Development Of Algorithms Research Articles

Development and validation of a risk prediction algorithm for evaluating the efficacy of postoperative adjuvant TACE therapy for hepatocellular carcinoma.

There is a lack of a reliable outcome prediction model for patients evaluating the feasibility of postoperative adjuvant transarterial chemoembolization (PA-TACE) therapy. Our goal was to develop an easy-to-use tool specifically for these patients. From January 2013 to June 2017, patients with hepatocellular carcinoma from the Liver Center of the First Affiliated Hospital of Chongqing Medical University received postoperative adjuvant Transarterial chemoembolization (TACE) therapy after liver cancer resection. A Cox proportional hazards model was established for these patients, followed by internal validation (enhanced bootstrap resampling technique) to further evaluate the predictive performance and discriminanceevaluate the predictive performance and discriminance, and compare it with other predictive models. The prognostic factors considered included tumour number, maximum tumor diameter, Edmondson-Steiner (ES) grade, Microvascular invasion (MVI) grade, Ki67, age, sex, hepatitis B surface antigen, cirrhosis, Alpha-fetoprotein(AFP), Albumin-bilirubin (ALBI) grade, Child-pugh grade, body mass index (BMI), Neutrophil-lymphocyte ratio (NLR), Platelet-to-lymphocyte ratio (PLR). The endpoint of the study was overall survival. The median overall survival was 36 (95%CI: 34.0-38.0 ) months, with 1-year, 2-year and 3-year survival rates being 96.3%, 84.0% and 75.3%, respectively. Tumour number, MVI grade, and BMI was incorporated into the model, which had good differentiation and accuracy. Internal validation (enhanced bootstrap ) suggested that Harrell's C statistic is 0.72. The model consistently outperforms other currently available models. This model may be an easy-to-use tool for screening patients suitable for PA-TACE treatment and guiding the selection of clinical protocols. But further research and external validation are required.

Yoga Posture Recognition Through Computer Vision and Deep Learning

Abstract: India is the place where yoga's science and discipline originated 5,000 years ago. The development of it in ancient India occurred through the Indus-Sarasvati civilization. The Indian subcontinent is where this ancient practice originates,and it has been cherished for its multifaceted benefits that encompass physical, mental, and spiritual. Through asana, meditation, and other breathing techniques, harmony is brought to both body and mind. It also brings peace to the mind. The rise in stress in today's modern lifestyle has led to a global growth in the popularity of yoga. The goal of yoga is to mechanically align the body with effort on the muscles, ligaments, and joints to achieve optimal posture. If the asanas are not performed properly, strain in the joints, ligaments, and backbone can occur, which can have an impact on the hip joints. Therefore, it is vital to maintain correct yoga postures while performing various asanas. The availability of yoga posture prediction and automatic movement analysis is now possible due to the development of computer vision algorithms and sensors. In this work, a framework for recognizing a yoga posture from an image has been built using deep learning techniques such as convolutional neural networks (CNN) and machine learning (ML). The CNN layer is used to extract characteristics from the keypoints, and it is succeeded by a large short-term recollection that recognizes the sequence in which a set of frames occurs in order to make predictions. The stances are then categorized as either correct or inappropriate. The system will provide the user with feedback and display the correctness of posture if the right attitude is detected. This review paper synthesizes the current state-of-the-art in the field of yogic intelligence, focusing on the application of computer vision and deep learning techniques for recognizing yoga postures

Using Artificial Intelligence to Improve Banking Services in India: A Review and Prospects for the Future

Abstract: Across the globe, artificial intelligence (AI) is revolutionizing the financial industry, and India is no exception. Artificial intelligence (AI) technologies are transforming a number of banking services, including customer care, risk management, fraud detection, and personalized financial advice. These innovations are attributed to the development of sophisticated machine learning algorithms, natural language processing, and data analytics. This study offers a thorough analysis of how artificial intelligence (AI) is enhancing banking services in India, looking at the prospects, obstacles, and state of the industry now.We highlight the most important AI applications in Indian banking, including chatbots for customer service, predictive analytics for credit scoring, and algorithmic trading for investment management, through a review of recent research articles, industry reports, and case studies. We also go over the ethical issues, legal framework, and possible societal repercussions of AI use in the Indian banking industry. In conclusion, we provide perspectives on forthcoming patterns and avenues for investigation to fully leverage artificial intelligence in augmenting banking amenities and promoting financial inclusivity in India.

