Documenting the de-identification process of clinical and imaging data for AI for health imaging projects.

Artificial intelligence (AI) is revolutionizing the field of medical imaging, holding the potential to shift medicine from a reactive "sick-care" approach to a proactive focus on healthcare and prevention. The successful development of AI in this domain relies on access to large, comprehensive, and standardized real-world datasets that accurately represent diverse populations and diseases. However, images and data are sensitive, and as such, before using them in any way the data needs to be modified to protect the privacy of the patients. This paper explores the approaches in the domain of five EU projects working on the creation of ethically compliant and GDPR-regulated European medical imaging platforms, focused on cancer-related data. It presents the individual approaches to the de-identification of imaging data, and describes the problems and the solutions adopted in each case. Further, lessons learned are provided, enabling future projects to optimally handle the problem of data de-identification. CRITICAL RELEVANCE STATEMENT: This paper presents key approaches from five flagship EU projects for the de-identification of imaging and clinical data offering valuable insights and guidelines in the domain. KEY POINTS: ΑΙ models for health imaging require access to large amounts of data. Access to large imaging datasets requires an appropriate de-identification process. This paper provides de-identification guidelines from the AI for health imaging (AI4HI) projects.

Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects.

Artificial intelligence (AI) is transforming the field of medical imaging and has the potential to bring medicine from the era of 'sick-care' to the era of healthcare and prevention. The development of AI requires access to large, complete, and harmonized real-world datasets, representative of the population, and disease diversity. However, to date, efforts are fragmented, based on single-institution, size-limited, and annotation-limited datasets. Available public datasets (e.g., The Cancer Imaging Archive, TCIA, USA) are limited in scope, making model generalizability really difficult. In this direction, five European Union projects are currently working on the development of big data infrastructures that will enable European, ethically and General Data Protection Regulation-compliant, quality-controlled, cancer-related, medical imaging platforms, in which both large-scale data and AI algorithms will coexist. The vision is to create sustainable AI cloud-based platforms for the development, implementation, verification, and validation of trustable, usable, and reliable AI models for addressing specific unmet needs regarding cancer care provision. In this paper, we present an overview of the development efforts highlighting challenges and approaches selected providing valuable feedback to future attempts in the area.Key points• Artificial intelligence models for health imaging require access to large amounts of harmonized imaging data and metadata.• Main infrastructures adopted either collect centrally anonymized data or enable access to pseudonymized distributed data.• Developing a common data model for storing all relevant information is a challenge.• Trust of data providers in data sharing initiatives is essential.• An online European Union meta-tool-repository is a necessity minimizing effort duplication for the various projects in the area.

Real-Time Abnormal Event Detection for Enhanced Security in Autonomous Shuttles Mobility Infrastructures.

Autonomous vehicles (AVs) are already operating on the streets of many countries around the globe. Contemporary concerns about AVs do not relate to the implementation of fundamental technologies, as they are already in use, but are rather increasingly centered on the way that such technologies will affect emerging transportation systems, our social environment, and the people living inside it. Many concerns also focus on whether such systems should be fully automated or still be partially controlled by humans. This work aims to address the new reality that is formed in autonomous shuttles mobility infrastructures as a result of the absence of the bus driver and the increased threat from terrorism in European cities. Typically, drivers are trained to handle incidents of passengers' abnormal behavior, incidents of petty crimes, and other abnormal events, according to standard procedures adopted by the transport operator. Surveillance using camera sensors as well as smart software in the bus will maximize the feeling and the actual level of security. In this paper, an online, end-to-end solution is introduced based on deep learning techniques for the timely, accurate, robust, and automatic detection of various petty crime types. The proposed system can identify abnormal passenger behavior such as vandalism and accidents but can also enhance passenger security via petty crimes detection such as aggression, bag-snatching, and vandalism. The solution achieves excellent results across different use cases and environmental conditions.

Effectiveness of myAirCoach: A mHealth Self-Management System in Asthma.

BACKGROUND: Self-management programs have beneficial effects on asthma control, but their implementation in clinical practice is poor. Mobile health (mHealth) could play an important role in enhancing self-management. OBJECTIVE: To assess the clinical effectiveness and technology acceptance of myAirCoach-supported self-management on top of usual care in patients with asthma using inhalation medication. METHODS: Patients were recruited in 2 separate studies. The myAirCoach system consisted of an inhaler adapter, an indoor air-quality monitor, a physical activity tracker, a portable spirometer, a fraction exhaled nitric oxide device, and an app. The primary outcome was asthma control; secondary outcomes were exacerbations, quality of life, and technology acceptance. In study 1, 30 participants were randomized to either usual care or myAirCoach support for 3 to 6 months; in study 2, 12 participants were provided with the myAirCoach system in a 3-month before-after study. RESULTS: In study 1, asthma control improved in the intervention group compared with controls (Asthma Control Questionnaire difference, 0.70; P = .006). A total of 6 exacerbations occurred in the intervention group compared with 12 in the control group (hazard ratio, 0.31; P = .06). Asthma-related quality of life improved (mini Asthma-related Quality of Life Questionnaire difference, 0.53; P = .04), but forced expiratory volume in 1 second was unchanged. In study 2, asthma control improved by 0.86 compared with baseline (P = .007) and quality of life by 0.16 (P = .64). Participants reported positive attitudes toward the system. DISCUSSION: Using the myAirCoach support system improves asthma control and quality of life, with a reduction in severe asthma exacerbations. Well-validated mHealth technologies should therefore be further studied.

