Search

Abstract Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology's contribution to patient care and population health, and will revolutionize radiologists' workflows. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI working group with the mandate to discuss and deliberate on practice, policy, and patient care issues related to the introduction and implementation of AI in imaging. This white paper provides recommendations for the CAR derived from deliberations between members of the AI working group. This white paper on AI in radiology will inform CAR members and policymakers on key terminology, educational needs of members, research and development, partnerships, potential clinical applications, implementation, structure and governance, role of radiologists, and potential impact of AI on radiology in Canada. [ABSTRACT FROM AUTHOR]

Repeat photography offers distinctive insights into ecological change, with ground‐based oblique photographs often predating early aerial images by decades. However, the oblique angle of the photographs presents challenges for extracting and analyzing ecological information using traditional remote sensing approaches. Several innovative methods have been developed for analyzing repeat photographs, but none offer a comprehensive end‐to‐end workflow incorporating image classification and georeferencing to produce quantifiable landcover data. In this paper, we provide an overview of two new tools, an automated deep learning classifier and intuitive georeferencing tool, and describe how they are used to derive landcover data from 19 images associated with the Mountain Legacy Project, a research team that works with the world's largest collection of systematic high‐resolution historic mountain photographs. We then combined these data to produce a contemporary landcover map for a study area in Jasper National Park, Canada. We assessed georeferencing accuracy by calculating the root‐mean‐square error and mean displacement for a subset of the images, which was 4.6 and 3.7 m, respectively. Overall classification accuracy of the landcover map produced from oblique images was 68%, which was comparable to landcover data produced from aerial imagery using a conventional classification method. The new workflow advances the use of repeat photographs for yielding quantitative landcover data. It has several advantages over existing methods including the ability to produce quick and consistent image classifications with little human input, and accurately georeference and combine these data to generate landcover maps for large areas. [ABSTRACT FROM AUTHOR]

There is a large amount of drilling core data in the Mackay River oil sands block in Canada, and the accurate identification of facies from the cores is important and necessary for the understanding of the subsurface reservoir. The traditional recognition method of facies from cores is by human work and is very time consuming. Furthermore, the results are different according to different geologists because of the subjective judgment criterion. An efficient and objective method is important to solve the above problem. In this paper, the deep learning image-recognition algorithm is used to automatically and intelligently recognize the facies type from the core image. Through a series of high-reliability preprocessing operations, such as cropping, segmentation, rotation transformation, and noise removal of the original core image, that have been manually identified, the key feature information in the images is extracted based on the ResNet50 convolutional neural network. On the dataset of about 200 core images from 13 facies, an intelligent identification system of facies from core images is constructed, which realizes automatic facies identification from core images. Comparing this method with traditional convolutional neural networks and support vector machines (SVM), the results show that the recognition accuracy of this model is as high as 91.12%, which is higher than the other two models. It is also shown that for a relatively special dataset, such as core images, it is necessary to rely on their global features in order to classify them, and, with a large similarity between some of the categories, it is extremely difficult to classify them. The selection of a suitable neural network model can have a great impact on the accuracy of recognition results. Then, the recognized facies are input as hard data to construct the three-dimensional facies model, which reveals the complex heterogeneity and distribution of the subsurface reservoir for further exploration and development. [ABSTRACT FROM AUTHOR]

Wetlands are important ecosystems that are linked to climate change mitigation. As 25% of global wetlands are located in Canada, accurate and up-to-date wetland classification is of high importance, nationally and internationally. The advent of deep learning techniques has revolutionized the current use of machine learning algorithms to classify complex environments, specifically in remote sensing. In this paper, we explore the potential and possible limitations to be overcome regarding the use of ensemble deep learning techniques for complex wetland classification and discusses the potential and limitation of various solo convolutional neural networks (CNNs), including DenseNet, GoogLeNet, ShuffleNet, MobileNet, Xception, Inception-ResNet, ResNet18, and ResNet101 in three different study areas located in Newfoundland and Labrador, Canada (i.e., Avalon, Gros Morne, and Grand Falls). Moreover, to improve the classification accuracies of wetland classes of bog, fen, marsh, swamp, and shallow water, the results of the three best CNNs in each study area is fused using three supervised classifiers of random forest (RF), bagged tree (BTree), Bayesian optimized tree (BOT), and one unsupervised majority voting classifier. The results suggest that the ensemble models, in particular BTree, have a valuable role to play in the classification of wetland classes of bog, fen, marsh, swamp, and shallow water. The ensemble CNNs show an improvement of 9.63–19.04% in terms of mean producer's accuracy compared to the solo CNNs, to recognize wetland classes in three different study areas. This research indicates a promising potential for integrating ensemble-based learning and deep learning for operational large area land cover, particularly complex wetland type classification. [ABSTRACT FROM AUTHOR]

