scholarly journals ENRIch: Exploiting Image Similarity to Maximize Efficient Machine Learning in Medical Imaging

2021 ◽  
Author(s):  
Erin M Chinn ◽  
Rohit Arora ◽  
Ramy Arnaout ◽  
Rima Arnaout
Keyword(s):  
Medical Imaging ◽  
Binary Classification ◽  
Model Performance ◽  
Training Data ◽  
Image Similarity ◽  
P Value ◽  
Pairwise Similarity ◽  
Original Dataset ◽  
Improve Model ◽  
Segmentation Task

Deep learning (DL) has been applied with success in proofs of concept across biomedical imaging, including across modalities and medical specialties1-17. Labeled data is critical to training and testing DL models, and such models traditionally require large amounts of training data, straining the limited (human) resources available for expert labeling/annotation. It would be ideal to prioritize labeling those images that are most likely to improve model performance and skip images that are redundant. However, straightforward, robust, and quantitative metrics for measuring and eliminating redundancy in datasets have not yet been described. Here, we introduce a new method, ENRIch (Eliminate Needless Redundancy in Imaging datasets), for assessing image dataset redundancy and test it on a well benchmarked medical imaging dataset3. First, we compute pairwise similarity metrics for images in a given dataset, resulting in a matrix of pairwise similarity values. We then rank images based on this matrix and use these rankings to curate the dataset, to minimize dataset redundancy. Using this method, we achieve similar AUC scores in a binary classification task with just a fraction of our original dataset (AUC of 0.99 +/- 1.35e-05 on 44 percent of available images vs. AUC of 0.99 +/- 9.32e-06 on all available images, p-value 0.0002) and better scores than the same sized training subsets chosen at random. We also demonstrate similar Jaccard scores in a multi-class segmentation task while eliminating redundant images (average Jaccard index of 0.58 on 80 percent of available images vs. 0.60 on all available images). Thus, algorithms that reduce dataset redundancy based on image similarity can significantly reduce the number of training images required, while preserving performance, in medical imaging datasets.

scholarly journals Estimating the phase volume fraction of multi-phase steel via unsupervised deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Sung Wook Kim ◽  
Seong-Hoon Kang ◽  
Se-Jong Kim ◽  
Seungchul Lee
Keyword(s):  
High Performance ◽  
Materials Science ◽  
Volume Fraction ◽  
Training Data ◽  
Phase Fraction ◽  
Phase Volume ◽  
Generative Adversarial Network ◽  
Phase Volume Fraction ◽  
Original Dataset ◽  
Multi Phase

AbstractAdvanced high strength steel (AHSS) is a steel of multi-phase microstructure that is processed under several conditions to meet the current high-performance requirements from the industry. Deep neural network (DNN) has emerged as a promising tool in materials science for the task of estimating the phase volume fraction of these steels. Despite its advantages, one of its major drawbacks is its requirement of a sufficient amount of training data with correct labels to the network. This often comes as a challenge in many areas where obtaining data and labeling it is extremely labor-intensive. To overcome this challenge, an unsupervised way of learning DNN, which does not require any manual labeling, is proposed. Information maximizing generative adversarial network (InfoGAN) is used to learn the underlying probability distribution of each phase and generate realistic sample points with class labels. Then, the generated data is used for training an MLP classifier, which in turn predicts the labels for the original dataset. The result shows a mean relative error of 4.53% at most, while it can be as low as 0.73%, which implies the estimated phase fraction closely matches the true phase fraction. This presents the high feasibility of using the proposed methodology for fast and precise estimation of phase volume fraction in both industry and academia.

scholarly journals Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1688
Author(s):  
Luqman Ali ◽  
Fady Alnajjar ◽  
Hamad Al Jassmi ◽  
Munkhjargal Gochoo ◽  
Wasif Khan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Crack Detection ◽  
Concrete Structures ◽  
Model Performance ◽  
Training Data ◽  
Computational Time ◽  
Data Heterogeneity ◽  
Public Datasets ◽  
Detection And Localization

