Design and validation of a convolutional neural network for fast, model-free blood flow imaging with multiple exposure speckle imaging.

Multiple exposure speckle imaging has demonstrated its improved accuracy compared to single exposure speckle imaging for relative quantitation of blood flow in vivo. However, the calculation of blood flow maps relies on a pixelwise non-linear fit of a multi-parametric model to the speckle contrasts. This approach has two major drawbacks. First, it is computer-intensive and prevents real time imaging and, second, the mathematical model is not universal and should in principle be adapted to the type of blood vessels. We evaluated a model-free machine learning approach based on a convolutional neural network as an alternative to the non-linear fit approach. A network was designed and trained with annotated speckle contrast data from microfluidic experiments. The neural network performances are then compared to the non-linear fit approach applied to in vitro and in vivo data. The study demonstrates the potential of convolutional networks to provide relative blood flow maps from multiple exposure speckle data in real time.

Learning about psychiatric aspects of medical assistance in dying: a pilot survey of self-perceived educational needs among assessors in a Canadian academic hospital.

BACKGROUND: Medical assistance in dying (MAiD) was legalized in Canada in 2016, although it has been accessible as an end-of-life option in the province of Quebec since 2015. Before its implementation in clinical settings, few physicians had received formal training on requests assessments. New data indicate MAiD requesters have high rates of psychiatric comorbidities. Hence, assessment and management of psychiatric and psychosocial issues among MAiD requesters are important competencies to develop for assessors, although few training programs address them. The aim of our study was to explore physicians' self-perceived educational needs on psychiatric aspects related to MAiD in the province of Quebec. METHODS: We conducted a cross-sectional online survey and used a non-probability sampling design in one academic tertiary care center. A descriptive analysis was performed, and responders were compared on different variables. RESULTS: From twenty-five physician assessors, nineteen responded anonymously to an online survey (n=19). The findings of our pilot study revealed that participants felt highly competent in most psychiatric aspects at end-of-life and related to MAiD practice, except for psychotherapy and psychopharmacology as well as depression identification. Most indicated strong interest in further training. No statistical differences were found among responders regarding previous experience or training in palliative care. CONCLUSIONS: Based on our study, MAiD assessors reported high level of competency in managing psychiatric issues among requesters, but that they also expressed a strong desire for additional education.