An Efficient Semi-Supervised Framework with Multi-Task and Curriculum Learning for Medical Image Segmentation.

A practical problem in supervised deep learning for medical image segmentation is the lack of labeled data which is expensive and time-consuming to acquire. In contrast, there is a considerable amount of unlabeled data available in the clinic. To make better use of the unlabeled data and improve the generalization on limited labeled data, in this paper, a novel semi-supervised segmentation method via multi-task curriculum learning is presented. Here, curriculum learning means that when training the network, simpler knowledge is preferentially learned to assist the learning of more difficult knowledge. Concretely, our framework consists of a main segmentation task and two auxiliary tasks, i.e. the feature regression task and target detection task. The two auxiliary tasks predict some relatively simpler image-level attributes and bounding boxes as the pseudo labels for the main segmentation task, enforcing the pixel-level segmentation result to match the distribution of these pseudo labels. In addition, to solve the problem of class imbalance in the images, a bounding-box-based attention (BBA) module is embedded, enabling the segmentation network to concern more about the target region rather than the background. Furthermore, to alleviate the adverse effects caused by the possible deviation of pseudo labels, error tolerance mechanisms are also adopted in the auxiliary tasks, including inequality constraint and bounding-box amplification. Our method is validated on ACDC2017 and PROMISE12 datasets. Experimental results demonstrate that compared with the full supervision method and state-of-the-art semi-supervised methods, our method yields a much better segmentation performance on a small labeled dataset. Code is available at https://github.com/DeepMedLab/MTCL.

Consumer Views on Health Applications of Consumer Digital Data and Health Privacy Among US Adults: Qualitative Interview Study.

BACKGROUND: In 2020, the number of internet users surpassed 4.6 billion. Individuals who create and share digital data can leave a trail of information about their habits and preferences that collectively generate a digital footprint. Studies have shown that digital footprints can reveal important information regarding an individual's health status, ranging from diet and exercise to depression. Uses of digital applications have accelerated during the COVID-19 pandemic where public health organizations have utilized technology to reduce the burden of transmission, ultimately leading to policy discussions about digital health privacy. Though US consumers report feeling concerned about the way their personal data is used, they continue to use digital technologies. OBJECTIVE: This study aimed to understand the extent to which consumers recognize possible health applications of their digital data and identify their most salient concerns around digital health privacy. METHODS: We conducted semistructured interviews with a diverse national sample of US adults from November 2018 to January 2019. Participants were recruited from the Ipsos KnowledgePanel, a nationally representative panel. Participants were asked to reflect on their own use of digital technology, rate various sources of digital information, and consider several hypothetical scenarios with varying sources and health-related applications of personal digital information. RESULTS: The final cohort included a diverse national sample of 45 US consumers. Participants were generally unaware what consumer digital data might reveal about their health. They also revealed limited knowledge of current data collection and aggregation practices. When responding to specific scenarios with health-related applications of data, they had difficulty weighing the benefits and harms but expressed a desire for privacy protection. They saw benefits in using digital data to improve health, but wanted limits to health programs' use of consumer digital data. CONCLUSIONS: Current privacy restrictions on health-related data are premised on the notion that these data are derived only from medical encounters. Given that an increasing amount of health-related data is derived from digital footprints in consumer settings, our findings suggest the need for greater transparency of data collection and uses, and broader health privacy protections.

Why we need a small data paradigm.

BACKGROUND: There is great interest in and excitement about the concept of personalized or precision medicine and, in particular, advancing this vision via various 'big data' efforts. While these methods are necessary, they are insufficient to achieve the full personalized medicine promise. A rigorous, complementary 'small data' paradigm that can function both autonomously from and in collaboration with big data is also needed. By 'small data' we build on Estrin's formulation and refer to the rigorous use of data by and for a specific N-of-1 unit (i.e., a single person, clinic, hospital, healthcare system, community, city, etc.) to facilitate improved individual-level description, prediction and, ultimately, control for that specific unit. MAIN BODY: The purpose of this piece is to articulate why a small data paradigm is needed and is valuable in itself, and to provide initial directions for future work that can advance study designs and data analytic techniques for a small data approach to precision health. Scientifically, the central value of a small data approach is that it can uniquely manage complex, dynamic, multi-causal, idiosyncratically manifesting phenomena, such as chronic diseases, in comparison to big data. Beyond this, a small data approach better aligns the goals of science and practice, which can result in more rapid agile learning with less data. There is also, feasibly, a unique pathway towards transportable knowledge from a small data approach, which is complementary to a big data approach. Future work should (1) further refine appropriate methods for a small data approach; (2) advance strategies for better integrating a small data approach into real-world practices; and (3) advance ways of actively integrating the strengths and limitations from both small and big data approaches into a unified scientific knowledge base that is linked via a robust science of causality. CONCLUSION: Small data is valuable in its own right. That said, small and big data paradigms can and should be combined via a foundational science of causality. With these approaches combined, the vision of precision health can be achieved.

[Big Data: Technical improvement, degradation or transformation of the solidarity model?] / Big Data : amélioration technique, dégradation ou transformation du modèle de solidarité ?

Big Data, the production of a massive amount of heterogeneous data, is often presented as a means to ensure the economic survival and sustainability of health systems. According to this perspective, Big Data could help save the spirit of our welfare states based on the principles of risks-sharing and equal access to care for all. According to a second perspective, opposed to the first, Big Data would fuel a process of demutualization, transferring to individuals a growing share of responsibility for managing their health. This article proposes to develop a third approach: Big Data does not induce a loss of solidarity but a transformation of the European model of welfare states. These are the data that are now the objects of the pooling. Individual and collective responsibilities are thus redistributed. However, this model, as new as it is, remains liberal in its inspiration; it basically allows the continuation of political liberalism by other means.

Development of South Australian-Victorian Prostate Cancer Health Outcomes Research Dataset.

BACKGROUND: Prostate cancer is the most commonly diagnosed and prevalent malignancy reported to Australian cancer registries, with numerous studies from single institutions summarizing patient outcomes at individual hospitals or States. In order to provide an overview of patterns of care of men with prostate cancer across multiple institutions in Australia, a specialized dataset was developed. This dataset, containing amalgamated data from South Australian and Victorian prostate cancer registries, is called the South Australian-Victorian Prostate Cancer Health Outcomes Research Dataset (SA-VIC PCHORD). RESULTS: A total of 13,598 de-identified records of men with prostate cancer diagnosed and consented between 2008 and 2013 in South Australia and Victoria were merged into the SA-VIC PCHORD. SA-VIC PCHORD contains detailed information about socio-demographic, diagnostic and treatment characteristics of patients with prostate cancer in South Australia and Victoria. Data from individual registries are available to researchers and can be accessed under individual data access policies in each State. CONCLUSIONS: The SA-VIC PCHORD will be used for numerous studies summarizing trends in diagnostic characteristics, survival and patterns of care in men with prostate cancer in Victoria and South Australia. It is expected that in the future the SA-VIC PCHORD will become a principal component of the recently developed bi-national Australian and New Zealand Prostate Cancer Outcomes Registry to collect and report patterns of care and standardised patient reported outcome measures of men nation-wide in Australia and New Zealand.