This paper proposes a customized convolutional neural network for crack detection in concrete structures. The proposed method is compared to four existing deep learning methods based on training data size, data heterogeneity, network complexity, and the number of epochs. The performance of the proposed convolutional neural network (CNN) model is evaluated and compared to pretrained networks, i.e., the VGG-16, VGG-19, ResNet-50, and Inception V3 models, on eight datasets of different sizes, created from two public datasets. For each model, the evaluation considered computational time, crack localization results, and classification measures, e.g., accuracy, precision, recall, and F1-score. Experimental results demonstrated that training data size and heterogeneity among data samples significantly affect model performance. All models demonstrated promising performance on a limited number of diverse training data; however, increasing the training data size and reducing diversity reduced generalization performance, and led to overfitting. The proposed customized CNN and VGG-16 models outperformed the other methods in terms of classification, localization, and computational time on a small amount of data, and the results indicate that these two models demonstrate superior crack detection and localization for concrete structures.

scholarly journals Towards Robust Representations of Spatial Networks Using Graph Neural Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6918
Author(s):  
Chidubem Iddianozie ◽  
Gavin McArdle
Keyword(s):  
Machine Learning ◽  
Model Performance ◽  
Network Models ◽  
Data Representation ◽  
Spatial Networks ◽  
Neural Network Models ◽  
Improve Model ◽  
Graph Neural Networks ◽  
Spatial Entities ◽  
Improve Model Performance

The effectiveness of a machine learning model is impacted by the data representation used. Consequently, it is crucial to investigate robust representations for efficient machine learning methods. In this paper, we explore the link between data representations and model performance for inference tasks on spatial networks. We argue that representations which explicitly encode the relations between spatial entities would improve model performance. Specifically, we consider homogeneous and heterogeneous representations of spatial networks. We recognise that the expressive nature of the heterogeneous representation may benefit spatial networks and could improve model performance on certain tasks. Thus, we carry out an empirical study using Graph Neural Network models for two inference tasks on spatial networks. Our results demonstrate that heterogeneous representations improves model performance for down-stream inference tasks on spatial networks.

scholarly journals Population Pharmacokinetics of Doxycycline in Children

2019 ◽  
Vol 63 (12) ◽  
Author(s):  
Elizabeth J. Thompson ◽  
Huali Wu ◽  
Chiara Melloni ◽  
Stephen Balevic ◽  
Janice E. Sullivan ◽  
...  
Keyword(s):  
Model Performance ◽  
Standard Of Care ◽  
Volume Of Distribution ◽  
Clinical Value ◽  
Final Model ◽  
Childhood Infections ◽  
Obesity Status ◽  
Improve Model ◽  
Using Data ◽  
Improve Model Performance

ABSTRACT Doxycycline is a tetracycline-class antimicrobial labeled by the U.S. Food and Drug Administration for children >8 years of age for many common childhood infections. Doxycycline is not labeled for children ≤8 years of age, due to the association between tetracycline-class antibiotics and tooth staining, although doxycycline may be used off-label under severe conditions. Accordingly, there is a paucity of pharmacokinetic (PK) data to guide dosing in children 8 years and younger. We leveraged opportunistically collected plasma samples after intravenous (i.v.) and oral doxycycline doses received per standard of care to characterize the PK of doxycycline in children of different ages and evaluated the effect of obesity and fasting status on PK parameters. We developed a population PK model of doxycycline using data collected from 47 patients 0 to 18 years of age, including 14 participants ≤8 years. We developed a 1-compartment PK model and found doxycycline clearance to be 3.32 liters/h/70 kg of body weight and volume to be 96.8 liters/70 kg for all patients, comparable to values reported in adults. We estimated a bioavailability of 89.6%, also consistent with adult data. Allometrically scaled clearance and volume of distribution did not differ between children 2 to ≤8 years of age and children >8 to ≤18 years of age, suggesting that younger children may be given the same per-kilogram dosing. Obesity status and fasting status were not selected for inclusion in the final model. Additional doxycycline PK samples collected in future studies may be used to improve model performance and maximize its clinical value.

scholarly journals Three-Dimensional Liver Image Segmentation Using Generative Adversarial Networks Based on Feature Restoration

2022 ◽  
Vol 8 ◽  
Author(s):  
Runnan He ◽  
Shiqi Xu ◽  
Yashu Liu ◽  
Qince Li ◽  
Yang Liu ◽  
...  
Keyword(s):  
Medical Imaging ◽  
Random Noise ◽  
Three Dimensional ◽  
Poor Quality ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Liver Segmentation ◽  
Deep Convolutional Neural Networks ◽  
Adversarial Networks ◽  
Liver Region