A machine learning algorithm for detecting abnormal patterns in continuous capnography and pulse oximetry monitoring.

Continuous capnography monitors patient ventilation but can be susceptible to artifact, resulting in alarm fatigue. Development of smart algorithms may facilitate accurate detection of abnormal ventilation, allowing intervention before patient deterioration. The objective of this analysis was to use machine learning (ML) to classify combined waveforms of continuous capnography and pulse oximetry as normal or abnormal. We used data collected during the observational, prospective PRODIGY trial, in which patients receiving parenteral opioids underwent continuous capnography and pulse oximetry monitoring while on the general care floor [1]. Abnormal ventilation segments in the data stream were reviewed by nine experts and inter-rater agreement was assessed. Abnormal segments were defined as the time series 60s before and 30s after an abnormal pattern was detected. Normal segments (90s continuous monitoring) were randomly sampled and filtered to discard sequences with missing values. Five ML models were trained on extracted features and optimized towards an Fβ score with β = 2. The results show a high inter-rater agreement (> 87%), allowing 7,858 sequences (2,944 abnormal) to be used for model development. Data were divided into 80% training and 20% test sequences. The XGBoost model had the highest Fβ score of 0.94 (with β = 2), showcasing an impressive recall of 0.98 against a precision of 0.83. This study presents a promising advancement in respiratory monitoring, focusing on reducing false alarms and enhancing accuracy of alarm systems. Our algorithm reliably distinguishes normal from abnormal waveforms. More research is needed to define patterns to distinguish abnormal ventilation from artifacts.

Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non-interventional study in Kenya.

Hypertension and diabetes mellitus (DM) are major causes of morbidity and mortality, with growing burdens in low-income countries where they are underdiagnosed and undertreated. Advances in machine learning may provide opportunities to enhance diagnostics in settings with limited medical infrastructure. A non-interventional study was conducted to develop and validate a machine learning algorithm to estimate cardiovascular clinical and laboratory parameters. At two sites in Kenya, digital retinal fundus photographs were collected alongside blood pressure (BP), laboratory measures and medical history. The performance of machine learning models, originally trained using data from the UK Biobank, were evaluated for their ability to estimate BP, glycated haemoglobin, estimated glomerular filtration rate and diagnoses from fundus images. In total, 301 participants were enrolled. Compared with the UK Biobank population used for algorithm development, participants from Kenya were younger and would probably report Black/African ethnicity, with a higher body mass index and prevalence of DM and hypertension. The mean absolute error was comparable or slightly greater for systolic BP, diastolic BP, glycated haemoglobin and estimated glomerular filtration rate. The model trained to identify DM had an area under the receiver operating curve of 0.762 (0.818 in the UK Biobank) and the hypertension model had an area under the receiver operating curve of 0.765 (0.738 in the UK Biobank). In a Kenyan population, machine learning models estimated cardiovascular parameters with comparable or slightly lower accuracy than in the population where they were trained, suggesting model recalibration may be appropriate. This study represents an incremental step toward leveraging machine learning to make early cardiovascular screening more accessible, particularly in resource-limited settings.

Enhancing Robustness within the Collaborative Federated Learning Framework: A Novel Grouping Algorithm for Edge Clients

In this study, we introduce a novel collaborative federated learning (FL) framework, aiming at enhancing robustness in distributed learning environments, particularly pertinent to IoT and industrial automation scenarios. At the core of our contribution is the development of an innovative grouping algorithm for edge clients. This algorithm employs a distinctive ID distribution function, enabling efficient and secure grouping of both normal and potentially malicious clients. Our proposed grouping scheme accurately determines the numerical difference between normal and malicious groups under various network scenarios. Our method addresses the challenge of model poisoning attacks, ensuring the accuracy of outcomes in a collaborative federated learning framework. Our numerical experiments demonstrate that our grouping scheme effectively limits the number of malicious groups. Additionally, our collaborative FL framework has shown resilience against various levels of poisoning attack abilities and maintained high prediction accuracy across a range of scenarios, showcasing its robustness against poisoning attacks.

