COVID-Net USPro: An Open-Source Explainable Few-Shot Deep Prototypical Network to Monitor and Detect COVID-19 Infection from Point-of-Care Ultrasound Images

As the Coronavirus Disease 2019 (COVID-19) continues to impact many aspects of life and the global healthcare systems, the adoption of rapid and effective screening methods to prevent further spread of the virus and lessen the burden on healthcare providers is a necessity. As a cheap and widely accessible medical image modality, point-of-care ultrasound (POCUS) imaging allows radiologists to identify symptoms and assess severity through visual inspection of the chest ultrasound images. Combined with the recent advancements in computer science, applications of deep learning techniques in medical image analysis have shown promising results, demonstrating that artificial intelligence-based solutions can accelerate the diagnosis of COVID-19 and lower the burden on healthcare professionals. However, the lack of a huge amount of well-annotated data poses a challenge in building effective deep neural networks in the case of novel diseases and pandemics. Motivated by this, we present COVID-Net USPro, an explainable few-shot deep prototypical network, that monitors and detects COVID-19 positive cases with high precision and recall from minimal ultrasound images. COVID-Net USPro achieves 99.65% overall accuracy, 99.7% recall and 99.67% precision for COVID-19 positive cases when trained with only 5 shots. The analytic pipeline and results were verified by our contributing clinician with extensive experience in POCUS interpretation, ensuring that the network makes decisions based on actual patterns.

A Trustworthy Framework for Medical Image Analysis with Deep Learning

Computer vision and machine learning are playing an increasingly important role in computer-assisted diagnosis; however, the application of deep learning to medical imaging has challenges in data availability and data imbalance, and it is especially important that models for medical imaging are built to be trustworthy. Therefore, we propose TRUDLMIA, a trustworthy deep learning framework for medical image analysis, which adopts a modular design, leverages self-supervised pre-training, and utilizes a novel surrogate loss function. Experimental evaluations indicate that models generated from the framework are both trustworthy and high-performing. It is anticipated that the framework will support researchers and clinicians in advancing the use of deep learning for dealing with public health crises including COVID-19.

On the evolution of research in hypersonics: application of natural language processing and machine learning

Research and development in hypersonics have progressed significantly in recent years, with various military and commercial applications being demonstrated increasingly. Public and private organizations in several countries have been investing in hypersonics, with the aim to overtake their competitors and secure/improve strategic advantage and deterrence. For these organizations, being able to identify emerging technologies in a timely and reliable manner is paramount. Recent advances in information technology have made it possible to analyze large amounts of data, extract hidden patterns, and provide decision-makers with new insights. In this study, we focus on scientific publications about hypersonics within the period of 2000-2020, and employ natural language processing and machine learning to characterize the research landscape by identifying 12 key latent research themes and analyzing their temporal evolution. Our publication similarity analysis revealed patterns that are indicative of cycles during two decades of research. The study offers a comprehensive analysis of the research field and the fact that the research themes are algorithmically extracted removes subjectivity from the exercise and enables consistent comparisons between topics and between time intervals.

Towards Trustworthy Healthcare AI: Attention-Based Feature Learning for COVID-19 Screening With Chest Radiography

Building AI models with trustworthiness is important especially in regulated areas such as healthcare. In tackling COVID-19, previous work uses convolutional neural networks as the backbone architecture, which has shown to be prone to over-caution and overconfidence in making decisions, rendering them less trustworthy -- a crucial flaw in the context of medical imaging. In this study, we propose a feature learning approach using Vision Transformers, which use an attention-based mechanism, and examine the representation learning capability of Transformers as a new backbone architecture for medical imaging. Through the task of classifying COVID-19 chest radiographs, we investigate into whether generalization capabilities benefit solely from Vision Transformers' architectural advances. Quantitative and qualitative evaluations are conducted on the trustworthiness of the models, through the use of "trust score" computation and a visual explainability technique. We conclude that the attention-based feature learning approach is promising in building trustworthy deep learning models for healthcare.

Women, artificial intelligence, and key positions in collaboration networks: Towards a more equal scientific ecosystem

Scientific collaboration in almost every discipline is mainly driven by the need of sharing knowledge, expertise, and pooled resources. Science is becoming more complex which has encouraged scientists to involve more in collaborative research projects in order to better address the challenges. As a highly interdisciplinary field with a rapidly evolving scientific landscape, artificial intelligence calls for researchers with special profiles covering a diverse set of skills and expertise. Understanding gender aspects of scientific collaboration is of paramount importance, especially in a field such as artificial intelligence that has been attracting large investments. Using social network analysis, natural language processing, and machine learning and focusing on artificial intelligence publications for the period from 2000 to 2019, in this work, we comprehensively investigated the effects of several driving factors on acquiring key positions in scientific collaboration networks through a gender lens. It was found that, regardless of gender, scientific performance in terms of quantity and impact plays a crucial in possessing the "social researcher" in the network. However, subtle differences were observed between female and male researchers in acquiring the "local influencer" role.

