Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic...
详细信息
Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm(3)) were as follows: controls: left = 3060 (standard deviation [SD], 502), right = 3120 (SD, 897);mild cognitive impairment (MCI): left = 2596 (SD, 447), right = 2686 (SD, 473);and Alzheimer's disease (AD): left = 2301 (SD, 492), right = 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's rho = < -0.468, P = <.0005). Cerebrospinal fluid spaces (mm(3)) were as follows: controls: left = 23 (32), right = 25 (25);MCI: left = 15 (13), right = 22 (16);and AD: left = 11(13), right = 20 (25). Five subjects (3.7%) presented with unusual anatomy. Conclusions: This work provides reference hippocampal labels for the training and certification of automated segmentation algorithms. The publicly released labels will allow the widespread implementation of the standard segmentation protocol. (C) 2015 The Alzheimer's Association. Published by Elsevier Inc. All rights reserved.
Machine learning is widely used in information systems design. Yet, trainingalgorithms on imbalanced datasets may severely affect performance on unseen data. For example, in some cases in healthcare, fintech, or cybe...
详细信息
Machine learning is widely used in information systems design. Yet, trainingalgorithms on imbalanced datasets may severely affect performance on unseen data. For example, in some cases in healthcare, fintech, or cybersecurity contexts, certain subclasses are difficult to learn because they are underrepresented in training data. Our study offers a flexible and efficient solution based on a new synthetic average neighborhood sampling algorithm (SANSA), which, in contrast to other solutions, introduces a novel "placement " parameter that can be tuned to adapt to each dataset's unique manifestation of the imbalance. This package can be downloaded for R- 1 . We tested SANSA against seven existing sampling methods used in conjunction with the four most frequently used machine learning models trained on 14 benchmark datasets. Our results provide suggestive evidence that SANSA offers a feasible solution to the imbalance problem for most datasets. Our findings provide practical recommendations for how SANSA can be effectively implemented while reducing the complexity level of an imbalanced learning pipeline.
Commercially available artificial intelligence (AI) algorithms outside of health care have been shown to be susceptible to ethnic, gender, and social bias, which has important implications in the development of Al alg...
详细信息
Commercially available artificial intelligence (AI) algorithms outside of health care have been shown to be susceptible to ethnic, gender, and social bias, which has important implications in the development of Al algorithms in health care and the radiologic sciences. To prevent the introduction bias in health care AI, the physician community should work with developers and regulators to develop pathways to ensure that algorithms marketed for widespread clinical practice are safe, effective, and free of unintended bias. The ACR Data Science Institute has developed structured Al use cases with data elements that allow the development of standardized data sets for AI testing and training across multiple institutions to promote the availability of diverse data for algorithm development. Additionally, the ACR Data Science Institute validation and monitoring services, ACR Certify-AI and ACR Assess-AI, incorporate standards to mitigate algorithm bias and promote health equity. In addition to promoting diversity, the ACR should promote and advocate for payment models for AI that afford access to AI tools for all of our patients regardless of socioeconomic status or the inherent resources of their health systems.
In order to detect the failure of an actuator of a helicopter swashplate, a simple detection method based on a negative selection algorithm (NSA) is developed. This technique, inspired by existing rules found in the b...
详细信息
ISBN:
(纸本)9781479967735
In order to detect the failure of an actuator of a helicopter swashplate, a simple detection method based on a negative selection algorithm (NSA) is developed. This technique, inspired by existing rules found in the biological immunity, rely on a set of elemental detectors which have been trained in order to recognize only the non-self (i.e. faulty) behaviors of the system, without needing an explicit model of the system dynamics. A simple model for the actuator failure is developed and coupled with a helicopter flight dynamics model, and some trajectories for the algorithm training and validation are simulated. A procedure for improving the efficiency of the algorithm by introducing weighting coefficients to the detection function is proposed and successfully tested. Moreover, the performance of the algorithm is slightly improved by observing the covariance of the flight dynamics states, instead of the variables themselves.
To achieve safe and optimal planning and operations of power systems there is a need for using more efficient methods for peak load forecasting. This paper demonstrates the application of sine-cosine algorithm (SCA) f...
详细信息
ISBN:
(纸本)9781538608722
To achieve safe and optimal planning and operations of power systems there is a need for using more efficient methods for peak load forecasting. This paper demonstrates the application of sine-cosine algorithm (SCA) for training artificial neural network (ANN) in the problem of load forecasting. The data used in this study were collected over three years, i.e. 2014-2016, for the day, temperature, relative humidity, electricity load demand. The data set was split into weekdays and weekends and the last year data was kept for testing the trained weights. Genetic algorithm (GA) is used to benchmark the results of SCA. The analysis results show that SCA and GA have good performance and provide good fitting for the trained data and good forecast;however, GA still outperform SCA under the same test conditions. Further improvement could be obtained by combining SCA with another swarm technique to solve wider range of forecasting problems.
The capabilities of machine learning algorithms for observing image-based scenes and recognizing embedded targets have been demonstrated by data scientists and computer vision engineers. Performant algorithms must be ...
详细信息
ISBN:
(纸本)9781510667136;9781510667143
The capabilities of machine learning algorithms for observing image-based scenes and recognizing embedded targets have been demonstrated by data scientists and computer vision engineers. Performant algorithms must be well-trained to complete such a complex task automatically, and this requires a large set of training data on which to base statistical predictions. For electro-optical infrared (EO/IR) remote sensing applications, a substantial image database with suitable variation is necessary. Numerous times of day, sensor perspectives, scene backgrounds, weather conditions and target mission profiles could be included in the training image set to ensure sufficient variety. Acquiring such a diverse image set from measured sources can be a challenge;generating synthetic imagery with appropriate features is possible but must be done with care if robust training is to be accomplished. In this work, MuSEST and CoThermT are used to generate synthetic EO/IR remote sensing imagery of various high-value targets with a range of environmental factors. The impact of simulation choices on image generation and algorithm performance is studied with standard computer vision deeplearning convolutional neural networks and a measured imagery benchmark. Differences discovered in the usage and efficacy of synthetic and measured imagery are reported.
暂无评论