Enhanced Approaches for Safeguarding Communication Channels from Illicit Messages

This research project presents a comprehensive strategy aimed at mitigating the pervasive threat of human trafficking through the innovative application of machine learning methodologies. The primary objective revolves around the development and deployment of sophisticated algorithms to identify and intercept human trafficking- related communications. Leveraging the power of Support Vector Machine (SVM) classification, the system meticulously scrutinizes textual data streams, flagging messages indicative of trafficking activities for further investigation. Moreover, our approach extends beyond mere message analysis by incorporating cutting-edge Utilize Convolutional Neural Network (CNN) models for performing facial recognition, age estimation, and gender identification. By harnessing the rich visual information embedded in images and videos, the system enhances its capability to identify potential victims and perpetrators with unprecedented accuracy and efficiency. A pivotal component of our solution is the seamless integration of an alert mechanism facilitated by a Simple Mail Transfer Protocol (SMTP) server. This critical feature ensures that pertinent authorities are promptly notified upon the detection of suspicious activities, enabling swift and decisive intervention. Through this amalgamation of advanced technological frameworks, our research endeavors to empower law enforcement agencies and humanitarian organizations in their tireless efforts to combat the heinous crime of human trafficking. In essence, this research represents a significant stride towards the realization of a technologically fortified defense against the exploitation of vulnerable individuals. By amalgamating state-of-the- art machine learning techniques with real-time alert systems, we aspire to create a formidable deterrent against the perpetrators of this egregious crime, thereby Ensuring the protection of human dignity and advocating for social justice.

SMART DRILLING TECHNOLOGIES: HARNESSING AI FOR PRECISION AND SAFETY IN OIL AND GAS WELL CONSTRUCTION

This paper explores the integration of AI in smart drilling technologies, examining its applications, benefits, challenges, and future prospects. By harnessing the power of AI, smart drilling technologies enable proactive decision-making, automation, and optimization throughout the drilling lifecycle. From well planning and design to real-time monitoring and control, AI-driven systems improve operational performance, reduce risks, and maximize resource recovery. Despite facing challenges such as data integration, technology adoption, and regulatory compliance, the potential benefits of smart drilling technologies are substantial. Enhanced precision, improved safety, increased efficiency, and sustainable practices are among the key benefits offered by these technologies. Looking towards the future, opportunities for further innovation and advancement abound, including the development of advanced AI algorithms, integration with IoT and big data analytics, and a focus on environmental sustainability. By embracing innovation, collaboration, and a commitment to sustainability, the oil and gas industry can unlock new opportunities for growth and resilience in the evolving landscape of oil and gas well construction. Smart drilling technologies hold the promise of reshaping the future of well construction, paving the way for safer, more efficient, and sustainable drilling operations in the oil and gas industry. Smart drilling technologies are revolutionizing the oil and gas industry, offering unprecedented levels of precision and safety in well construction. By integrating artificial intelligence (AI) into drilling processes, these technologies optimize drilling parameters, reduce risks, and maximize resource recovery.. Enhanced precision, improved safety, increased efficiency, and sustainable practices are among the key benefits offered by these technologies. Looking towards the future, opportunities for further innovation and advancement abound, including the development of advanced AI algorithms, integration with IoT and big data analytics, and a focus on environmental sustainability.
 Keywords: Smart drilling, Artificial intelligence (AI), Oil and gas industry Efficiency, Safety, Sustainability.

