Standard Artificial Intelligence Research Articles

A Guideline for Open-Source Tools to Make Medical Imaging Data Ready for Artificial Intelligence Applications: A Society of Imaging Informatics in Medicine (SIIM) Survey.

In recent years, the role of Artificial Intelligence (AI) in medical imaging has become increasingly prominent, with the majority of AI applications approved by the FDA being in imaging and radiology in 2023. The surge in AI model development to tackle clinical challenges underscores the necessity for preparing high-quality medical imaging data. Proper data preparation is crucial as it fosters the creation of standardized and reproducible AI models while minimizing biases. Data curation transforms raw data into a valuable, organized, and dependable resource and is a fundamental process to the success of machine learning and analytical projects. Considering the plethora of available tools for data curation in different stages, it is crucial to stay informed about the most relevant tools within specific research areas. In the current work, we propose a descriptive outline for different steps of data curation while we furnish compilations of tools collected from a survey applied among members of the Society of Imaging Informatics (SIIM) for each of these stages. This collection has the potential to enhance the decision-making process for researchers as they select the most appropriate tool for their specific tasks.

Knowledge, Attitude and Practice of Radiologists Regarding Artificial Intelligence in Medical Imaging.

This study aimed to investigate the knowledge, attitudes, and practice (KAP) of radiologists regarding artificial intelligence (AI) in medical imaging in the southeast of China. This cross-sectional study was conducted among radiologists in the Jiangsu, Zhejiang, and Fujian regions from October to December 2022. A self-administered questionnaire was used to collect demographic data and assess the KAP of participants towards AI in medical imaging. A structural equation model (SEM) was used to analyze the relationships between KAP. The study included 452 valid questionnaires. The mean knowledge score was 9.01±4.87, the attitude score was 48.96±4.90, and 75.22% of participants actively engaged in AI-related practices. Having a master's degree or above (OR=1.877, P=0.024), 5-10 years of radiology experience (OR=3.481, P=0.010), AI diagnosis-related training (OR=2.915, P<0.001), and engaging in AI diagnosis-related research (OR=3.178, P<0.001) were associated with sufficient knowledge. Participants with a junior college degree (OR=2.139, P=0.028), 5-10 years of radiology experience (OR=2.462, P=0.047), and AI diagnosis-related training (OR=2.264, P<0.001) were associated with a positive attitude. Higher knowledge scores (OR=5.240, P<0.001), an associate senior professional title (OR=4.267, P=0.026), 5-10 years of radiology experience (OR=0.344, P=0.044), utilizing AI diagnosis (OR=3.643, P=0.001), and engaging in AI diagnosis-related research (OR=6.382, P<0.001) were associated with proactive practice. The SEM showed that knowledge had a direct effect on attitude (β=0.481, P<0.001) and practice (β=0.412, P<0.001), and attitude had a direct effect on practice (β=0.135, P<0.001). Radiologists in southeastern China hold a favorable outlook on AI-assisted medical imaging, showing solid understanding and enthusiasm for its adoption, despite half lacking relevant training. There is a need for more AI diagnosis-related training, an efficient standardized AI database for medical imaging, and active promotion of AI-assisted imaging in clinical practice. Further research with larger sample sizes and more regions is necessary.

