Deep neural networks (DNNs) have achieved outstanding performance and broad implementation in computer vision tasks such as classification, denoising, segmentation and image synthesis. However, DNN-based models and algorithms have seen limited adaptation and development within radiomics which aim to improve diagnosis or prognosis of cancer. Traditionally, medical practitioners have used expert-derived features such as intensity, shape, textual, and others. We hypothesize that, despite the potential of DNNs to improve oncological classification performances in radiomics, a lack of interpretability of such models prevents their broad utilization, performance, and generalizability. Therefore, the INFORM consortium proposes to investigate explainable artificial intelligence (XAI) with a dual aim of building high performance DNN-based classifiers and developing novel interpretability techniques for radiomics. First, in order to overcome the limited data typically available in radomic studies, we will investigate Monte Carlo methods and generative adversarial networks (GAN) for realistic simulation that can aid building and training DNN architectures. Second, we tackle the interpretability of DNN-based feature engineering and latent variable modeling with innovative developments of saliency maps and related visualization techniques. Both supervised and unsupervised learning will be used to generate features, which can be interpreted in terms of input pixels and expert-derived features. Third, we propose to build explainable AI models that incorporate both expert-derived and DNN-based features. By quantitatively understanding the interplay between expert-derived and DNN-based features, our models will be readily understood and translated into medical applications. Fourth, evaluation will be carried out by clinical collaborators with a focus on lung, cervical and rectal cancer. These proposed DNN models, specifically developed to reveal their innerworkings, will leverage the robustness and trustworthiness of expert-derived features that medical practitioners are familiar with, while providing quantitative and visual feedback. Overall, our methodological research will advance interpretability of feature engineering, generative models, and DNN classifiers with applications in radiomics and broad medical imaging. With this project we aim at maximizing the impact on the patient management of ML and DL techniques by developing novel methods to facilitate training of decision-aid systems for clinical treatment strategies optimization. The methodological approaches we propose in this specific area will play a major role in facilitating the acceptability of DL-based decision-aid systems relying on medical imaging for oncology. The proposed validated predictive models in various cancer types within the context of this project might subsequently be used to drive future prospective clinical studies in which patients could be offered alternative treatment strategies based on the results of these predictive models. Such a clinical and social potential is further enhanced by the public-private collaboration proposed in this project, where the developed methodologies will find their way in products. The multidisciplinarity of INFORM is key to meet the target challenges and achieve the proposed goals. All partners have their individual world-leading qualifications and additional scientific expertise providing all the prerequisites for the efficient implementation of INFORM’s approach. The successful implementation of this project will have a large and prolonged impact both in the Medical/Oncology and the Computing/ Artificial Intelligence field of predictive radiomics model, as well as the same methodology could be extended to other diagnostic and therapeutic medical applications.

Abortion laws are the crux of human rights diversity today. Abortion laws evidence best how differently human rights meanings are construed in various local settings. However, we know very little about how this diversity is generated in practice. This project will scrutinize the communication processes that use human rights as arguments to change abortion laws. We will contrast abortion debates from the last ten years in pairs of countries that represent three regional human rights systems: Mozambique and Senegal (the African Union), Poland and Ireland (the Council of Europe), and Argentina and Honduras (the Organization of American States). These debates show the ambivalence of human rights: they were used successfully to argue both for more liberal and more restrictive abortion laws. To explain this ambivalence, we will apply concepts of argumentative architecture and involvement patterns, coined by the PI as part of her figurational sociology of law, based on Norbert Elias’s theory of the process of civilization. Using a mixed-methods approach that combines qualitative sociology, legal analysis, and corpus linguistics, we will offer a multi-dimensional model for a globally comparative, interdisciplinary socio-legal study of human rights. We will study the structure, composition, and embedding of arguments, along with group perspectives, emotions, and circles of identification of arguing actors so as to arrive at a heat map that will show the distribution of involvement in argumentative architectures. By constructing a global meta-typology of argumentative architectures and involvement patterns in abortion debates, we will explore the integrative, civilizing potential of human rights and identify the centrifugal forces in human rights figuration that comprise the local, regional, and global levels. Finally, we will revisit the role of human rights as a universal toolbox for ideologies in order to plead their conditional rehabilitation.