Application and progress of water colour remote sensing technology in monitoring chlorophyll concentration changes in seawater

This paper provides an in-depth discussion on the application and progress of water colour remote sensing technology in monitoring changes in chlorophyll concentration in seawater. The hydrochromatic remote sensing technique uses spectral data acquired by remote sensing satellites and airborne platforms to monitor and analyse the distribution of marine chlorophyll, which is of great significance for understanding and protecting marine ecosystems. The article first introduces the basic principles and development history of this technology, and then discusses in detail its applications in global ocean monitoring, including resource management, environmental assessment, and ecological protection. In the discussion, we highlight the advantages of water colour remote sensing technology in providing large-scale and efficient ocean monitoring, while also pointing out the challenges it faces in terms of data accuracy, atmospheric disturbance handling and algorithm development. In particular, these challenges are gradually being overcome with the application of advanced computational techniques, such as machine learning and artificial intelligence, resulting in significant improvements in monitoring accuracy and efficiency. Finally, this paper looks at the future direction of water colour remote sensing technology, including technological innovation, data integration and interdisciplinary collaboration, highlighting the potential value of this technology in addressing global climate change and marine environmental protection. Through this comprehensive analysis, we have gained a deeper understanding and appreciation of the important role of water colour remote sensing technology in global ocean monitoring and management.

Generative artificial intelligence to produce high-fidelity blastocyst-stage embryo images.

Can generative artificial intelligence (AI) models produce high-fidelity images of human blastocysts? Generative AI models exhibit the capability to generate high-fidelity human blastocyst images, thereby providing substantial training datasets crucial for the development of robust AI models. The integration of AI into IVF procedures holds the potential to enhance objectivity and automate embryo selection for transfer. However, the effectiveness of AI is limited by data scarcity and ethical concerns related to patient data privacy. Generative adversarial networks (GAN) have emerged as a promising approach to alleviate data limitations by generating synthetic data that closely approximate real images. Blastocyst images were included as training data from a public dataset of time-lapse microscopy (TLM) videos (n = 136). A style-based GAN was fine-tuned as the generative model. We curated a total of 972 blastocyst images as training data, where frames were captured within the time window of 110-120 h post-insemination at 1-h intervals from TLM videos. We configured the style-based GAN model with data augmentation (AUG) and pretrained weights (Pretrained-T: with translation equivariance; Pretrained-R: with translation and rotation equivariance) to compare their optimization on image synthesis. We then applied quantitative metrics including Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) to assess the quality and fidelity of the generated images. Subsequently, we evaluated qualitative performance by measuring the intelligence behavior of the model through the visual Turing test. To this end, 60 individuals with diverse backgrounds and expertise in clinical embryology and IVF evaluated the quality of synthetic embryo images. During the training process, we observed consistent improvement of image quality that was measured by FID and KID scores. Pretrained and AUG + Pretrained initiated with remarkably lower FID and KID values compared to both Baseline and AUG + Baseline models. Following 5000 training iterations, the AUG + Pretrained-R model showed the highest performance of the evaluated five configurations with FID and KID scores of 15.2 and 0.004, respectively. Subsequently, we carried out the visual Turing test, such that IVF embryologists, IVF laboratory technicians, and non-experts evaluated the synthetic blastocyst-stage embryo images and obtained similar performance in specificity with marginal differences in accuracy and sensitivity. In this study, we primarily focused the training data on blastocyst images as IVF embryos are primarily assessed in blastocyst stage. However, generation of an array of images in different preimplantation stages offers further insights into the development of preimplantation embryos and IVF success. In addition, we resized training images to a resolution of 256 × 256 pixels to moderate the computational costs of training the style-based GAN models. Further research is needed to involve a more extensive and diverse dataset from the formation of the zygote to the blastocyst stage, e.g. video generation, and the use of improved image resolution to facilitate the development of comprehensive AI algorithms and to produce higher-quality images. Generative AI models hold promising potential in generating high-fidelity human blastocyst images, which allows the development of robust AI models as it can provide sufficient training datasets while safeguarding patient data privacy. Additionally, this may help to produce sufficient embryo imaging training data with different (rare) abnormal features, such as embryonic arrest, tripolar cell division to avoid class imbalances and reach to even datasets. Thus, generative models may offer a compelling opportunity to transform embryo selection procedures and substantially enhance IVF outcomes. This study was supported by a Horizon 2020 innovation grant (ERIN, grant no. EU952516) and a Horizon Europe grant (NESTOR, grant no. 101120075) of the European Commission to A.S. and M.Z.E., the Estonian Research Council (grant no. PRG1076) to A.S., and the EVA (Erfelijkheid Voortplanting & Aanleg) specialty program (grant no. KP111513) of Maastricht University Medical Centre (MUMC+) to M.Z.E. Not applicable.