Background: Emerging artificial intelligence (AI) technologies have diverse applications in medicine. As AI tools advance towards clinical implementation, skills in how to use and interpret AI in a healthcare setting could become integral for physicians. This study examines undergraduate medical students' perceptions of AI, educational opportunities about of AI in medicine, and the desired medium for AI curriculum delivery. Methods: A 32 question survey for undergraduate medical students was distributed from May–October 2021 to students to all 17 Canadian medical schools. The survey assessed the currently available learning opportunities about AI, the perceived need for learning opportunities about AI, and barriers to educating about AI in medicine. Interviews were conducted with participants to provide narrative context to survey responses. Likert scale survey questions were scored from 1 (disagree) to 5 (agree). Interview transcripts were analyzed using qualitative thematic analysis. Results: We received 486 responses from 17 of 17 medical schools (roughly 5% of Canadian undergraduate medical students). The mean age of respondents was 25.34, with 45% being in their first year of medical school, 27% in their 2nd year, 15% in their 3rd year, and 10% in their 4th year. Respondents agreed that AI applications in medicine would become common in the future (94% agree) and would improve medicine (84% agree Further, respondents agreed that they would need to use and understand AI during their medical careers (73% agree; 68% agree), and that AI should be formally taught in medical education (67% agree). In contrast, a significant number of participants indicated that they did not have any formal educational opportunities about AI (85% disagree) and that AI-related learning opportunities were inadequate (74% disagree). Interviews with 18 students were conducted. Emerging themes from the interviews were a lack of formal education opportunities and non-AI content taking priority in the curriculum. Conclusion: A lack of educational opportunities about AI in medicine were identified across Canada in the participating students. As AI tools are currently progressing towards clinical implementation and there is currently a lack of educational opportunities about AI in medicine, AI should be considered for inclusion in formal medical curriculum. [ABSTRACT FROM AUTHOR]

New 'big data' streams such as street-level imagery are offering unprecedented possibilities for developing health-relevant data on the urban environment. Urban environmental features derived from street-level imagery have been used to assess pedestrian-friendly neighbourhood design and to predict active commuting, but few such studies have been conducted in Canada. Using 1.15 million Google Street View (GSV) images in seven Canadian cities, we applied image segmentation and object detection computer vision methods to extract data on persons, bicycles, buildings, sidewalks, open sky (without trees or buildings), and vegetation at postal codes. The associations between urban features and walk-to-work rates obtained from the Canadian Census were assessed. We also assessed how GSV-derived urban features perform in predicting walk-to-work rates relative to more widely used walkability measures. Results showed that features derived from street-level images are better able to predict the percent of people walking to work as their primary mode of transportation compared to data derived from traditional walkability metrics. Given the increasing coverage of street-level imagery around the world, there is considerable potential for machine learning and computer vision to help researchers study patterns of active transportation and other health-related behaviours and exposures. [ABSTRACT FROM AUTHOR]

Uncertainty modeling of renewable energy sources, load demand, electricity price, etc. create a high volume of data in smart grids. Accordingly, in this article, a precise forecasting method based on a deep learning concept with microclustering (MC) task is presented. The MC method is structured based on hybrid unsupervised and supervised clustering tasks by K-means and Gaussian support vector machine, respectively. In the proposed method, the input data sequence is clustered by the MC task, and then the forecasting process is employed. By applying the MC, input data in each hour are categorized into different groups, and a distinctive forecasting unit is allocated to each one. In this way, more clusters and forecasting networks are earmarked for the hours with higher fluctuation rates. The bi-directional long short-term memory (B-LSTM), which is one of the newest recurrent artificial neural networks, is proposed as the forecasting unit. The B-LSTM has bidirectional memory—feedforward and feedback loops—that helps us to investigate both previous and future hidden layers data. The optimal number of clusters in each hour is determined based on the Davies–Bouldin index. To evaluate the performance of the proposed method, in this study, three forecasting tasks including the wind speed, load demand, and electricity price are studied in different periods using the Ontario province, Canada, data set. The results are compared with other benchmarking methods to verify the robustness and effectiveness of the proposed method. In fact, the proposed method, which is equipped with the MC technique and B-LSTM networks, significantly promotes the forecasting results, especially in spike points. [ABSTRACT FROM AUTHOR]

