Segmentation ability map: Interpret deep features for medical image segmentation.

Deep convolutional neural networks (CNNs) have been widely used for medical image segmentation. In most studies, only the output layer is exploited to compute the final segmentation results and the hidden representations of the deep learned features have not been well understood. In this paper, we propose a prototype segmentation (ProtoSeg) method to compute a binary segmentation map based on deep features. We measure the segmentation abilities of the features by computing the Dice between the feature segmentation map and ground-truth, named as the segmentation ability score (SA score for short). The corresponding SA score can quantify the segmentation abilities of deep features in different layers and units to understand the deep neural networks for segmentation. In addition, our method can provide a mean SA score which can give a performance estimation of the output on the test images without ground-truth. Finally, we use the proposed ProtoSeg method to compute the segmentation map directly on input images to further understand the segmentation ability of each input image. Results are presented on segmenting tumors in brain MRI, lesions in skin images, COVID-related abnormality in CT images, prostate segmentation in abdominal MRI, and pancreatic mass segmentation in CT images. Our method can provide new insights for interpreting and explainable AI systems for medical image segmentation. Our code is available on: https://github.com/shengfly/ProtoSeg.

The ‘Coping with COVID-19’ Newsletter: People with learning disabilities share their stories through collective narrative documents

We begin this article by reviewing some of the common discourses relating to people with learning disabilities across the Covid-19 pandemic. We then discuss some of the narratives that we have observed people with learning disabilities creating about themselves across the Covid-19 pandemic. We go on to discuss a project aimed at documenting some of these narratives. We reflect on the communication models and collective narrative practices used in the project as well as how these were adapted to meet the needs of people with learning disabilities. We conclude this article with reflections on the effects and outcomes of this project. © 2022, British Psychological Society. All rights reserved.

SARS-CoV-2 detection by a clinical diagnostic RT-LAMP assay [version 1;peer review: 2 approved with reservations]

The ongoing pandemic of SARS-CoV-2 calls for rapid and cost-effective methods to accurately identify infected individuals. The vast majority of patient samples is assessed for viral RNA presence by RT-qPCR. Our biomedical research institute, in collaboration between partner hospitals and an accredited clinical diagnostic laboratory, established a diagnostic testing pipeline that has reported on more than 252,000 RT-qPCR results since its commencement at the beginning of April 2020. However, due to ongoing demand and competition for critical resources, alternative testing strategies were sought. In this work, we present a clinically-validated procedure for high-throughput SARSCoV-2 detection by RT-LAMP in 25 minutes that is robust, reliable, repeatable, sensitive, specific, and inexpensive © 2021. Buck MD et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Policy Responses to Automation in Canada

The impacts of automation and emerging technologies on federal, provincial, and local economies have direct implications for labour markets across the country and require a policy response. Taking into account the impacts of the global COVID-19 pandemic on economies and workforces across the country, this paper reviews the policy choices available to various levels of Canadian governments and businesses in response to the challenges posed by automation. It concludes that reskilling workers, closing economic gaps between rural and urban areas, and preparing for widespread automation are just some of the ways that policymakers, business leaders, and local employers can prepare for, and address, the effects of emerging technologies.

Activism in the time of COVID-19

In many countries, COVID-19 has amplified the health, economic and social inequities that motivate group-based collective action. We draw upon the SIRDE/IDEAS model of social change to explore how the pandemic might have affected complex reactions to social injustices. We argue that the virus elicits widespread negative emotions which are spread contagiously through social media due to increased social isolation caused by shelter-in-place directives. When an incident occurs which highlights systemic injustices, the prevailing negative emotional climate intensifies anger at these injustices as well as other emotions, which motivates participation in protest actions despite the obvious risk. We discuss how the pandemic might shape both normative and non-normative protests, including radical violent and destructive collective actions. We also discuss how separatism is being encouraged in some countries due to a lack of effective national leadership and speculate that this is partially the result of different patterns of social identification. © The Author(s) 2021.

Holding onto the ‘mystery’ within online family and systemic therapy

Covid-19 has led to a shift towards online therapy. This paper focuses on therapists’ experiences of translating systemic practice online with families. A range of UK services are represented, including community, inpatient, adult and children services. A social construction theory, coordinated management of meaning, is used to understand online family and systemic therapy. The new context of online therapy influenced all other levels of the therapeutic encounter including content and structure of sessions, therapeutic relationship, therapists’ identity and culture of therapy. The relationship between ‘doing’ online therapy and reflecting on practice has been central in co-constructing new ways of interacting. There were many similarities across services, where there were differences these were client and context specific. As better ways of engaging emerged, therapists became more confident, creativity in therapy increased and attitudes about online therapy became more positive. Practitioner points: Online systemic therapy is possible across adult and children services at different tiers within community and inpatient settings. CMM provides a framework to understand communication in online therapy. Online therapy requires reconsiderations at all levels of the therapeutic encounter. Increased confidence and competence correlates with positive attitudes about online therapy. Online therapy is impacting on the overall evolving culture of therapy. © 2021 The Association for Family Therapy and Systemic Practice