Integrated design optimization method for pavement structure and materials based on further development of finite element and particle swarm optimization algorithm

The maintenance design for existing asphalt pavements, characterized by their typical structure and material composition, falls short of meeting the diverse requirements of pavements. There is an urgent need for a more rational design approach that can achieve accurate pavement design while also reducing construction costs. This paper focuses on selected conventional road surface structures and conducts an analysis of how pavement structure and materials impact fatigue life and construction expenses. It employs Python to perform three-dimensional finite element road modeling, analysis, and data extraction at specific locations, using normalized fatigue equation to calculate pavement fatigue life. The optimization variables selected are the modulus E and thickness h, with pavement maintenance cost serving as the optimization target function. The particle swarm optimization algorithm is employed for optimizing these variables. A comparative analysis is carried out for five improved optimization algorithms, optimizing combinations of inertia weight, learning factors, particle speed, number of particles, and iteration times. The results reveal that the enhanced optimization algorithms significantly improve iteration trends, featuring velocity limitations and natural selection mechanisms. Between 0 and 20 iterations, all algorithms search for the optimal solution over a wider interval with greater fluctuations. Between 20 and 30 iterations, each algorithm gradually converges towards its solution, stabilizing in the later stages. Based on optimization speed and actual engineering cost benchmarks, the NDPSO algorithm is selected, resulting in a 52.8% reduction in actual engineering costs. Adjustments to the particle count and iteration number of the NDPSO algorithm are made based on computational cost and optimization accuracy, thus choosing 20 particles and 50 iterations as the recommended parameter combination. By combining automated finite element modeling, analysis, and particle swarm optimization, this paper offers a novel and effective automated design reference for extending the lifespan of asphalt pavement structures.

Benchmarking multi-ancestry prostate cancer polygenic risk scores in a real-world cohort.

Prostate cancer is a heritable disease with ancestry-biased incidence and mortality. Polygenic risk scores (PRSs) offer promising advancements in predicting disease risk, including prostate cancer. While their accuracy continues to improve, research aimed at enhancing their effectiveness within African and Asian populations remains key for equitable use. Recent algorithmic developments for PRS derivation have resulted in improved pan-ancestral risk prediction for several diseases. In this study, we benchmark the predictive power of six widely used PRS derivation algorithms, including four of which adjust for ancestry, against prostate cancer cases and controls from the UK Biobank and All of Us cohorts. We find modest improvement in discriminatory ability when compared with a simple method that prioritizes variants, clumping, and published polygenic risk scores. Our findings underscore the importance of improving upon risk prediction algorithms and the sampling of diverse cohorts.

A Survey of Algorithmic Methods for Competency Self-Assessments in Human-Autonomy Teaming

Humans working with autonomous artificially intelligent systems may not be experts in the inner workings of their machine teammates, but need to understand when to employ, trust, and rely on the system. A critical challenge is to develop machine agents with the capacity to understand their own capabilities and limitations, and the ability to communicate this information to human partners. Self-assessment is an emerging field that tackles this challenge through the development of algorithms that enable autonomous agents to understand and communicate their competency. These methods can engender appropriate trust and align human expectations with autonomous assistant abilities. However, current research in self-assessment is dispersed across many fields, including artificial intelligence, robotics, and human factors. This survey connects work from these disparate areas and reviews state-of-the-art methods for algorithmic self-assessments that enable autonomous agents to estimate, understand, and communicate valuable information pertaining to their competency, with focus on methods that can improve interactions within human-machine teams. To better understand the landscape of self-assessment approaches, we present a framework for categorizing work in self-assessment based on underlying algorithm type: test-based , learning-based , or knowledge-based . We synthesize common features across these approaches and discuss relevant future directions for research in this emerging space.

