Evaluation of conventional and deep learning based image harmonization methods in radiomics studies

2021 ◽  
Author(s):  
Florent Tixier ◽  
Vincent Jaouen ◽  
Clément Hognon ◽  
Olivier Gallinato ◽  
Thierry Colin ◽  
...  
Keyword(s):  
Prediction Models ◽  
Texture Features ◽  
Reference Image ◽  
P Value ◽  
Survival Prediction ◽  
Shape Features ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Histogram Matching ◽  
The Impact

Abstract Objective: To evaluate the impact of image harmonization on outcome prediction models using radiomics. Approach: 234 patients from the Brain Tumor Image Segmentation Benchmark (BRATS) dataset with T1 MRI were enrolled in this study. Images were harmonized through a reference image using histogram matching (HHM) and a generative adversarial network (GAN)-based method (HGAN). 88 radiomics features were extracted on HHM, HGAN and original (HNONE) images. Wilcoxon paired test was used to identify features significantly impacted by the harmonization protocol used. Radiomic prediction models were built using feature selection with the Least Absolute Shrinkage and Selection Operator (LASSO) and Kaplan-Meier analysis. Main results: More than 50% of the features (49/88) were statistically modified by the harmonization with HHM and 55 with HGAN (adjusted p-value < 0.05). The contribution of histogram and texture features selected by the LASSO, in comparison to shape features that were not impacted by harmonization, was higher in harmonized datasets (47% for Hnone, 62% for HHM and 71% for HGAN). Both image-based harmonization methods allowed to split patients into two groups with significantly different survival (p<0.05). With the HGAN images, we were also able to build and validate a model using only features impacted by the harmonization (median survivals of 189 vs. 437 days, p=0.006) Significance: Data harmonization in a multi-institutional cohort allows to recover the predictive value of some radiomics features that was lost due to differences in the image properties across centers. In terms of ability to build survival prediction models in the BRATS dataset, the loss of power from impacted histogram and heterogeneity features was compensated by the selection of additional shape features. The harmonization using a GAN-based approach outperformed the histogram matching technique, supporting the interest for the development of new advanced harmonization techniques for radiomic analysis purposes.

Underwater Acoustic Target Recognition Based on Generative Adversarial Network Data Augmentation

2021 ◽  
Vol 263 (2) ◽  
pp. 4558-4564
Author(s):  
Minghong Zhang ◽  
Xinwei Luo
Keyword(s):  
Data Augmentation ◽  
Target Recognition ◽  
Training Data ◽  
Small Samples ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Underwater Acoustic ◽  
Adversarial Network ◽  
Acoustic Target ◽  
The Impact

Underwater acoustic target recognition is an important aspect of underwater acoustic research. In recent years, machine learning has been developed continuously, which is widely and effectively applied in underwater acoustic target recognition. In order to acquire good recognition results and reduce the problem of overfitting, Adequate data sets are essential. However, underwater acoustic samples are relatively rare, which has a certain impact on recognition accuracy. In this paper, in addition of the traditional audio data augmentation method, a new method of data augmentation using generative adversarial network is proposed, which uses generator and discriminator to learn the characteristics of underwater acoustic samples, so as to generate reliable underwater acoustic signals to expand the training data set. The expanded data set is input into the deep neural network, and the transfer learning method is applied to further reduce the impact caused by small samples by fixing part of the pre-trained parameters. The experimental results show that the recognition result of this method is better than the general underwater acoustic recognition method, and the effectiveness of this method is verified.

scholarly journals Multi-omics Data Integration by Generative Adversarial Network

2021 ◽  
Author(s):  
Khandakar Tanvir Ahmed ◽  
Jiao Sun ◽  
Jeongsik Yong ◽  
Wei Zhang
Keyword(s):  
Large Scale ◽  
Synthetic Data ◽  
Interaction Network ◽  
Vital Role ◽  
The Cancer Genome Atlas ◽  
Survival Prediction ◽  
Omics Data ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cancer Outcome

Accurate disease phenotype prediction plays an important role in the treatment of heterogeneous diseases like cancer in the era of precision medicine. With the advent of high throughput technologies, more comprehensive multi-omics data is now available that can effectively link the genotype to phenotype. However, the interactive relation of multi-omics datasets makes it particularly challenging to incorporate different biological layers to discover the coherent biological signatures and predict phenotypic outcomes. In this study, we introduce omicsGAN, a generative adversarial network (GAN) model to integrate two omics data and their interaction network. The model captures information from the interaction network as well as the two omics datasets and fuse them to generate synthetic data with better predictive signals. Large-scale experiments on The Cancer Genome Atlas (TCGA) breast cancer and ovarian cancer datasets validate that (1) the model can effectively integrate two omics data (i.e., mRNA and microRNA expression data) and their interaction network (i.e., microRNA-mRNA interaction network). The synthetic omics data generated by the proposed model has a better performance on cancer outcome classification and patients survival prediction compared to original omics datasets. (2) The integrity of the interaction network plays a vital role in the generation of synthetic data with higher predictive quality. Using a random interaction network does not allow the framework to learn meaningful information from the omics datasets; therefore, results in synthetic data with weaker predictive signals.