Measuring the Impact of AI in the Diagnosis of Hospitalized Patients

Artificial intelligence (AI) could support clinicians when diagnosing hospitalized patients; however, systematic bias in AI models could worsen clinician diagnostic accuracy. Recent regulatory guidance has called for AI models to include explanations to mitigate errors made by models, but the effectiveness of this strategy has not been established. To evaluate the impact of systematically biased AI on clinician diagnostic accuracy and to determine if image-based AI model explanations can mitigate model errors. Randomized clinical vignette survey study administered between April 2022 and January 2023 across 13 US states involving hospitalist physicians, nurse practitioners, and physician assistants. Clinicians were shown 9 clinical vignettes of patients hospitalized with acute respiratory failure, including their presenting symptoms, physical examination, laboratory results, and chest radiographs. Clinicians were then asked to determine the likelihood of pneumonia, heart failure, or chronic obstructive pulmonary disease as the underlying cause(s) of each patient's acute respiratory failure. To establish baseline diagnostic accuracy, clinicians were shown 2 vignettes without AI model input. Clinicians were then randomized to see 6 vignettes with AI model input with or without AI model explanations. Among these 6 vignettes, 3 vignettes included standard-model predictions, and 3 vignettes included systematically biased model predictions. Clinician diagnostic accuracy for pneumonia, heart failure, and chronic obstructive pulmonary disease. Median participant age was 34 years (IQR, 31-39) and 241 (57.7%) were female. Four hundred fifty-seven clinicians were randomized and completed at least 1 vignette, with 231 randomized to AI model predictions without explanations, and 226 randomized to AI model predictions with explanations. Clinicians' baseline diagnostic accuracy was 73.0% (95% CI, 68.3% to 77.8%) for the 3 diagnoses. When shown a standard AI model without explanations, clinician accuracy increased over baseline by 2.9 percentage points (95% CI, 0.5 to 5.2) and by 4.4 percentage points (95% CI, 2.0 to 6.9) when clinicians were also shown AI model explanations. Systematically biased AI model predictions decreased clinician accuracy by 11.3 percentage points (95% CI, 7.2 to 15.5) compared with baseline and providing biased AI model predictions with explanations decreased clinician accuracy by 9.1 percentage points (95% CI, 4.9 to 13.2) compared with baseline, representing a nonsignificant improvement of 2.3 percentage points (95% CI, -2.7 to 7.2) compared with the systematically biased AI model. Although standard AI models improve diagnostic accuracy, systematically biased AI models reduced diagnostic accuracy, and commonly used image-based AI model explanations did not mitigate this harmful effect. ClinicalTrials.gov Identifier: NCT06098950.

The Application of Artificial Intelligence (AI)-Based Ultrasound for the Diagnosis of Fatty Liver Disease: A Systematic Review.

Fatty liver disease, also known as hepatic steatosis, poses a significant global health concern due to the excessive accumulation of fat within the liver. If left untreated, this condition can give rise to severe complications. Recent advances in artificial intelligence (AI, specifically AI-based ultrasound imaging) offer promising tools for diagnosing this condition. This review endeavors to explore the current state of research concerning AI's role in diagnosing fatty liver disease, with a particular emphasis on imaging methods. To this end, a comprehensive search was conducted across electronic databases, including Google Scholar and Embase, to identify relevant studies published between January 2010 and May 2023, with keywords such as "fatty liver disease" and "artificial intelligence (AI)." The article selection process adhered to the PRISMA framework, ultimately resulting in the inclusion of 13 studies. These studies leveraged AI-assisted ultrasound due to its accessibility and cost-effectiveness, and they hailed from diverse countries, including India, China, Singapore, the United States, Egypt, Iran, Poland, Malaysia, and Korea. These studies employed a variety of AI classifiers, such as support vector machines, convolutional neural networks, multilayer perceptron, fuzzy Sugeno, and probabilistic neural networks, all of which demonstrated a remarkable level of precision. Notably, one study even achieved a diagnostic accuracy rate of 100%, underscoring AI's potential in diagnosing fatty liver disease. Nevertheless, the review acknowledged certain limitations within the included studies, with the majority featuring relatively small sample sizes, often encompassing fewer than 100 patients. Additionally, the variability in AI algorithms and imaging techniques added complexity to the comparative analysis. In conclusion, this review emphasizes the potential of AI in enhancing the diagnosis and management of fatty liver disease through advanced imaging techniques. Future research endeavors should prioritize the execution of large-scale studies that employ standardized AI algorithms and imaging techniques to validate AI's utility in diagnosing this prevalent health condition.

AI and semantic ontology for personalized activity eCoaching in healthy lifestyle recommendations: a meta-heuristic approach