Medical imaging provides a powerful tool for medical diagnosis. In the process of computer-aided diagnosis and treatment of liver cancer based on medical imaging, accurate segmentation of liver region from abdominal CT images is an important step. However, due to defects of liver tissue and limitations of CT imaging procession, the gray level of liver region in CT image is heterogeneous, and the boundary between the liver and those of adjacent tissues and organs is blurred, which makes the liver segmentation an extremely difficult task. In this study, aiming at solving the problem of low segmentation accuracy of the original 3D U-Net network, an improved network based on the three-dimensional (3D) U-Net, is proposed. Moreover, in order to solve the problem of insufficient training data caused by the difficulty of acquiring labeled 3D data, an improved 3D U-Net network is embedded into the framework of generative adversarial networks (GAN), which establishes a semi-supervised 3D liver segmentation optimization algorithm. Finally, considering the problem of poor quality of 3D abdominal fake images generated by utilizing random noise as input, deep convolutional neural networks (DCNN) based on feature restoration method is designed to generate more realistic fake images. By testing the proposed algorithm on the LiTS-2017 and KiTS19 dataset, experimental results show that the proposed semi-supervised 3D liver segmentation method can greatly improve the segmentation performance of liver, with a Dice score of 0.9424 outperforming other methods.

scholarly journals DANNP: an efficient artificial neural network pruning tool

2017 ◽  
Vol 3 ◽  
pp. e137 ◽  
Author(s):  
Mona Alshahrani ◽  
Othman Soufan ◽  
Arturo Magana-Mora ◽  
Vladimir B. Bajic
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Model Performance ◽  
Training Data ◽  
Classification Problems ◽  
Link Type ◽  
On Line ◽  
Pruning Algorithms ◽  
Artificial Neural ◽  
The Impact

Background Artificial neural networks (ANNs) are a robust class of machine learning models and are a frequent choice for solving classification problems. However, determining the structure of the ANNs is not trivial as a large number of weights (connection links) may lead to overfitting the training data. Although several ANN pruning algorithms have been proposed for the simplification of ANNs, these algorithms are not able to efficiently cope with intricate ANN structures required for complex classification problems. Methods We developed DANNP, a web-based tool, that implements parallelized versions of several ANN pruning algorithms. The DANNP tool uses a modified version of the Fast Compressed Neural Network software implemented in C++ to considerably enhance the running time of the ANN pruning algorithms we implemented. In addition to the performance evaluation of the pruned ANNs, we systematically compared the set of features that remained in the pruned ANN with those obtained by different state-of-the-art feature selection (FS) methods. Results Although the ANN pruning algorithms are not entirely parallelizable, DANNP was able to speed up the ANN pruning up to eight times on a 32-core machine, compared to the serial implementations. To assess the impact of the ANN pruning by DANNP tool, we used 16 datasets from different domains. In eight out of the 16 datasets, DANNP significantly reduced the number of weights by 70%–99%, while maintaining a competitive or better model performance compared to the unpruned ANN. Finally, we used a naïve Bayes classifier derived with the features selected as a byproduct of the ANN pruning and demonstrated that its accuracy is comparable to those obtained by the classifiers trained with the features selected by several state-of-the-art FS methods. The FS ranking methodology proposed in this study allows the users to identify the most discriminant features of the problem at hand. To the best of our knowledge, DANNP (publicly available at www.cbrc.kaust.edu.sa/dannp) is the only available and on-line accessible tool that provides multiple parallelized ANN pruning options. Datasets and DANNP code can be obtained at www.cbrc.kaust.edu.sa/dannp/data.php and https://doi.org/10.5281/zenodo.1001086.

scholarly journals Online Multilingual Hate Speech Detection: Experimenting with Hindi and English Social Media

2020 ◽  
Author(s):  
Neeraj Vashistha ◽  
Arkaitz Zubiaga
Keyword(s):  
Social Media ◽  
Hate Speech ◽  
Model Performance ◽  
Academic Community ◽  
Human Interaction ◽  
Superior Performance ◽  
Competitive Performance ◽  
Speech Detection ◽  
Improve Model ◽  
Use Of The Internet