Improved Landsat Operational Land Imager (OLI) Cloud and Shadow Detection with the Learning Attention Network Algorithm (LANA)

Landsat cloud and cloud shadow detection has a long heritage based on the application of empirical spectral tests to single image pixels, including the Landsat product Fmask algorithm, which uses spectral tests applied to optical and thermal bands to detect clouds and uses the sun-sensor-cloud geometry to detect shadows. Since the Fmask was developed, convolutional neural network (CNN) algorithms, and in particular U-Net algorithms (a type of CNN with a U-shaped network structure), have been developed and are applied to pixels in square patches to take advantage of both spatial and spectral information. The purpose of this study was to develop and assess a new U-Net algorithm that classifies Landsat 8/9 Operational Land Imager (OLI) pixels with higher accuracy than the Fmask algorithm. The algorithm, termed the Learning Attention Network Algorithm (LANA), is a form of U-Net but with an additional attention mechanism (a type of network structure) that, unlike conventional U-Net, uses more spatial pixel information across each image patch. The LANA was trained using 16,861 512 × 512 30 m pixel annotated Landsat 8 OLI patches extracted from 27 images and 69 image subsets that are publicly available and have been used by others for cloud mask algorithm development and assessment. The annotated data were manually refined to improve the annotation and were supplemented with another four annotated images selected to include clear, completely cloudy, and developed land images. The LANA classifies image pixels as either clear, thin cloud, cloud, or cloud shadow. To evaluate the classification accuracy, five annotated Landsat 8 OLI images (composed of >205 million 30 m pixels) were classified, and the results compared with the Fmask and a publicly available U-Net model (U-Net Wieland). The LANA had a 78% overall classification accuracy considering cloud, thin cloud, cloud shadow, and clear classes. As the LANA, Fmask, and U-Net Wieland algorithms have different class legends, their classification results were harmonized to the same three common classes: cloud, cloud shadow, and clear. Considering these three classes, the LANA had the highest (89%) overall accuracy, followed by Fmask (86%), and then U-Net Wieland (85%). The LANA had the highest F1-scores for cloud (0.92), cloud shadow (0.57), and clear (0.89), and the other two algorithms had lower F1-scores, particularly for cloud (Fmask 0.90, U-Net Wieland 0.88) and cloud shadow (Fmask 0.45, U-Net Wieland 0.52). In addition, a time-series evaluation was undertaken to examine the prevalence of undetected clouds and cloud shadows (i.e., omission errors). The band-specific temporal smoothness index (TSIλ) was applied to a year of Landsat 8 OLI surface reflectance observations after discarding pixel observations labelled as cloud or cloud shadow. This was undertaken independently at each gridded pixel location in four 5000 × 5000 30 m pixel Landsat analysis-ready data (ARD) tiles. The TSIλ results broadly reflected the classification accuracy results and indicated that the LANA had the smallest cloud and cloud shadow omission errors, whereas the Fmask had the greatest cloud omission error and the second greatest cloud shadow omission error. Detailed visual examination, true color image examples and classification results are included and confirm these findings. The TSIλ results also highlight the need for algorithm developers to undertake product quality assessment in addition to accuracy assessment. The LANA model, training and evaluation data, and application codes are publicly available for other researchers.