BackgroundAutomated coaches (eCoach) can help people lead a healthy lifestyle (e.g., reduction of sedentary bouts) with continuous health status monitoring and personalized recommendation generation with artificial intelligence (AI). Semantic ontology can play a crucial role in knowledge representation, data integration, and information retrieval.MethodsThis study proposes a semantic ontology model to annotate the AI predictions, forecasting outcomes, and personal preferences to conceptualize a personalized recommendation generation model with a hybrid approach. This study considers a mixed activity projection method that takes individual activity insights from the univariate time-series prediction and ensemble multi-class classification approaches. We have introduced a way to improve the prediction result with a residual error minimization (REM) technique and make it meaningful in recommendation presentation with a Naïve-based interval prediction approach. We have integrated the activity prediction results in an ontology for semantic interpretation. A SPARQL query protocol and RDF Query Language (SPARQL) have generated personalized recommendations in an understandable format. Moreover, we have evaluated the performance of the time-series prediction and classification models against standard metrics on both imbalanced and balanced public PMData and private MOX2-5 activity datasets. We have used Adaptive Synthetic (ADASYN) to generate synthetic data from the minority classes to avoid bias. The activity datasets were collected from healthy adults (n = 16 for public datasets; n = 15 for private datasets). The standard ensemble algorithms have been used to investigate the possibility of classifying daily physical activity levels into the following activity classes: sedentary (0), low active (1), active (2), highly active (3), and rigorous active (4). The daily step count, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) serve as input for the classification models. Subsequently, we re-verify the classifiers on the private MOX2-5 dataset. The performance of the ontology has been assessed with reasoning and SPARQL query execution time. Additionally, we have verified our ontology for effective recommendation generation.ResultsWe have tested several standard AI algorithms and selected the best-performing model with optimized configuration for our use case by empirical testing. We have found that the autoregression model with the REM method outperforms the autoregression model without the REM method for both datasets. Gradient Boost (GB) classifier outperforms other classifiers with a mean accuracy score of 98.00%, and 99.00% for imbalanced PMData and MOX2-5 datasets, respectively, and 98.30%, and 99.80% for balanced PMData and MOX2-5 datasets, respectively. Hermit reasoner performs better than other ontology reasoners under defined settings. Our proposed algorithm shows a direction to combine the AI prediction forecasting results in an ontology to generate personalized activity recommendations in eCoaching.ConclusionThe proposed method combining step-prediction, activity-level classification techniques, and personal preference information with semantic rules is an asset for generating personalized recommendations.

13 Precision Livestock Farming Tools for Climate-Smart Feedyard Operations

Abstract Precision Livestock Farming (PLF) is a technology-driven approach comprising sensors, cameras, global positioning system tracking, and data analytics to collect real-time data on animal behavior, health, welfare, and performance that enables feedyard operations to make informed decisions and take proactive measures to ensure optimized management and the well-being of their livestock and production efficiency. PLF systems leverage advanced analytical tools and techniques, such as artificial intelligence (AI), including machine learning and deep learning, by integrating data provided by various sensors and software with related datasets and standard AI models to obtain unique data-driven decisions on a range of management practices. The most imminent benefits of PLF include reduced environmental impact and increased profitability. Current PLF tools for climate-smart feedyard operations include 1) feed management systems that use data from feed intake and animal behavior to optimize feed efficiency and minimize waste, which has the potential to decrease the amount of greenhouse gas (GHG) emissions linked to livestock feeding and feed production; 2) environmental monitoring systems to collect local temperature, humidity, and air quality to optimize the pen environment, which can reduce stress on animals, reduce diseases, such as the incidence of respiratory and foot infections, and improve their overall health; 3) feeding systems to use data from individual animals to provide individualized feed and nutrient programs, thus, helping to improve and select for feed efficiency and reduce the amount of feed wasted, assisting with mitigating GHG emissions associated with livestock feeding and feed production; 4) individual animal monitoring systems to access behavior, health and well-being of individual animals that, through early disease symptoms detection, can prevent and reduce recovery time, and reduce the amount of medication applied to animals, reducing GHG gas emissions associated with pharmaceutical products; and 5) waste management systems to help reduce GHG emissions associated with manure production by optimizing manure management and reducing the amount of waste, which can also help reduce unpleasant odors and improve the overall environment conditions in and around feedyards. Waste management systems could also measure the soil and water contamination with fugitive nutrients, feed additives, implants, antibiotics, and other pharmaceuticals administrated to animals to maintain health standards. The adoption of PLF tools in feedyard operations aims to create a sustainable and efficient livestock industry by reducing waste, optimizing resources, and improving animal welfare through advanced technologies and analytical tools. Additionally, PLF tools enable feedyards to optimize feeding and breeding programs, minimize waste and environmental pollution, and improve the quality and safety of animal products. In today's fast-paced industry, PLF tools are essential for feedyard operations to monitor, analyze, and make informed decisions about the well-being and production efficiency of their livestock, ultimately contributing to a more sustainable and efficient livestock industry.

