scholarly journals Medical Augmentation (Med-Aug) for Optimal Data Augmentation in Medical Deep Learning Networks

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7018
Author(s):  
Justin Lo ◽  
Jillian Cardinell ◽  
Alejo Costanzo ◽  
Dafna Sussman
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Data Augmentation ◽  
Search Algorithm ◽  
High Dimensional ◽  
Learning Networks ◽  
Imaging Data ◽  
Covariance Matrix Adaptation ◽  
Using Data ◽  
Adaptation Evolution

Deep learning (DL) algorithms have become an increasingly popular choice for image classification and segmentation tasks; however, their range of applications can be limited. Their limitation stems from them requiring ample data to achieve high performance and adequate generalizability. In the case of clinical imaging data, images are not always available in large quantities. This issue can be alleviated by using data augmentation (DA) techniques. The choice of DA is important because poor selection can possibly hinder the performance of a DL algorithm. We propose a DA policy search algorithm that offers an extended set of transformations that accommodate the variations in biomedical imaging datasets. The algorithm makes use of the efficient and high-dimensional optimizer Bi-Population Covariance Matrix Adaptation Evolution Strategy (BIPOP-CMA-ES) and returns an optimal DA policy based on any input imaging dataset and a DL algorithm. Our proposed algorithm, Medical Augmentation (Med-Aug), can be implemented by other researchers in related medical DL applications to improve their model’s performance. Furthermore, we present our found optimal DA policies for a variety of medical datasets and popular segmentation networks for other researchers to use in related tasks.

scholarly journals Deep Learning of COVID-19 Chest X-Rays: New Models or Fine Tuning?

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Data Augmentation ◽  
Dominant Role ◽  
Care Center ◽  
Characteristic Curve ◽  
Fine Tuning ◽  
Urgent Care ◽  
X Rays ◽  
Training Time

Chest X-rays have been found to be very promising for assessing COVID-19 patients, especially for resolving emergency-department and urgent-care-center overcapacity. Deep-learning (DL) methods in artificial intelligence (AI) play a dominant role as high-performance classifiers in the detection of the disease using chest X-rays. While many new DL models have been being developed for this purpose, this study aimed to investigate the fine tuning of pretrained convolutional neural networks (CNNs) for the classification of COVID-19 using chest X-rays. Three pretrained CNNs, which are AlexNet, GoogleNet, and SqueezeNet, were selected and fine-tuned without data augmentation to carry out 2-class and 3-class classification tasks using 3 public chest X-ray databases. In comparison with other recently developed DL models, the 3 pretrained CNNs achieved very high classification results in terms of accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver-operating-characteristic curve. AlexNet, GoogleNet, and SqueezeNet require the least training time among pretrained DL models, but with suitable selection of training parameters, excellent classification results can be achieved without data augmentation by these networks. The findings contribute to the urgent need for harnessing the pandemic by facilitating the deployment of AI tools that are fully automated and readily available in the public domain for rapid implementation.

A Similarity-Based Object Classification Using Deep Neural Networks

2019 ◽  
pp. 197-219
Author(s):  
Parvathi R. ◽  
Pattabiraman V.
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Search Algorithm ◽  
Random Projection ◽  
Learning Networks ◽  
Learning Models ◽  
External Conditions ◽  
And Training

This chapter proposes a hybrid method for classification of the objects based on deep neural network and a similarity-based search algorithm. The objects are pre-processed with external conditions. After pre-processing and training different deep learning networks with the object dataset, the authors compare the results to find the best model to improve the accuracy of the results based on the features of object images extracted from the feature vector layer of a neural network. RPFOREST (random projection forest) model is used to predict the approximate nearest images. ResNet50, InceptionV3, InceptionV4, and DenseNet169 models are trained with this dataset. A proposal for adaptive finetuning of the deep learning models by determining the number of layers required for finetuning with the help of the RPForest model is given, and this experiment is conducted using the Xception model.

scholarly journals Mirrored Orthogonal Sampling for Covariance Matrix Adaptation Evolution Strategies