Deep Learning on Multi Sensor Data for Counter UAV Applications-A Systematic Review.

Usage of Unmanned Aerial Vehicles (UAVs) is growing rapidly in a wide range of consumer applications, as they prove to be both autonomous and flexible in a variety of environments and tasks. However, this versatility and ease of use also brings a rapid evolution of threats by malicious actors that can use UAVs for criminal activities, converting them to passive or active threats. The need to protect critical infrastructures and important events from such threats has brought advances in counter UAV (c-UAV) applications. Nowadays, c-UAV applications offer systems that comprise a multi-sensory arsenal often including electro-optical, thermal, acoustic, radar and radio frequency sensors, whose information can be fused to increase the confidence of threat's identification. Nevertheless, real-time surveillance is a cumbersome process, but it is absolutely essential to detect promptly the occurrence of adverse events or conditions. To that end, many challenging tasks arise such as object detection, classification, multi-object tracking and multi-sensor information fusion. In recent years, researchers have utilized deep learning based methodologies to tackle these tasks for generic objects and made noteworthy progress, yet applying deep learning for UAV detection and classification is considered a novel concept. Therefore, the need to present a complete overview of deep learning technologies applied to c-UAV related tasks on multi-sensor data has emerged. The aim of this paper is to describe deep learning advances on c-UAV related tasks when applied to data originating from many different sensors as well as multi-sensor information fusion. This survey may help in making recommendations and improvements of c-UAV applications for the future.

Substance deposition assessment in obstructed pulmonary system through numerical characterization of airflow and inhaled particles attributes.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) and asthma are considered as the two most widespread obstructive lung diseases, whereas they affect more than 500 million people worldwide. Unfortunately, the requirement for detailed geometric models of the lungs in combination with the increased computational resources needed for the simulation of the breathing did not allow great progress to be made in the past for the better understanding of inflammatory diseases of the airways through detailed modelling approaches. In this context, computational fluid dynamics (CFD) simulations accompanied by fluid particle tracing (FPT) analysis of the inhaled ambient particles are deemed critical for lung function assessment. Also they enable the understanding of particle depositions on the airways of patients, since these accumulations may affect or lead to inflammations. In this direction, the current study conducts an initial investigation for the better comprehension of particle deposition within the lungs. More specifically, accurate models of the airways obstructions that relate to pulmonary disease are developed and a thorough assessment of the airflow behavior together with identification of the effects of inhaled particle properties, such as size and density, is conducted. Our approach presents a first step towards an effective personalization of pulmonary treatment in regards to the geometric characteristics of the lungs and the in depth understanding of airflows within the airways. METHODS: A geometry processing technique involving contraction algorithms is established and used to employ the different respiratory arrangements associated with lung related diseases that exhibit airways obstructions. Apart from the normal lung case, two categories of obstructed cases are examined, i.e. models with obstructions in both lungs and models with narrowings in the right lung only. Precise assumptions regarding airflow and deposition fraction (DF) over various sections of the lungs are drawn by simulating these distinct incidents through the finite volume method (FVM) and particularly the CFD and FPT algorithms. Moreover, a detailed parametric analysis clarifies the effects of the particles size and density in terms of regional deposition upon several parts of the pulmonary system. In this manner, the deposition pattern of various substances can be assessed. RESULTS: For the specific case of the unobstructed lung model most particles are detected on the right lung (48.56% of total, when the air flowrate is 12.6 L/min), a fact that is also true when obstructions arise symmetrically in both lungs (51.45% of total, when the air flowrate is 6.06 L/min and obstructions occur after the second generation). In contrast, when narrowings are developed on the right lung only, most particles are pushed on the left section (68.22% of total, when the air flowrate is 11.2 L/min) indicating that inhaled medication is generally deposited away from the areas of inflammation. This observation is useful when designing medical treatment of lung diseases. Furthermore, particles with diameters from 1 µm to 10 µm are shown to be mainly deposited on the lower airways, whereas particles with diameters of 20 µm and 30 µm are mostly accumulated in the upper airways. As a result, the current analysis indicates increased DF levels in the upper airways when the particle diameter is enlarged. Additionally, when the particles density increases from 1000 Kg/m3 to 2000 Kg/m3, the DF is enhanced on every generation and for all cases investigated herein. The results obtained by our simulations provide an accurate and quantitative estimation of all important parameters involved in lung modeling. CONCLUSIONS: The treatment of respiratory diseases with inhaled medical substances can be advanced by the clinical use of accurate CFD and FPT simulations and specifically by evaluating the deposition of inhaled particles in a regional oriented perspective in regards to different particle sizes and particle densities. Since a drug with specific characteristics (i.e. particle size and density) exhibits maximum deposition on particular lung areas, the current study provides initial indications to a qualified physician for proper selection of medication.