Abstract TP95: Utility Of Automated Artificial Intelligence Software In The Analysis Of Ct Perfusion With Acetazolamide Challenge For The Assessment Of Cerebrovascular Reserve In Patients With Cervico-cranial Arterial Stenoses And Occlusions

Background: Cerebrovascular reserve (CVR) assessment is valuable in predicting stroke risk in patients with cranio-cervical stenoses and occlusions. CTP with Acetazolamide challenge (AC) allows a qualitative and quantitative assessment of CVR but is limited by ROI positioning, motion and software. Artificial intelligence (AI) automated software with delay in arrival correction has been validated for the processing of CTP data for acute stroke and may more easily detect abnormal CVR. We sought to compare the results of image-processing with a standard platform (Vitrea™) and AI platform (RAPID™). Methods: Retrospective analysis of an IRB approved prospective database of patients who had CTP with acetazolamide (1g IV) who also had a stenosis/occlusion of the internal carotid or middle cerebral arteries was performed. Symptomatic status was defined as recurrent symptoms related to the vessel of interest within 6 months of scan. Two readers, blinded to the clinical scenario, independently reviewed the CTP datasets and identified CBF regional abnormalities and changes post AC using the 2 different platforms. Abnormal CVR was defined as an increase of CBF post AC of &lt;25% of the baseline in the region of interest with Vitrea™, and an expansion of the volume of tissue with CBF&lt;30% using RAPID™. CTP analyses were correlated with the clinical presentation. Results: Thirty patients fulfilling criteria received CTP before and after AC. 24 patients (80%) were symptomatic. Vitrea™ detected decrease in CBF pre-AC in 27 patients and worsening CBF value post-AC in 19 patients. 10 Patients had an increase &gt;25% in CBF post AC. Rapid™ detected 5 patients with CBF lesion &lt;30% pre-AC. Expansion of the CBF lesion occurred in 8 patients post-AC with a mean change in volume of 7.7 ml (P-value=0.002). The sensitivity for the detection of poor CVR in patients with recurrent symptoms was 80% (95% CI 59.30 - 93.17) with Vitrea™ and 45% (95% CI 25.55%-67.18%) with RAPID™. Conclusion: Automated post processing software with delay in arrival correction algorithm is less sensitive to abnormal CVR and has lower correlation with clinical presentation in this small cohort. Further study is warranted to identify thresholds that may better correlate.

Combining Standard Artificial Intelligence Models, Pre-Processing Techniques, and Post-Processing Methods to Improve the Accuracy of Monthly Runoff Predictions in Karst-Area Watersheds

The complex and unique topography of karst regions highlights the weaknesses of traditional hydrological models which fail to fully generalize them. The successive proposals of standard artificial intelligence (AI) models, pre-processing techniques, and post-processing methods have provided new opportunities to enhance the accuracy of runoff prediction in karst areas. In this study, first, the BP neural network model and the Elman neural network model were used for runoff prediction. Then, the performance of four coupled models—formed by combining two AI pre-processing techniques, Empirical Modal Decomposition (EMD) and Ensemble Empirical Modal Decomposition (EEMD), with the previously mentioned AI models—was investigated. Finally, the accuracy of triple-coupled models, formed by applying the post-processing method of quantile mapping (QM) to the previous coupled models, was estimated. The Nash–Sutcliffe efficiency (NSE), the mean absolute percentage error (MAPE), the root mean square error (RMSE), and the peak percentage of threshold statistics (PPTS) were selected to evaluate and analyze the forecasting results of the above models. The results demonstrated that the BP model had the best prediction effect of the standard AI models, the coupled forecasting models had better prediction accuracy than the standard AI models, and the triple-coupled QM–EMD–Elman model had the best forecasting effect with an NSE value of 0.73, MAPE value of 0.75, RMSE value of 34.60, and PPTS value of 2.36.

