Personalized approach to developing image processing and analysis methods for medical video systems.

Video monitoring is often conducted in hospitals. In case of prolonged monitoring, huge amounts of data are generated. There is a high demand for very efficient video compression methods. The current medical video systems utilize standard compression algorithms such as MPEG-1 and MPEG-2, which were designed for generic video rather than medical video. The features of this type of video such as long idle periods and small local motions, are not sufficiently addressed in these standards. As a result, current systems produce considerable redundancy in the output data. In this paper, we present a two-step method to compress medical monitoring video more efficiently. In the first step, a novel algorithm is utilized to detect the motion activities of the input video sequence. Then, the video sequence is segmented into several rectangle image regions (video object planes), which contain motion activities restricted within these windows. In the second step, the generated video object planes are compressed by an MPEG-4 module (or any module that features high compression efficiency). Our experimental results show that the two-step method improves the compression ratio significantly when compared with the existing generic MPEG algorithms while still retaining the essential video quality.

Since the turn of the millennium researchers have access to an ever-increasing pool of novel types of video recordings. People use camcorders, mobile phone cameras, and even drones to film and photograph social life, and many public spaces are under video surveillance. More and more sociologists, psychologists, education researchers, and criminologists rely on such visuals to observe and analyze social life as it happens. Based on qualitative or quantitative techniques, scholars trace situations or events step-by-step to explain a social process or outcome. Recently, a methodological framework has been formulated under the label Video Data Analysis (VDA) to provide a reference point for scholars across disciplines. Our paper aims to further contribute to this effort by detailing important issues and potential challenges along the VDA research process. The paper briefly introduces VDA and the value of 21st century visuals for understanding social phenomena. It then reflects on important issues and potential challenges in five steps of conducting VDA, and formulate guidelines on how to conduct a VDA: From setting up the research, to choosing data sources, assessing their validity, to analyzing the data and presenting the findings. These reflections aim to further methodological foundations for studying situational dynamics with 21st century video data.

EACMFS Prizes and Awards

Melanoma is recognized as one of the most dangerous type of skin cancer. A novel method to detect melanoma in real time with the help of Graphical Processing Unit (GPU) is proposed. Existing systems can process medical images and perform a diagnosis based on Image Processing technique and Artificial Intelligence. They are also able to perform video processing with the help of large hardware resources at the backend. This incurs significantly higher costs and space and are complex by both software and hardware. Graphical Processing Units have high processing capabilities compared to a Central Processing Unit of a system. Various approaches were used for implementing real time detection of Melanoma. The results and analysis based on various approaches and the best approach based on our study is discussed in this work. A performance analysis for the approaches on the basis of CPU and GPU environment is also discussed. The proposed system will perform real-time analysis of live medical video data and performs diagnosis. The system when implemented yielded an accuracy of 90.133% which is comparable to existing systems.

Image binarization is one of the fundamental methods in image processing and it is mainly used as a preprocessing for other methods in image processing. We present an image binarization method with the primary purpose to find markers such as those used in mobile 3D scanning systems. Handling a mobile 3D scanning system often includes bad conditions such as light reflection and non-uniform illumination. As the basic part of the scanning process, the proposed binarization method successfully overcomes the above problems and does it successfully. Due to the trend of increasing image size and real-time image processing we were able to achieve the required small algorithmic complexity. The paper outlines a comparison with several other methods with a focus on objects with markers including the calibration system plane of the 3D scanning system. Although it is obvious that no binarization algorithm is best for all types of images, we also give the results of the proposed method applied to historical documents.

Image and video data analysis has become an increasingly important research area with applications in different domains such as security surveillance, healthcare, augmented and virtual reality, video and image editing, activity analysis and recognition, synthetic content generation, distance education, telepresence, remote sensing, sports analytics, art, non-photorealistic rendering, search engines, and social media. Recent advances in Artificial Intelligence (AI) and particularly deep learning have sparked new research challenges and led to significant advancements, especially in image and video analysis. These advancements have also resulted in significant research and development in other areas such as visualization and visual analytics, and have created new opportunities for future lines of research. In this survey article, we present the current state of the art at the intersection of visualization and visual analytics, and image and video data analysis. We categorize the visualization articles included in our survey based on different taxonomies used in visualization and visual analytics research. We review these articles in terms of task requirements, tools, datasets, and application areas. We also discuss insights based on our survey results, trends and patterns, the current focus of visualization research, and opportunities for future research.

The principal goal of visualization is to create a visual representation of complex information and large datasets in order to gain insight and understanding. Our current research focuses on methods for handling uncertainty stemming from data acquisition and algorithmic sources. Most visualization methods, especially those applied to 3D data, implicitly use some form of classification or segmentation to eliminate unimportant regions and illuminate those of interest. The process of classification is inherently uncertain; in many cases the source data contains error and noise, data transformations such as filtering can further introduce and magnify the uncertainty. More advanced classification methods rely on some sort of model or statistical method to determine what is and is not a feature of interest. While these classification methods can model uncertainty or fuzzy probabilistic memberships, they typically only provide discrete, maximum a-posteriori memberships. It is vital that visualization methods provide the user access to uncertainly in classification or image generation if the results of the visualization are to be trusted.