UAV‐based simultaneous localization and mapping in outdoor environments: A systematic scoping review

AbstractThis study aims to investigate the current knowledge of unmanned aerial vehicle (UAV)‐based simultaneous localization and mapping (SLAM) in outdoor environments and to discuss challenges and limitations in this field. A literature search was conducted in three online databases (Web of Science, Scopus, and IEEE) for articles published before October 2022 related to UAV‐based SLAM. A scoping review was carried out to identify the key concepts and applications, and discover research gaps in the use of algorithm‐oriented and task‐oriented, open‐source studies. A total of 97 studies met the criteria after conducting a two‐step screening by a systematic method followed the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses. Among eligible studies, 97 were classified into two main categories: algorithm‐oriented studies and task‐oriented studies. The analysis of the literature revealed that the majority of the studies were focused on the development and implementation of new algorithms and algorithms. This review highlights the significance and diversity of sensors utilized in UAVs in different tasks and applications scenarios that employ different types of sensors. The evaluation method is able to show the real results and performance of the new algorithms in the target scenarios compared with the evaluation method by the public data set and simulation platform.

A bilevel learning approach for nonlocal image deblurring with variable weights parameter

This paper introduces an innovative bilevel optimization approach to elevate the deblurring process. By integrating a weights variable nonlocal model with a spatially varying attached term, the methodology aims to achieve enhanced restoration outcomes. Theoretical scrutiny is dedicated to unraveling the solution of the model, paving the way for the development of an efficient algorithm meticulously crafted to compute the clean image. This algorithm excels in learning both the weights parameter and the balanced L2-L1 attached parameter concurrently, thereby ensuring optimal performance. Through careful parameter selection, the proposed nonlocal deblurring model showcases superior effectiveness, surpassing existing models in terms of both performance and efficacy.

A protocol for annotation of total body photography for machine learning to analyze skin phenotype and lesion classification

IntroductionArtificial Intelligence (AI) has proven effective in classifying skin cancers using dermoscopy images. In experimental settings, algorithms have outperformed expert dermatologists in classifying melanoma and keratinocyte cancers. However, clinical application is limited when algorithms are presented with ‘untrained’ or out-of-distribution lesion categories, often misclassifying benign lesions as malignant, or misclassifying malignant lesions as benign. Another limitation often raised is the lack of clinical context (e.g., medical history) used as input for the AI decision process. The increasing use of Total Body Photography (TBP) in clinical examinations presents new opportunities for AI to perform holistic analysis of the whole patient, rather than a single lesion. Currently there is a lack of existing literature or standards for image annotation of TBP, or on preserving patient privacy during the machine learning process.MethodsThis protocol describes the methods for the acquisition of patient data, including TBP, medical history, and genetic risk factors, to create a comprehensive dataset for machine learning. 500 patients of various risk profiles will be recruited from two clinical sites (Australia and Spain), to undergo temporal total body imaging, complete surveys on sun behaviors and medical history, and provide a DNA sample. This patient-level metadata is applied to image datasets using DICOM labels. Anonymization and masking methods are applied to preserve patient privacy. A two-step annotation process is followed to label skin images for lesion detection and classification using deep learning models. Skin phenotype characteristics are extracted from images, including innate and facultative skin color, nevi distribution, and UV damage. Several algorithms will be developed relating to skin lesion detection, segmentation and classification, 3D mapping, change detection, and risk profiling. Simultaneously, explainable AI (XAI) methods will be incorporated to foster clinician and patient trust. Additionally, a publicly released dataset of anonymized annotated TBP images will be released for an international challenge to advance the development of new algorithms using this type of data.ConclusionThe anticipated results from this protocol are validated AI-based tools to provide holistic risk assessment for individual lesions, and risk stratification of patients to assist clinicians in monitoring for skin cancer.

Identifying episodic carbon monoxide emission events in the MOPITT measurement dataset