Wind speed and global radiation forecasting based on differential, deep and stochastic machine learning of patterns in 2-level historical meteo-quantity sets

AbstractAccurate forecasting of wind speed and solar radiation can help operators of wind farms and Photo-Voltaic (PV) plants prepare efficient and practicable production plans to balance the supply with demand in the generation and consumption of Renewable Energy (RE). Reliable Artificial Intelligence (AI) forecast models can minimize the effect of wind and solar power fluctuations, eliminating their intermittent character in system dispatch planning and utilization. Intelligent wind and solar energy management is essential in load scheduling and decision-making processes to meet user requirements. The proposed 24-h prediction schemes involve the beginning detection and secondary similarity re-evaluation of optimal day-data sequences, which is a notable incremental improvement against state-of-the-art in the consequent application of statistical AI learning. 2-level altitude measurements allow the identification of data relationships between two surface layers (hill and lowland) and adequate interpretation of various meteorological situations, whose differentiate information is used by AI models to recognize upcoming changes in the mid-term day horizon. Observations at two professional meteorological stations comprise specific quantities, of which the most valuable are automatically selected as input for the day model. Differential learning is a novel designed unconventional neurocomputing approach that combines derivative components produced in selected network nodes in the weighted modular output. The complexity of the node-stepwise composed model corresponds to the patterns included in the training data. It allows for representation of high uncertain and nonlinear dynamic systems, dependent on local RE production, not substantially reducing the input vector dimensionality leading to model over simplifications as standard AI does. Available angular and frequency time data (e.g., wind direction, humidity, and irradiation cycles) are combined with the amplitudes to solve reduced Partial Differential Equations (PDEs), defined in network nodes, in the periodical complex form. This is a substantial improvement over the previous publication design. The comparative results show better efficiency and reliability of differential learning in representing the modular uncertainty and PDE dynamics of patterns on a day horizon, taking into account recent deep and stochastic learning. A free available C++ parametric software together with the processed meteo-data sets allow additional comparisons with the presented model results.

Rapid and Accurate Diagnosis of COVID-19 Cases from Chest X-ray Images through an Optimized Features Extraction Approach

The mutants of novel coronavirus (COVID-19 or SARS-Cov-2) are spreading with different variants across the globe, affecting human health and the economy. Rapid detection and providing timely treatment for the COVID-19 infected is the greater challenge. For fast and cost-effective detection, artificial intelligence (AI) can perform a key role in enhancing chest X-ray images and classifying them as infected/non-infected. However, AI needs huge datasets to train and detect the COVID-19 infection, which may impact the overall system speed. Therefore, Deep Neural Network (DNN) is preferred over standard AI models to speed up the classification with a set of features from the datasets. Further, to have accurate feature extraction, an algorithm that combines Zernike Moment Feature (ZMF) and Gray Level Co-occurrence Matrix Feature (GF) is proposed and implemented. The proposed algorithm uses 36 Zernike Moment features with variance and contrast textures. This helps to detect the COVID-19 infection accurately. Finally, the Region Blocking (RB) approach with an optimum sub-image size (32 × 32) is employed to improve the processing speed up to 2.6 times per image. The performance of this implementation presents an accuracy (A) of 93.4%, sensitivity (Se) of 72.4%, specificity (Sp) of 95%, precision (Pr) of 74.9% and F1-score (F1) of 72.3%. These metrics illustrate that the proposed model can identify the COVID-19 infection with a lesser dataset and improved accuracy up to 1.3 times than state-of-the-art existing models.

Harnessing the Power of Artificial Intelligence to Teach Cleft Lip Surgery.

Background:Artificial intelligence (AI) leverages today’s exceptional computational powers and algorithmic abilities to learn from large data sets and solve complex problems. The aim of this study was to construct an AI model that can intelligently and reliably recognize the anatomy of cleft lip and nasal deformity and automate placement of nasolabial markings that can guide surgical design.Methods:We adopted the high-resolution net architecture, a recent family of convolutional neural networks–based deep learning architecture specialized in computer-vision tasks to train an AI model, which can detect and place the 21 cleft anthropometric points on cleft lip photographs and videos. The model was tested by calculating the Euclidean distance between hand-marked anthropometric points placed by an expert cleft surgeon to ones generated by our cleft AI model. A normalized mean error (NME) was calculated for each point.Results:All NME values were between 0.029 and 0.055. The largest NME was for cleft-side cphi. The smallest NME value was for cleft-side alare. These errors were well within standard AI benchmarks.Conclusions:We successfully developed an AI algorithm that can identify the 21 surgically important anatomic landmarks of the unilateral cleft lip. This model can be used alone or integrated with surface projection to guide various cleft lip/nose repairs. Having demonstrated the feasibility of creating such a model on the complex three-dimensional surface of the lip and nose, it is easy to envision expanding the use of AI models to understand all of human surface anatomy—the full territory and playground of plastic surgeons.