2019 ◽  
Vol 27 (4) ◽  
pp. 699-725 ◽  
Author(s):  
Hao Wang ◽  
Michael Emmerich ◽  
Thomas Bäck
Keyword(s):  
Convergence Rate ◽  
Covariance Matrix ◽  
Sampling Technique ◽  
Black Box ◽  
Evolution Strategies ◽  
High Dimensional ◽  
Major Purpose ◽  
Search Spaces ◽  
Covariance Matrix Adaptation ◽  
Adaptation Evolution

Generating more evenly distributed samples in high dimensional search spaces is the major purpose of the recently proposed mirrored sampling technique for evolution strategies. The diversity of the mutation samples is enlarged and the convergence rate is therefore improved by the mirrored sampling. Motivated by the mirrored sampling technique, this article introduces a new derandomized sampling technique called mirrored orthogonal sampling. The performance of this new technique is both theoretically analyzed and empirically studied on the sphere function. In particular, the mirrored orthogonal sampling technique is applied to the well-known Covariance Matrix Adaptation Evolution Strategy (CMA-ES). The resulting algorithm is experimentally tested on the well-known Black-Box Optimization Benchmark (BBOB). By comparing the results from the benchmark, mirrored orthogonal sampling is found to outperform both the standard CMA-ES and its variant using mirrored sampling.

scholarly journals Image editing-based data augmentation for illumination-insensitive background subtraction

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Dimitrios Sakkos ◽  
Edmond S. L. Ho ◽  
Hubert P. H. Shum ◽  
Garry Elvin
Keyword(s):  
Deep Learning ◽  
Pilot Study ◽  
Background Subtraction ◽  
Data Augmentation ◽  
Point Of View ◽  
Content Type ◽  
Illumination Changes ◽  
Image Appearance ◽  
Using Data ◽  
Limited Training Samples

PurposeA core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In our pilot study published in, Sakkos:SKIMA 2019, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly but also features semantic transformations of illumination which enhance the generalisation of the model.Design/methodology/approachIn our pilot study published in SKIMA 2019, the proposed framework successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask generated randomly. In this paper, we further enhance the data augmentation framework by proposing new variations in image appearance both locally and globally.FindingsExperimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place.Originality/valueSuch data augmentation allows us to effectively train an illumination-invariant deep learning model for BGS. We further propose a post-processing method that removes noise from the output binary map of segmentation, resulting in a cleaner, more accurate segmentation map that can generalise to multiple scenes of different conditions. We show that it is possible to train deep learning models even with very limited training samples. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation

scholarly journals Structured report data can be used to develop deep learning algorithms: a proof of concept in ankle radiographs

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Daniel Pinto dos Santos ◽  
Sebastian Brodehl ◽  
Bettina Baeßler ◽  
Gordon Arnhold ◽  
Thomas Dratsch ◽  
...  
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Learning Algorithms ◽  
Area Under The Curve ◽  
Learning Networks ◽  
Report Data ◽  
Structured Reports ◽  
Picture Archiving And Communication ◽  
Using Data

Abstract Background Data used for training of deep learning networks usually needs large amounts of accurate labels. These labels are usually extracted from reports using natural language processing or by time-consuming manual review. The aim of this study was therefore to develop and evaluate a workflow for using data from structured reports as labels to be used in a deep learning application. Materials and methods We included all plain anteriorposterior radiographs of the ankle for which structured reports were available. A workflow was designed and implemented where a script was used to automatically retrieve, convert, and anonymize the respective radiographs of cases where fractures were either present or absent from the institution’s picture archiving and communication system (PACS). These images were then used to retrain a pretrained deep convolutional neural network. Finally, performance was evaluated on a set of previously unseen radiographs. Results Once implemented and configured, completion of the whole workflow took under 1 h. A total of 157 structured reports were retrieved from the reporting platform. For all structured reports, corresponding radiographs were successfully retrieved from the PACS and fed into the training process. On an unseen validation subset, the model showed a satisfactory performance with an area under the curve of 0.850 (95% CI 0.634–1.000) for detection of fractures. Conclusion We demonstrate that data obtained from structured reports written in clinical routine can be used to successfully train deep learning algorithms. This highlights the potential role of structured reporting for the future of radiology, especially in the context of deep learning.

Sign in / Sign up

Export Citation Format

Share Document