Urgency of the research. Traffic jams are a major problem for all road users and increasing traffic intensity is the main reason for that along with unsatisfying quality of traffic control system. Systems that control transportation flow and make decisions about changing control parameters should receive reliable and actual traffic intensity data. Due to that fact, one of the most important tasks is collection and processing traffic data.Target setting. Averaged over the day (or even the year) value of the traffic intensity can provide high-quality estimates of the control parameters for averaged values, however not for actual values, especially when large fluctuations in traffic intensity during the day are occur. For effective traffic management, it is important to have sufficiently accurate information about the state of the road (its intensity and congestion) at the time of the decision. In this scientific research, the task is to develop a technology for the traffic intensity evaluation on the basis of successive values of the congestion ratio resulting from image processing of a video image of a traffic lane. Actual scientific researches and issues analysis. Scientific publications were reviewed, which highlight the existing methods for traffic intensity evaluation, and it was concluded that the existing methods are not accurate enough to use it in modern conditions and therefore significantly limit the development of traffic management information systems.Uninvestigated parts of general matters defining. Video data analysis has not been used previously for the automated evaluation of traffic intensity.The research objective. The purpose of this study is to increase the accuracy of determining traffic intensity on the basis of real-time analysis of video stream data by automatically processing video data obtained from a video surveillance camera of a traffic lane.The statement of basic material. The method for determining the TLCR congestion index from the data, obtained as a result of processing a frame of a video sequence using the U-Net neural network, is presented. The sequence of time-ordered values of the congestion indicator turns into a sequence of traffic intensity indicators on the basis of the formula obtained as a result of the research. Experimental research that proves the high accuracy of traffic indicators evaluation is represented. The sequence of data processing and transformations constitutes a new technology determining traffic intensity.Conclusions. In this research, the technology of traffic intensity evaluation according to the video data getting from a surveillance camera, which provides a much higher accuracy in evaluating the traffic intensity in a road area than existing ones, is developed.

While previous research on audiovisual data segmentation and indexing primarily focuses on the pictorial part, significant clues contained in the accompanying audio flow are often ignored. A fully functional system for video content parsing can be achieved more successfully through a proper combination of audio and visual information. By investigating the data structure of different video types, we present tools for both audio and visual content analysis and a scheme for video segmentation and annotation in this research. In the proposed system, video data are segmented into audio scenes and visual shots by detecting abrupt changes in audio and visual features, respectively. Then, the audio scene is categorized and indexed as one of the basic audio types while a visual shot is presented by keyframes and associate image features. An index table is then generated automatically for each video clip based on the integration of outputs from audio and visual analysis. It is shown that the proposed system provides satisfying video indexing results.

This paper focuses on the analysis and monitoring application of medical data for chronic diseases in elderly individuals living alone using wearable medical sensor wristbands. It introduces the background, objectives, significance, content, and methods of the research. The development and application of wearable medical sensor wristbands and the status of chronic diseases in elderly living alone are discussed, highlighting existing research gaps. The section on the characteristics and needs analysis of chronic diseases in elderly living alone defines the term, analyzes common types and characteristics of chronic diseases, and examines the medical needs of such patients. The principles and technologies of wearable medical sensor wristbands are explained, covering working principles, common sensor technologies, and data collection and transmission technologies. The section on the collection and processing of medical data for chronic diseases in elderly living alone discusses data collection methods and steps, data processing and analysis methods, and data security and privacy protection. The design of a chronic disease medical monitoring system for elderly living alone based on wearable medical sensor wristbands is detailed, including system architecture and functional design, data visualization and report generation, and real-time monitoring and warning mechanisms. The experimental and results analysis section describes the experimental design and data collection methods, followed by an analysis and discussion of the results. In the summary and outlook section, the research work is summarized, existing problems and potential improvements are pointed out, and future developments are anticipated. This research provides new insights into the analysis and monitoring application of medical data for chronic diseases in elderly living alone using wearable medical sensor wristbands, offering a new approach to promoting health management and disease prevention for the elderly living alone.

Generative AI models have emerged as transformative tools in the healthcare domain, offering significant advances in disease detection, diagnosis, prognosis, and treatment planning. Although substantial progress has been made in the generation of 2D medical images, the synthesis of complex medical videos remains an unexplored area. The available literature on the generation of synthetic medical videos is minimal, highlighting a significant gap in this emerging area of research. This paper reviews the literature related to biomedical video synthesis using diffusion models and generative adversarial networks. The review aims to consolidate all relevant literature and highlight the different publicly available datasets, performance matrices, and the challenges associated with the generation of medical videos, along with some potential mitigation strategies. The findings of this review reveal that key challenges, such as maintaining temporal consistency, addressing computational inefficiencies, and overcoming data scarcity, are interconnected issues. Addressing these issues collectively is essential for the development of accurate and robust generative models tailored for medical video synthesis. The proposed potential mitigation strategies for the limitations of generative models in this review serve as a foundational resource for future research, aiming to enhance the reliability and applicability of generative AI models in clinical settings. These advances have the potential to significantly impact the domains of connected healthcare and personalized medicine by enabling the generation of realistic, high-quality medical video data that can enhance the training of diagnostic algorithms, improve the robustness of AI-assisted video interpretation, simulate disease progression or regression for more precise treatment planning, and support the development of personalized medicine techniques through enriched longitudinal data analysis.