Background: Over 58 000 suicides in Europe every year have an impact on the educational system, employability and economy. In Sweden, in 2014, the indirect costs (loss of the quality-adjusted life-years, QALYs) of suicides were estimated 849 383 mln euro and approximately 4,3-5,7 mln euro in direct costs (costs of transport, treatment, investigation) (Swedish Civil Contingencies Agency, 2015). Given that more than 50% of individuals who committed suicide had recent contact with healthcare prior to death, it is vital to increase suicide preventive skills of students and teachers in the field of Medicine, Nursing, Psychology, Social Work and Media. Enhancing skills in suicide risk assessment and prevention by the introduction of digital tools which can be used by a person in an acute suicidal crisis (including students and teachers), may save life and improve the accessibility of mental health services for disadvantaged groups. Currently, in the participating countries, there are no available online suicide prevention tools in the field of higher education. The ELLIPSE program aims to fill this gap. The objective: To tackle skills-gaps in suicide prevention while addressing the learning needs and preferences of students as well as the reality of the labor market in the field of health and social care. To enable institutions of higher education to provide online courses in suicide prevention to students. To increase skills of prospective health and social care professionals to cope with the challenges of working with populations at risk for suicide and to increase available employees with skills that professionally serve this population. To encourage prospective journalists to engage in suicide prevention. To promote internationalization, mobility and development of European standards in this field. The participants: Students and teachers in the field of Medicine, Nursing, Psychology, Social Work and Media, NGOs representing patients and relatives, suicide loss survivors, health- and social care workers, first responders, media and policy makers in Sweden, Norway, Poland, Hungary and Austria. The number of participants will be min. 600. The activities: Focus groups, joint staff training event, transnational project meetings, organization of international conferences, survey study, literature research and data analysis. Development and implementation of an e-learning and self-help crisis app. Publishing manuals. Ongoing dissemination and communications via websites, social media, interviews, articles, press conference on World Day of Suicide Prevention, mail, phone contact and networks of participating organizations. The methodology: All activities are grouped in three 1- year phases. The project will start with the dissemination of information about the project World Day of Suicide Prevention (10th September). Phase 1: development of surveys and 10 focus groups representing patients and relatives, suicide loss survivors, mental health and primary healthcare, social care workers, first responders, as well as media, managers, policy makers, students and teachers in the field of Medicine, Nursing, Psychology, Social Care and Media. Phase 2: A preliminary version of e-learning modules, handbook and self-help app will be created and evaluated in feasibility surveys for acceptance. Phase 3: The final version of e-learning program, handbook and self-help app will be launched and evaluated after 3 and 6 months. In Phase 3, research activities will complement the evaluation procedures and will result in open-access scientific publications. The potential protective effects of the suicide preventive programs on suicide rates can be modified by many bio-psycho-socio-cultural factors that need to be taken account. Project will end with the 1st International Conference on Educational Programs in Suicide Prevention 2022. The international expert group will publish guidelines, checklist and a final report.Results and impact. Designed for students and teachers in the field of higher education an e-learning OER course on suicide prevention in the field of higher education with a handbook, a self-help crisis app, a manual with the description of the step-by-step project activities and expert guidelines on educational programs in suicide prevention. All materials will be published online in 6 languages incl. English. The project will monitor the number of users and the potential influence of the program on learners and participants-developer of the program. Participating organizations are expected to have a strong focus on dissemination and sustainability of the project. It may have a large and sustainable impact on organizational and regional (better communication, skills and empowerment), national (increased competence) and international level (development of international expert guidelines on educational programs in suicide prevention that may help to keep high standards of future programs in this field).