Nonlinear Integrated Fuzzy Modeling to Predict Dynamic Occupant Environment Comfort for Optimized Sustainability

In the ever-evolving vibrant landscape of our times, it is crucial that a peaceful environment is ensured taking into account all the likely ecological parameters along with humidity and temperature while conserving energy. Thus, besides mechanical and electric control systems, it has become vital to ensure that artificial intelligence (AI) is assimilated and deployed into the systems so as to raise the well-being of the environment. By disseminating intelligence across the building by utilizing the new internet of things (IoT) technology, along with control formats, local open standard data, AI algorithms, and cloud-based predictive analytics, the heating, ventilation, and air conditioning (HVAC) mechanism renders the capability to acclimatize to use patterns, alterations in use patterns, and equipment breakdown. By tracing human activity coupled with analysis of noise, energy, and temperature in the building, its occupants and facility managers can obtain vital insights for planning, optimum use of space, and behavioral changes, in turn ensuring more content and safer inhabitants and considerably more efficient structures. Moreover, fuzzy modeling shows its applicability factor with the execution of human rationale and reasoning with if-then rules as attained from the system’s input-output info for model setup and training. Additionally, it presents advantages pertaining to predictive functions for tackling nonlinearity and uncertainty as well as studying the capability of the models recommended. Thus, the multi-dimensional model recommended in this study outlines a system architecture as an implementation methodology and how it harmonizes prevailing systems while offering comprehensive knowledge to HVAC systems for the accomplishment of lower energy consumption and inhabitant safety and well-being on the basis of the fuzzy modeling. With tolerance for CO2 discharges moving towards zero, the recommended multi-dimensional model provides substantial advantages for the HVAC sector for meeting the essential objectives while taking into account enhanced sustainability in vibrant and nonlinear environments for enhancing the accuracy and fairness of the assessment outcomes.

AI recognition of patient race in medical imaging: a modelling study

Previous studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. We aimed to conduct a comprehensive evaluation of the ability of AI to recognise a patient's racial identity from medical images. Using private (Emory CXR, Emory Chest CT, Emory Cervical Spine, and Emory Mammogram) and public (MIMIC-CXR, CheXpert, National Lung Cancer Screening Trial, RSNA Pulmonary Embolism CT, and Digital Hand Atlas) datasets, we evaluated, first, performance quantification of deep learning models in detecting race from medical images, including the ability of these models to generalise to external environments and across multiple imaging modalities. Second, we assessed possible confounding of anatomic and phenotypic population features by assessing the ability of these hypothesised confounders to detect race in isolation using regression models, and by re-evaluating the deep learning models by testing them on datasets stratified by these hypothesised confounding variables. Last, by exploring the effect of image corruptions on model performance, we investigated the underlying mechanism by which AI models can recognise race. In our study, we show that standard AI deep learning models can be trained to predict race from medical images with high performance across multiple imaging modalities, which was sustained under external validation conditions (x-ray imaging [area under the receiver operating characteristics curve (AUC) range 0·91-0·99], CT chest imaging [0·87-0·96], and mammography [0·81]). We also showed that this detection is not due to proxies or imaging-related surrogate covariates for race (eg, performance of possible confounders: body-mass index [AUC 0·55], disease distribution [0·61], and breast density [0·61]). Finally, we provide evidence to show that the ability of AI deep learning models persisted over all anatomical regions and frequency spectrums of the images, suggesting the efforts to control this behaviour when it is undesirable will be challenging and demand further study. The results from our study emphasise that the ability of AI deep learning models to predict self-reported race is itself not the issue of importance. However, our finding that AI can accurately predict self-reported race, even from corrupted, cropped, and noised medical images, often when clinical experts cannot, creates an enormous risk for all model deployments in medical imaging. National Institute of Biomedical Imaging and Bioengineering, MIDRC grant of National Institutes of Health, US National Science Foundation, National Library of Medicine of the National Institutes of Health, and Taiwan Ministry of Science and Technology.

