance independent of age and lifestyle (e.g., diet and exercise). Developmental stability is the latent capacity to buffer ontogenetic stressors and is measured by low fluctuating asymmetry (FA). FA is random—with respect to the largest side—departures from perfect morphological symmetry. The degree of asymmetry has been associated with physical fitness, morbidity, and mortality in many species, including humans. We expected that low FA (independent of age, diet and exercise) will predict faster choice reaction time (i.e., correct keyboard responses to stimuli appearing in a random location on a computer monitor). Eighty-eight university students self-reported their fish product consumption, exercise, had their faces 3D scanned and cognitive performance measured. Unexpectedly, increased fish product consumption was associated with worsened choice reaction time. Facial asymmetry and multiple face shape variation parameters predicted slower choice reaction time independent of sex, age, diet or exercise. Future work should develop longitudinal interventions to minimize early cognitive decline among vulnerable people (e.g., those who have experienced ontogenetic stressors affecting optimal neurocognitive development).
A framework for validating AI in precision medicine : considerations from the European ITFoC consortium
(2021-10-02) Tsopra, Rosy; Fernandez, Xose; Luchinat, Claudio; Alberghina, Lilia; Lehrach, Hans; Vanoni, Marco; Dreher, Felix; Sezerman, O Ugur Sezerman; Cuggia, Marc; de Tayrac, Marie; Miklaševičs, Edvīns; Itu, Lucian Mihai; Geanta , Marius; Ogilvie, Lesley; Godey, Florence; Boldisor, Cristian Nicolae; Campillo-Gimenez , Boris; Cioroboiu, Cosmina; Ciusdel, Costin Florian; Coman , Simona; Cubelos, Oliver Hijano; Itu, Alina; Lange, Bodo; Le Gallo, Matthieu; Lespagnol, Alexandra; Mauri , Giancarlo; Soykam, H Okan; Rance , Bastien; Turano, Paola; Tenori, Leonardo; Vignoli, Alessia; Wierling , Christoph; Benhabiles, Nora; Burgun, Anita; Onkoloģijas institūts
Background Artificial intelligence (AI) has the potential to transform our healthcare systems significantly. New AI technologies based on machine learning approaches should play a key role in clinical decision-making in the future. However, their implementation in health care settings remains limited, mostly due to a lack of robust validation procedures. There is a need to develop reliable assessment frameworks for the clinical validation of AI. We present here an approach for assessing AI for predicting treatment response in triple-negative breast cancer (TNBC), using real-world data and molecular -omics data from clinical data warehouses and biobanks. Methods The European “ITFoC (Information Technology for the Future Of Cancer)” consortium designed a framework for the clinical validation of AI technologies for predicting treatment response in oncology. Results This framework is based on seven key steps specifying: (1) the intended use of AI, (2) the target population, (3) the timing of AI evaluation, (4) the datasets used for evaluation, (5) the procedures used for ensuring data safety (including data quality, privacy and security), (6) the metrics used for measuring performance, and (7) the procedures used to ensure that the AI is explainable. This framework forms the basis of a validation platform that we are building for the “ITFoC Challenge”. This community-wide competition will make it possible to assess and compare AI algorithms for predicting the response to TNBC treatments with external real-world datasets. Conclusions The predictive performance and safety of AI technologies must be assessed in a robust, unbiased and transparent manner before their implementation in healthcare settings. We believe that the consideration of the ITFoC consortium will contribute to the safe transfer and implementation of AI in clinical settings, in the context of precision oncology and personalized care.
Hand-Washing Video Dataset Annotated According to the World Health Organization’s Hand-Washing Guidelines
(2021-04-07) Lulla, Martins; Rutkovskis, Aleksejs; Slavinska, Andreta; Vilde, Aija; Gromova, Anastasija; Ivanovs, Maksims; Skadins, Ansis; Kadikis, Roberts; Elsts, Atis; Medical Education Technology Centre
Washing hands is one of the most important ways to prevent infectious diseases, including COVID-19. The World Health Organization (WHO) has published hand-washing guidelines. This paper presents a large real-world dataset with videos recording medical staff washing their hands as part of their normal job duties in the Pauls Stradins Clinical University Hospital. There are 3185 hand-washing episodes in total, each of which is annotated by up to seven different persons. The annotations classify the washing movements according to the WHO guidelines by marking each frame in each video with a certain movement code. The intention of this “in-the-wild” dataset is two-fold: to serve as a basis for training machine-learning classifiers for automated hand-washing movement recognition and quality control, and to allow to investigation of the real-world quality of washing performed by working medical staff. We demonstrate how the data can be used to train a machine-learning classifier that achieves classification accuracy of 0.7511 on a test dataset.
Human–robot collaboration trends and safety aspects : A systematic review
(2021-09) Arents, Janis; Abolins, Valters; Judvaitis, Janis; Vismanis, Oskars; Oraby, Aly; Ozols, Kaspars
Smart manufacturing and smart factories depend on automation and robotics, whereas human–robot collaboration (HRC) contributes to increasing the effectiveness and productivity of today’s and future factories. Industrial robots especially in HRC settings can be hazardous if safety is not addressed properly. In this review, we look at the collaboration levels of HRC and what safety actions have been used to address safety. One hundred and ninety-three articles were identified from which, after screening and eligibility stages, 46 articles were used for the extraction stage. Predefined parameters such as: devices, algorithms, collaboration level, safety action, and standards used for HRC were extracted. Despite close human and robot collaboration, 25% of all reviewed studies did not use any safety actions, and more than 50% did not use any standard to address safety issues. This review shows HRC trends and what kind of functionalities are lacking in today’s HRC systems. HRC systems can be a tremendously complex process; therefore, proper safety mechanisms must be addressed at an early stage of development.

Browse

Browsing Research outputs from Pure / Zinātniskās darbības rezultāti no ZDIS Pure by Subject "1.2 Computer and information sciences"

Results Per Page

Sort Options