PurposeThe purpose of this paper is to present the results of a comparison study of using a mobile medical information system between civilian medical students and physicians undergoing military service in Finland. Special emphasis is on differences in system usage, and perceptions towards the mobile medical system. Other points of interest are the important features of the mobile medical system, advantages and disadvantages of using the system in actual emergency situations and use of the device to search for general information.Design/methodology/approachThe study is conducted between two groups of users, medical students and physicians undertaking military service.FindingsThe two groups are found to have similar behaviors toward the mobile system in different contexts. This study helps develop an understanding of how the two groups of users use a mobile medical information system while also providing insights of some behavioral differences between them. Not all of the differences are significant; indicating the possibility of developing a universal tool for both military and civilian contexts, but more contents of military medicine should be supplemented for military physicians.Originality/valueThis paper addresses an area of increasing research interest, i.e. mobile medical informatics.

The National Weather Service in San Juan receives wave model output for the Puerto Rican regional coastal waters generated by NCEP's WaveWatch III model. These predictions are often unreliable mainly due to the fact that in-situ observations are not available for the coastal regions of Puerto Rico. These observations are required for calibration and validation of the wave model predictions. It is proposed to use video cameras to collect images of the nearshore zone of the ocean and to develop an algorithm for processing the video data. The data will be recorded in daylight by video cameras pointed at areas in the nearshore zone where the waves have not yet been affected by the reefs. After the video data have been received, a routine processes them in real time. To implement this, an observation system is required. Our design includes the following components: a Sanyo 1/2 inch CCD VGA (640/spl times/480) camera, an AXIS Camera Server, and a PC. The algorithm is based on several image processing methods and techniques, which allow for classification of objects with different grayscale intensity levels. The algorithm produces an output that includes estimates of wave parameters, such as period and direction in physical units.

Medical imaging using different modalities has many problems. The main ones are low informativeness, various distortion noises, and a large amount of information. Fusion, denoising, and visual data compression are used to solve them in practice. Discrete wavelet transform is one way to implement various fusion, denoising, and compression methods for 2D and 3D medical image processing. Medical imaging systems produce increasingly accurate images with scanning technology and digital devices development. These images have improved quality using both higher spatial resolutions and color bit-depth. Processing a large volume of medical imaging data requires considerable resources and processing time. Modern wavelet-based devices for medical image processing do not meet the current performance demand. Hardware accelerators are being designed to solve this problem. This paper proposes new (field-programmable gate array) FPGA accelerators using wavelet processing (WP) with scaled filter coefficients (SFC) and parallel computing in residue number system (RNS) to improve the performance of high-quality 3D medical image WP systems. The computational complexity is reduced using the developed WP method with SFC and the proposed wavelet filter coefficients scaling algorithm. Parallel computing is organized in RNS using moduli sets of a particular type. Hardware implementation of 3D medical image WP using the proposed FPGA accelerators increases device performance by 2.89-3.59 times, increasing the hardware resources by 1.18-3.29 times compared to state-of-the-art solutions. The device performance improvement is achieved while maintaining high-quality 3D medical image processing in peak signal-to-noise ratio terms.

Computed tomography is now widely used in cardiac surgery as a method of non-destructive study of internal structure of objects, including specific tasks, such as mathematical modeling of physiological processes, surgical interventions in augmented reality, 3D printing, and radiomics. One of the key steps in creating a 3D model from computed tomography data is segmentation the process of selecting objects in the image. Currently, there are several approaches to automating the segmentation process, including image processing methods, texture analysis and machine learning algorithms (in particular, clustering). Image processing methods are the simplest of the presented approaches and are found in various applications for segmentation of tomographic data. This paper reviews the advantages and disadvantages of various image processing methods (threshold, region growing, contour detection, and morphological watersheds) as tools for automated cardiac segmentation from computed tomography data. It was revealed that computed tomography images have characteristic features affecting the segmentation process (presence of noise, partial volume effect, etc.). The choice of the segmentation method is based on the brightness characteristics of the area of interest and also requires knowledge of the subject area, so it should be performed by a specialist with competence in anatomy and digital image processing. As independent methods of automated segmentation, the listed methods are applicable only in relatively simple cases (selection of homogeneous or high-contrast areas), otherwise, a combination of these methods, the use of machine learning algorithms or manual correction of the results is required.