Abstract. The Measurements Of Pollution In The Troposphere (MOPITT) instrument aboard NASA's Terra satellite has been measuring upwelling radiance in a nadir-viewing mode since March 2000. These radiance measurements are inverted to yield estimates of carbon monoxide (CO) profiles and total columns, providing the longest satellite record of this trace gas to date. The CO measurements from MOPITT have been used in a variety of ways, including trend analyses and the construction of CO budgets. However, their use is complicated by the influence of episodic emission events, which release large quantities of CO into the atmosphere with irregular timing, such as large sporadic wildfires of natural or anthropogenic origin. The chaotic nature of these events is a large source of variability in CO budgets and models, requiring that these events be well characterized in order to develop an improved understanding of the role they have in influencing tropospheric CO. This study describes the development of a multistep algorithm that is used to identify large episodic emission events using daily mean Level 2 (L2) MOPITT total column measurements gridded to a 0.5 by 0.5° spatial resolution. The core component of this procedure involves empirically determining the expectation density function (EDF) that describes the departure of daily-mean CO observations from the baseline behaviour of CO, as described by its periodic components and trends. The EDFs employed are not assumed to be symmetric but instead are constructed from a pair of superimposed normal distributions. Enhancement flag files are produced following this methodology, identifying the episodic events that show strong enhancement of CO outside of the range of expected CO behaviour and are now made available for the period 3 March 2000 to 31 July 2022. The distribution and frequency of these flagged measurements over this 22-year period are analyzed in order to illustrate the robustness of this method.

Development and validation of a deep learning-based microsatellite instability predictor from prostate cancer whole-slide images

Microsatellite instability-high (MSI-H) is a tumor-agnostic biomarker for immune checkpoint inhibitor therapy. However, MSI status is not routinely tested in prostate cancer, in part due to low prevalence and assay cost. As such, prediction of MSI status from hematoxylin and eosin (H&E) stained whole-slide images (WSIs) could identify prostate cancer patients most likely to benefit from confirmatory testing to evaluate their eligibility for immunotherapy and need for Lynch syndrome testing. Prostate biopsies and surgical resections from prostate cancer patients referred to our institution were analyzed. MSI status was determined by next-generation sequencing. Patients sequenced before a cutoff date formed an algorithm development set (n = 4015, MSI-H 1.8%) and a paired validation set (n = 173, MSI-H 19.7%) that consisted of two serial sections from each sample, one stained and scanned internally and the other at an external site. Patients sequenced after the cutoff date formed a temporally independent validation set (n = 1350, MSI-H 2.3%). Attention-based multiple instance learning models were trained to predict MSI-H from H&E WSIs. The predictor achieved area under the receiver operating characteristic curve values of 0.78 (95% CI [0.69–0.86]), 0.72 (95% CI [0.63–0.81]), and 0.72 (95% CI [0.62–0.82]) on the internally prepared, externally prepared, and temporal validation sets, respectively, showing effective predictability and generalization to both external staining/scanning processes and temporally independent samples. While MSI-H status is significantly correlated with Gleason score, the model remained predictive within each Gleason score subgroup.

A comprehensive benchmark of graph-based genetic variant genotyping algorithms on plant genomes for creating an accurate ensemble pipeline.

Although sequencing technologies have boosted the measurement of the genomic diversity of plant crops, it remains challenging to accurately genotype millions of genetic variants, especially structural variations, with only short reads. In recent years, many graph-based variation genotyping methods have been developed to address this issue and tested for human genomes. However, their performance in plant genomes remains largely elusive. Furthermore, pipelines integrating the advantages of current genotyping methods might be required, considering the different complexity of plant genomes. Here we comprehensively evaluate eight such genotypers in different scenarios in terms of variant type and size, sequencing parameters, genomic context, and complexity, as well as graph size, using both simulated and real data sets from representative plant genomes. Our evaluation reveals that there are still great challenges to applying existing methods to plants, such as excessive repeats and variants or high resource consumption. Therefore, we propose a pipeline called Ensemble Variant Genotyper (EVG) that can achieve better genotyping performance in almost all experimental scenarios and comparably higher genotyping recall and precision even using 5× reads. Furthermore, we demonstrate that EVG is more robust with an increasing number of graphed genomes, especially for insertions and deletions. Our study will provide new insights into the development and application of graph-based genotyping algorithms. We conclude that EVG provides an accurate, unbiased, and cost-effective way for genotyping both small and large variations and will be potentially used in population-scale genotyping for large, repetitive, and heterozygous plant genomes.