Biological data sets are increasingly becoming information-dense, making it effective to use a computer science-based analysis. We used convolution neural networks (CNN) and the specific CNN architecture Unet to study sponge behavior over time. We analyzed a large time series of hourly high-resolution still images of a marine sponge, Suberites concinnus (Demospongiae, Suberitidae) captured between 2012 and 2015 using the NEPTUNE seafloor cabled observatory, off the west coast of Vancouver Island, Canada. We applied semantic segmentation with the Unet architecture with some modifications, including adapting parts of the architecture to be more applicable to three-channel images (RGB). Some alterations that made this model successful were the use of a dice-loss coefficient, Adam optimizer and a dropout function after each convolutional layer which provided losses, accuracies and dice scores of up to 0.03, 0.98 and 0.97, respectively. The model was tested with five-fold cross-validation. This study is a first step towards analyzing trends in the behavior of a demosponge in an environment that experiences severe seasonal and inter-annual changes in climate. The end objective is to correlate changes in sponge size (activity) over seasons and years with environmental variables collected from the same observatory platform. Our work provides a roadmap for others who seek to cross the interdisciplinary boundaries between biology and computer science. [ABSTRACT FROM AUTHOR]

In 2014, through the World-Class Tanker Safety System (WCTSS) initiative, the Government of Canada launched the Northern Marine Transportation Corridors (NMTC) concept. The corridors were created as a strategic framework to guide Federal investments in marine transportation in the Arctic. With new government investment, under the Oceans Protection Plan (OPP), the corridors initiative, known as the Northern Low-Impact Shipping Corridors, will continue to be developed. Since 2016, the Canadian Hydrographic Service (CHS) has been using the corridors as a key layer in a geographic information system (GIS) model known as the CHS Priority Planning Tool (CPPT). The CPPT helps CHS prioritize its survey and charting efforts in Canada's key traffic areas. Even with these latest efforts, important gaps in the surveys still need to be filled in order to cover the Canadian waterways. To help further develop the safety to navigation and improve survey mission planning, CHS has also been exploring new technologies within remote sensing. Under the Government Related Initiatives Program (GRIP) of the Canadian Space Agency (CSA), CHS has been investigating the potential use of Earth observation (EO) data to identify potential hazards to navigation that are not currently charted on CHS products. Through visual interpretation of satellite imagery, and automatic detection using artificial intelligence (AI), CHS identified several potential hazards to navigation that had previously gone uncharted. As a result, five notices to mariners (NTMs) were issued and the corresponding updates were applied to the charts. In this study, two AI approaches are explored using deep learning and machine learning techniques: the convolution neural network (CNN) and random forest (RF) classification. The study investigates the effectiveness of the two models in identifying shoals in Sentinel-2 and WorldView-2 satellite imagery. The results show that both CNN and RF models can detect shoals with accuracies ranging between 79 and 94% over two study sites; however, WorldView-2 images deliver results with higher accuracy and lower omission errors. The high processing times of using high-resolution imagery and training a deep learning model may not be necessary in order to quickly scan images for shoals; but training a CNN model with a large training set may lead to faster processing times without the need to train individual images. [ABSTRACT FROM AUTHOR]

Despite recent advances of deep Convolutional Neural Networks (CNNs) in various computer vision tasks, their potential for classification of multispectral remote sensing images has not been thoroughly explored. In particular, the applications of deep CNNs using optical remote sensing data have focused on the classification of very high-resolution aerial and satellite data, owing to the similarity of these data to the large datasets in computer vision. Accordingly, this study presents a detailed investigation of state-of-the-art deep learning tools for classification of complex wetland classes using multispectral RapidEye optical imagery. Specifically, we examine the capacity of seven well-known deep convnets, namely DenseNet121, InceptionV3, VGG16, VGG19, Xception, ResNet50, and InceptionResNetV2, for wetland mapping in Canada. In addition, the classification results obtained from deep CNNs are compared with those based on conventional machine learning tools, including Random Forest and Support Vector Machine, to further evaluate the efficiency of the former to classify wetlands. The results illustrate that the full-training of convnets using five spectral bands outperforms the other strategies for all convnets. InceptionResNetV2, ResNet50, and Xception are distinguished as the top three convnets, providing state-of-the-art classification accuracies of 96.17%, 94.81%, and 93.57%, respectively. The classification accuracies obtained using Support Vector Machine (SVM) and Random Forest (RF) are 74.89% and 76.08%, respectively, considerably inferior relative to CNNs. Importantly, InceptionResNetV2 is consistently found to be superior compared to all other convnets, suggesting the integration of Inception and ResNet modules is an efficient architecture for classifying complex remote sensing scenes such as wetlands. [ABSTRACT FROM AUTHOR]