COVID-Net UV: An End-to-End Spatio-Temporal Deep Neural Network Architecture for Automated Diagnosis of COVID-19 Infection from Ultrasound Videos

Besides vaccination, as an effective way to mitigate the further spread of COVID-19, fast and accurate screening of individuals to test for the disease is yet necessary to ensure public health safety. We propose COVID-Net UV, an end-to-end hybrid spatio-temporal deep neural network architecture, to detect COVID-19 infection from lung point-of-care ultrasound videos captured by convex transducers. COVID-Net UV comprises a convolutional neural network that extracts spatial features and a recurrent neural network that learns temporal dependence. After careful hyperparameter tuning, the network achieves an average accuracy of 94.44% with no false-negative cases for COVID-19 cases. The goal with COVID-Net UV is to assist front-line clinicians in the fight against COVID-19 via accelerating the screening of lung point-of-care ultrasound videos and automatic detection of COVID-19 positive cases.

Detecting Emerging Technologies and their Evolution using Deep Learning and Weak Signal Analysis

Emerging technologies can have major economic impacts and affect strategic stability. Yet, early identification of emerging technologies remains challenging. In order to identify emerging technologies in a timely and reliable manner, a comprehensive examination of relevant scientific and technological (S&T) trends and their related references is required. This examination is generally done by domain experts and requires significant amounts of time and effort to gain insights. The use of domain experts to identify emerging technologies from S&T trends may limit the capacity to analyse large volumes of information and introduce subjectivity in the assessments. Decision support systems are required to provide accurate and reliable evidence-based indicators through constant and continuous monitoring of the environment and help identify signals of emerging technologies that could alter security and economic prosperity. For example, the research field of hypersonics has recently witnessed several advancements having profound technological, commercial, and national security implications. In this work, we present a multi-layer quantitative approach able to identify future signs from scientific publications on hypersonics by leveraging deep learning and weak signal analysis. The proposed framework can help strategic planners and domain experts better identify and monitor emerging technology trends.

Improving Classification Model Performance on Chest X-Rays through Lung Segmentation

Chest radiography is an effective screening tool for diagnosing pulmonary diseases. In computer-aided diagnosis, extracting the relevant region of interest, i.e., isolating the lung region of each radiography image, can be an essential step towards improved performance in diagnosing pulmonary disorders. Methods: In this work, we propose a deep learning approach to enhance abnormal chest x-ray (CXR) identification performance through segmentations. Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets. The proposed pipeline is evaluated on Shenzhen Hospital (SH) data set for the segmentation module, and COVIDx data set for both segmentation and classification modules. Novel statistical analysis is conducted in addition to regular evaluation metrics for the segmentation module. Furthermore, the results of the optimized approach are analyzed with gradient-weighted class activation mapping (Grad-CAM) to investigate the rationale behind the classification decisions and to interpret its choices. Results and Conclusion: Different data sets, methods, and scenarios for each module of the proposed pipeline are examined for designing an optimized approach, which has achieved an accuracy of 0.946 in distinguishing abnormal CXR images (i.e., Pneumonia and COVID-19) from normal ones. Numerical and visual validations suggest that applying automated segmentation as a pre-processing step for classification improves the generalization capability and the performance of the classification models.

Performance or Trust? Why Not Both. Deep AUC Maximization with Self-Supervised Learning for COVID-19 Chest X-ray Classifications

Effective representation learning is the key in improving model performance for medical image analysis. In training deep learning models, a compromise often must be made between performance and trust, both of which are essential for medical applications. Moreover, models optimized with cross-entropy loss tend to suffer from unwarranted overconfidence in the majority class and over-cautiousness in the minority class. In this work, we integrate a new surrogate loss with self-supervised learning for computer-aided screening of COVID-19 patients using radiography images. In addition, we adopt a new quantification score to measure a model's trustworthiness. Ablation study is conducted for both the performance and the trust on feature learning methods and loss functions. Comparisons show that leveraging the new surrogate loss on self-supervised models can produce label-efficient networks that are both high-performing and trustworthy.

NRC-GAMMA: Introducing a Novel Large Gas Meter Image Dataset

Automatic meter reading technology is not yet widespread. Gas, electricity, or water accumulation meters reading is mostly done manually on-site either by an operator or by the homeowner. In some countries, the operator takes a picture as reading proof to confirm the reading by checking offline with another operator and/or using it as evidence in case of conflicts or complaints. The whole process is time-consuming, expensive, and prone to errors. Automation can optimize and facilitate such labor-intensive and human error-prone processes. With the recent advances in the fields of artificial intelligence and computer vision, automatic meter reading systems are becoming more viable than ever. Motivated by the recent advances in the field of artificial intelligence and inspired by open-source open-access initiatives in the research community, we introduce a novel large benchmark dataset of real-life gas meter images, named the NRC-GAMMA dataset. The data were collected from an Itron 400A diaphragm gas meter on January 20, 2020, between 00:05 am and 11:59 pm. We employed a systematic approach to label the images, validate the labellings, and assure the quality of the annotations. The dataset contains 28,883 images of the entire gas meter along with 57,766 cropped images of the left and the right dial displays. We hope the NRC-GAMMA dataset helps the research community to design and implement accurate, innovative, intelligent, and reproducible automatic gas meter reading solutions.