Stable Deep MRI Reconstruction Using Generative Priors.

Data-driven approaches recently achieved remarkable success in magnetic resonance imaging (MRI) reconstruction, but integration into clinical routine remains challenging due to a lack of generalizability and interpretability. In this paper, we address these challenges in a unified framework based on generative image priors. We propose a novel deep neural network based regularizer which is trained in a generative setting on reference magnitude images only. After training, the regularizer encodes higher-level domain statistics which we demonstrate by synthesizing images without data. Embedding the trained model in a classical variational approach yields high-quality reconstructions irrespective of the sub-sampling pattern. In addition, the model shows stable behavior when confronted with out-of-distribution data in the form of contrast variation. Furthermore, a probabilistic interpretation provides a distribution of reconstructions and hence allows uncertainty quantification. To reconstruct parallel MRI, we propose a fast algorithm to jointly estimate the image and the sensitivity maps. The results demonstrate competitive performance, on par with state-of-the-art end-to-end deep learning methods, while preserving the flexibility with respect to sub-sampling patterns and allowing for uncertainty quantification.

Understanding immunity: an alternative framework beyond defense and strength.

In this paper we address the issue of how to think about immunity. Many immunological writings suggest a straightforward option: the view that the immune system is primarily a system of defense, which naturally invites the talk of strong immunity and strong immune response. Despite their undisputable positive role in immunology, such metaphors can also pose a risk of establishing a narrow perspective, omitting from consideration phenomena that do not neatly fit those powerful metaphors. Building on this analysis, we argue two things. First, we argue that the immune system is involved not only in defense. Second, by disentangling various possible meanings of 'strength' and 'weakness' in immunology, we also argue that such a construal of immunity generally contributes to the distortion of the overall picture of what the immune system is, what it does, and why it sometimes fails. Instead, we propose to understand the nature of the immune system in terms of contextuality, regulation, and trade-offs. We suggest that our approach provides lessons for a general understanding of the organizing principles of the immune system in health and disease. For all this to work, we discuss a wide range of immunological phenomena.

Assessing the quality of evidence from epidemiological agent-based models for the COVID-19 pandemic.

Agent-based models (ABMs) are one of the main sources of evidence for decisions regarding mitigation and suppression measures against the spread of SARS-CoV-2. These models have not been previously included in the hierarchy of evidence put forth by the evidence-based medicine movement, which prioritizes those research methods that deliver results less susceptible to the risk of confounding. We point out the need to assess the quality of evidence delivered by ABMs and ask the question of what is the risk that assumptions entertained in ABMs do not include all the key factors and make model predictions susceptible to the problem of confounding.

Agent-based modelling for SARS-CoV-2 epidemic prediction and intervention assessment: A methodological appraisal.

BACKGROUND: Our purpose is to assess epidemiological agent-based models-or ABMs-of the SARS-CoV-2 pandemic methodologically. The rapid spread of the outbreak requires fast-paced decision-making regarding mitigation measures. However, the evidence for the efficacy of non-pharmaceutical interventions such as imposed social distancing and school or workplace closures is scarce: few observational studies use quasi-experimental research designs, and conducting randomized controlled trials seems infeasible. Additionally, evidence from the previous coronavirus outbreaks of SARS and MERS lacks external validity, given the significant differences in contagiousness of those pathogens relative to SARS-CoV-2. To address the pressing policy questions that have emerged as a result of COVID-19, epidemiologists have produced numerous models that range from simple compartmental models to highly advanced agent-based models. These models have been criticized for involving simplifications and lacking empirical support for their assumptions. METHODS: To address these voices and methodologically appraise epidemiological ABMs, we consider AceMod (the model of the COVID-19 epidemic in Australia) as a case study of the modelling practice. RESULTS: Our example shows that, although epidemiological ABMs involve simplifications of various sorts, the key characteristics of social interactions and the spread of SARS-CoV-2 are represented sufficiently accurately. This is the case because these modellers treat empirical results as inputs for constructing modelling assumptions and rules that the agents follow; and they use calibration to assert the adequacy to benchmark variables. CONCLUSIONS: Given this, we claim that the best epidemiological ABMs are models of actual mechanisms and deliver both mechanistic and difference-making evidence. Consequently, they may also adequately describe the effects of possible interventions. Finally, we discuss the limitations of ABMs and put forward policy recommendations.