The exponential increase in the use of the Internet and social media over the last two decades has changed human interaction. This has led to many positive outcomes, but at the same time it has brought risks and harms. While the volume of harmful content online, such as hate speech, is not manageable by humans, interest in the academic community to investigate automated means for hate speech detection has increased. In this study, we analyse six publicly available datasets by combining them into a single homogeneous dataset and classify them into three classes, abusive, hateful or neither. We create a baseline model and we improve model performance scores using various optimisation techniques. After attaining a competitive performance score, we create a tool which identifies and scores a page with effective metric in near-real time and uses the same as feedback to re-train our model. We prove the competitive performance of our multilingual model on two langauges, English and Hindi, leading to comparable or superior performance to most monolingual models.

scholarly journals Understanding covariate shift in model performance

F1000Research ◽  
2016 ◽  
Vol 5 ◽  
pp. 597 ◽  
Author(s):  
Georgia McGaughey ◽  
W. Patrick Walters ◽  
Brian Goldman
Keyword(s):  
Logistic Regression ◽  
Model Performance ◽  
Training Data ◽  
Obvious Advantage

Three (3) different methods (logistic regression, covariate shift and k-NN) were applied to five (5) internal datasets and one (1) external, publically available dataset where covariate shift existed. In all cases, k-NN’s performance was inferior to either logistic regression or covariate shift. Surprisingly, there was no obvious advantage for using covariate shift to reweight the training data in the examined datasets.

scholarly journals USING SEMANTICALLY PAIRED IMAGES TO IMPROVE DOMAIN ADAPTATION FOR THE SEMANTIC SEGMENTATION OF AERIAL IMAGES

2020 ◽  
Vol V-2-2020 ◽  
pp. 483-492
Author(s):  
D. Gritzner ◽  
J. Ostermann
Keyword(s):  
Time Window ◽  
Domain Adaptation ◽  
Geographical Area ◽  
Model Performance ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Training Data ◽  
Aerial Images ◽  
Target Domain ◽  
Training Examples

Abstract. Modern machine learning, especially deep learning, which is used in a variety of applications, requires a lot of labelled data for model training. Having an insufficient amount of training examples leads to models which do not generalize well to new input instances. This is a particular significant problem for tasks involving aerial images: often training data is only available for a limited geographical area and a narrow time window, thus leading to models which perform poorly in different regions, at different times of day, or during different seasons. Domain adaptation can mitigate this issue by using labelled source domain training examples and unlabeled target domain images to train a model which performs well on both domains. Modern adversarial domain adaptation approaches use unpaired data. We propose using pairs of semantically similar images, i.e., whose segmentations are accurate predictions of each other, for improved model performance. In this paper we show that, as an upper limit based on ground truth, using semantically paired aerial images during training almost always increases model performance with an average improvement of 4.2% accuracy and .036 mean intersection-over-union (mIoU). Using a practical estimate of semantic similarity, we still achieve improvements in more than half of all cases, with average improvements of 2.5% accuracy and .017 mIoU in those cases.

scholarly journals Evaluating the impact of grid cell properties in spatial discretization of groundwater model for a tropical karst catchment in Rote Island, Indonesia

2016 ◽  
Vol 48 (6) ◽  
pp. 1757-1772 ◽  
Author(s):  
Dua K. S. Y. Klaas ◽  
Monzur Alam Imteaz ◽  
Arul Arulrajah
Keyword(s):  
Estimation Method ◽  
Model Performance ◽  
Grid Cell ◽  
Specific Yield ◽  
Spatial Discretization ◽  
Observation Well ◽  
Improve Model ◽  
Karst Catchment ◽  
The Impact ◽  
Tropical Karst

Abstract To assess the effect of three grid cell properties (size, mean slope of the surface and distance between centre of grid and observation well) on groundwater models' performances, a tropical karst catchment characterized by monsoonal season in Rote Island, Indonesia was selected. Here, MODFLOW was used to develop models with five different spatial discretization schemes: 10 × 10 m, 20 × 20 m, 30 × 30 m, 40 × 40 m and 50 × 50 m. Using parameter estimation method, hydraulic conductivity and specific yield values over a selection of pilot points were estimated. The trends of the performances were calculated at each observation well in order to recommend the most appropriate location for observation well placement in terms of topographical characteristic. It is confirmed that the deterioration of model performance is mainly controlled by the increase of distance between well and centre of the cell, and the mean slope of the surface. Results reveal that model performance increases substantially for areas of low slope (<3%) and medium slope (3–10%) for a smaller grid cell size. Therefore, to improve model performance, it is recommended that the observations wells are placed in areas of low and medium slopes.

Sign in / Sign up

Export Citation Format

Share Document