AI-Based Media Coding Standards

Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) is the first standards organization to develop data coding standards that have artificial intelligence (AI) as their core technology. MPAI believes that universally accessible standards for AI-based data coding can have the same positive effects on AI as standards had on digital media. Elementary components of MPAI standards&#x2013;AI modules (AIMs)&#x2013;expose standard interfaces for operation in a standard AI framework (AIF). As their performance may depend on the technologies used, MPAI expects that competing developers providing AIMs will promote horizontal markets of AI solutions that build on and further promote AI innovation. Finally, the MPAI framework licences (FWLs) provide guidelines to intellectual property right (IPR) holders facilitating the availability of compatible licenses to standard users.

Artificial intelligence and spine imaging: limitations, regulatory issues and future direction.

As big data and artificial intelligence (AI) in spine care, and medicine as a whole, continue to be at the forefront of research, careful consideration to the quality and techniques utilized is necessary. Predictive modeling, data science, and deep analytics have taken center stage. Within that space, AI and machine learning (ML) approaches toward the use of spine imaging have gathered considerable attention in the past decade. Although several benefits of such applications exist, limitations are also present and need to be considered. The following narrative review presents the current status of AI, in particular, ML, with special regard to imaging studies, in the field of spinal research. A multi-database assessment of the literature was conducted up to September 1, 2021, that addressed AI as it related to imaging of the spine. Articles written in English were selected and critically assessed. Overall, the review discussed the limitations, data quality and applications of ML models in the context of spine imaging. In particular, we addressed the data quality and ML algorithms in spine imaging research by describing preliminary results from a widely accessible imaging algorithm that is currently available for spine specialists to reference for information on severity of spine disease and degeneration which ultimately may alter clinical decision-making. In addition, awareness of the current, under-recognized regulation surrounding the execution of ML for spine imaging was raised. Recommendations were provided for conducting high-quality, standardized AI applications for spine imaging.

Understanding Organizations’ Artificial Intelligence Journey: A Qualitative Approach

Background: With growth in Artificial Intelligence (AI) adoption, challenges and hurdles are also becoming evident. Organizations implementing AI are challenged to find ways to leverage AI to produce optimum results and benefits for the organization. Understanding other organizations’ AI implementation journeys will help them start and implement AI. By understanding the different facets of AI implementation, they can strategize AI to gain business value. Though several studies have examined AI adoption, there are few studies on how firms implement it. We close this gap by studying AI adoption and implementations in various firms. Method: Using a qualitative approach of semi-structured interviews, we studied twenty global organizations of various sizes that have implemented AI. Results: The study categorizes the results into four major themes – facilitators, barriers, trends, and strategies for implementing AI. Our study reinforces the relevance of the TOE framework and Roger’s DOI theory in studying AI adoption. Organizational factors such as top management support, strategic roadmap, availability of skilled resources, and corporate culture influenced AI adoption. Their lack of data or poor data quality is a primary challenge. The privacy laws concerning data, as well as regulatory bottlenecks, further exacerbate this problem. We also identified and mapped the standard AI implementations to their AI technologies. We found that most of them exploit AI’s image and natural language processing capabilities to automate their processes. Regarding implementation, firms work with partners to obtain customer data and use federated learning. Conclusion: Understanding firms’ AI implementation journey will help us promote further adoption and experimentation. Organizations can identify areas where they can leverage AI to enhance value, prepare themselves for the future, start and proceed with AI implementation efforts and overcome barriers they might encounter.

Artificial Intelligence in Undergraduate Medical Education: A Scoping Review.

Artificial intelligence (AI) is a rapidly growing phenomenon poised to instigate large-scale changes in medicine. However, medical education has not kept pace with the rapid advancements of AI. Despite several calls to action, the adoption of teaching on AI in undergraduate medical education (UME) has been limited. This scoping review aims to identify gaps and key themes in the peer-reviewed literature on AI training in UME. The scoping review was informed by Arksey and O'Malley's methodology. Seven electronic databases including MEDLINE and EMBASE were searched for articles discussing the inclusion of AI in UME between January 2000 and July 2020. A total of 4,299 articles were independently screened by 3 co-investigators and 22 full-text articles were included. Data were extracted using a standardized checklist. Themes were identified using iterative thematic analysis. The literature addressed: (1) a need for an AI curriculum in UME, (2) recommendations for AI curricular content including machine learning literacy and AI ethics, (3) suggestions for curriculum delivery, (4) an emphasis on cultivating "uniquely human skills" such as empathy in response to AI-driven changes, and (5) challenges with introducing an AI curriculum in UME. However, there was considerable heterogeneity and poor consensus across studies regarding AI curricular content and delivery. Despite the large volume of literature, there is little consensus on what and how to teach AI in UME. Further research is needed to address these discrepancies and create a standardized framework of competencies that can facilitate greater adoption and implementation of a standardized AI curriculum in UME.

Applying Learning by Observation and Case-Based Reasoning to Improve Commercial RTS Game AI

This document summarises my research in the area of Real-Time Strategy (RTS) video game Artificial Intelligence (AI). The main objective of this research is to increase the quality of AI used in commercial RTS games, which has seen little improvement over the past decade. This objective will be addressed by investigating the use of a learning by observation, case-based reasoning agent, which can be applied to new RTS games with minimal development effort. To be successful, this agent must compare favourably with standard commercial RTS AI techniques: it must be easier to apply, have reasonable resource requirements, and produce a better player. Currently, a prototype implementation has been produced for the game StarCraft, and it has demonstrated the need for processing large sets of input data into a more concise form for use at run-time.

Evaluation of Clinical Application Potential based on a Deep Learning Technique with Real-Size Dental Panoramic Radiography: A Preliminary Study

With the recent advancement of artificial intelligence (AI), data-based research is being actively conducted in the dental medical field. However, there is a limited amoun of research yet based on algorithms using panoramic radiography. This study was conducted to find the standard AI reading that distinguishes the young from the elderly using panoramic radiographic images, and to confirm the applicability of the method as a means of increasing the reliability of a diagnosis. A total of 117 panoramas in A dental clinic were used. The selected radiographic images were classified into two groups: the old group and the young group. To load the classified images into the suggested and designed multi-layer neural network model (modified DarkNet), they were split into 70 % training data and 30 % testing data using the ‘SplitEachLable()’ Matlab function. To identify the old group, the focal class activation mapping or CAM (the height of the alveolar bone and the major places where other treatment actions took place) area was estimated. To identify the young group, a wide CAM area over the entire area was estimated as a feature. These data could be important quantitative indicators of the health of the alveolar bone and of the overall dental condition. Significant results and features were derived to show the potential of quantitative indicators for dental care. The results of this study confirmed the possibility of estimating the alveolar bone age based on AI.

State of AI-Based Monitoring in Smart Manufacturing and Introduction to Focused Section

Over the past few decades, intelligentization, supported by artificial intelligence (AI) technologies, has become an important trend for industrial manufacturing, accelerating the development of smart manufacturing. In modern industries, standard AI has been endowed with additional attributes, yielding the so-called industrial artificial intelligence (IAI) that has become the technical core of smart manufacturing. AI-powered manufacturing brings remarkable improvements in many aspects of closed-loop production chains from manufacturing processes to end product logistics. In particular, IAI incorporating domain knowledge has benefited the area of production monitoring considerably. Advanced AI methods such as deep neural networks, adversarial training, and transfer learning have been widely used to support both diagnostics and predictive maintenance of the entire production process. It is generally believed that IAI is the critical technologies needed to drive the future evolution of industrial manufacturing. This article offers a comprehensive overview of AI-powered manufacturing and its applications in monitoring. More specifically, it summarizes the key technologies of IAI and discusses their typical application scenarios with respect to three major aspects of production monitoring: fault diagnosis, remaining useful life prediction, and quality inspection. In addition, the existing problems and future research directions of IAI are also discussed. This article further introduces the papers in this focused section on AI-based monitoring in smart manufacturing by weaving them into the overview, highlighting how they contribute to and extend the body of literature in this area.