Generative adversarial network and texture features applied to automatic glaucoma detection

2020 ◽  
Vol 90 ◽  
pp. 106165
Author(s):  
Tomaz Ribeiro Viana Bisneto ◽  
Antonio Oseas de Carvalho Filho ◽  
Deborah Maria Vieira Magalhães
Keyword(s):  
Texture Features ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Glaucoma Detection

scholarly journals A Reference-Guided Double Pipeline Face Image Completion Network

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1969
Author(s):  
Hongrui Liu ◽  
Shuoshi Li ◽  
Hongquan Wang ◽  
Xinshan Zhu
Keyword(s):  
Signal To Noise Ratio ◽  
Receptive Fields ◽  
Similarity Index ◽  
Face Image ◽  
Reference Image ◽  
Image Completion ◽  
Generative Adversarial Network ◽  
Identity Information ◽  
Adversarial Network ◽  
Reference Images

The existing face image completion approaches cannot be utilized to rationally complete damaged face images where their identity information is completely lost due to being obscured by center masks. Hence, in this paper, a reference-guided double-pipeline face image completion network (RG-DP-FICN) is designed within the framework of the generative adversarial network (GAN) completing the identity information of damaged images utilizing reference images with the same identity as damaged images. To reasonably integrate the identity information of reference images into completed images, the reference image is decoupled into identity features (e.g., the contour of eyes, eyebrows, nose) and pose features (e.g., the orientation of face and the positions of the facial features), and then the resulting identity features are fused with posture features of damaged images. Specifically, a lightweight identity predictor is used to extract the pose features; an identity extraction module is designed to compress and globally extract the identity features of the reference images, and an identity transfer module is proposed to effectively fuse identity and pose features by performing identity rendering on different receptive fields. Furthermore, quantitative and qualitative evaluations are conducted on a public dataset CelebA-HQ. Compared to the state-of-the-art methods, the evaluation metrics peak signal-to-noise ratio (PSNR), structure similarity index (SSIM) and L1 loss are improved by 2.22 dB, 0.033 and 0.79%, respectively. The results indicate that RG-DP-FICN can generate completed images with reasonable identity, with superior completion effect compared to existing completion approaches.

scholarly journals GENERATIVE ADVERSARIAL NETWORKS TO GENERALISE URBAN AREAS IN TOPOGRAPHIC MAPS

2021 ◽  
Vol XLIII-B4-2021 ◽  
pp. 15-22
Author(s):  
A. Courtial ◽  
G. Touya ◽  
X. Zhang
Keyword(s):  
Urban Areas ◽  
Topographic Maps ◽  
Generative Adversarial Networks ◽  
Topographic Map ◽  
Generative Adversarial Network ◽  
Inner Cities ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
The Impact

Abstract. This article presents how a generative adversarial network (GAN) can be employed to produce a generalised map that combines several cartographic themes in the dense context of urban areas. We use as input detailed buildings, roads, and rivers from topographic datasets produced by the French national mapping agency (IGN), and we expect as output of the GAN a legible map of these elements at a target scale of 1:50,000. This level of detail requires to reduce the amount of information while preserving patterns; covering dense inner cities block by a unique polygon is also necessary because these blocks cannot be represented with enlarged individual buildings. The target map has a style similar to the topographic map produced by IGN. This experiment succeeded in producing image tiles that look like legible maps. It also highlights the impact of data and representation choices on the quality of predicted images, and the challenge of learning geographic relationships.

scholarly journals Research of Single Image Rain Removal Algorithm Based on LBP-CGAN Rain Generation Method

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Ping Xue ◽  
Hai He
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Signal To Noise Ratio ◽  
Image Data ◽  
Texture Features ◽  
Generative Adversarial Network ◽  
Average Value ◽  
Adversarial Network ◽  
Negative Effect ◽  
Trained Neural Network

Rain has an undesirable negative effect on the clarity of the collected images. In situation where images are captured in rain, it can lead to a loss of information and disability in reflecting real images of the situation. Consequently, rain has become an obstacle in outdoor scientific research studies. The reason why images captured in rain are difficult to process is due to the indistinguishable interactions between the background features and rain textures. Since current image data are only processed with the CNN (convolutional neural network) model, a trained neural network to remove rain and obtain clear images, the resulted images are either insufficient or excessive from standard results. In order to achieve more ideal results of clearer images, series of additional methods are taken place. Firstly, the LBP (local binary pattern) method is used to extract the texture features of rain in the image. Then, the CGAN (conditional generative adversarial network) model is constructed to generate rain datasets according to the extracted rain characteristics. Finally, the existing clear images, rain datasets generated by CGAN, as well as the images with rain are used for convolution operation to remove rain from the images, and the average value of PSNR (peak signal to noise ratio) can reach 38.79 by using this algorithm. Moreover, a large number of experiments are done and have proven that this joint processing method is able to successfully and effectively generate clear images despite the rain.

scholarly journals A deep learning segmentation strategy that minimizes the amount of manually annotated images

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 256
Author(s):  
Thierry Pécot ◽  
Alexander Alekseyenko ◽  
Kristin Wallace
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Training Data ◽  
Artificial Data ◽  
Deep Convolutional Neural Networks ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Segmentation Strategy ◽  
Adversarial Network ◽  
The Impact

Deep learning has revolutionized the automatic processing of images. While deep convolutional neural networks have demonstrated astonishing segmentation results for many biological objects acquired with microscopy, this technology's good performance relies on large training datasets. In this paper, we present a strategy to minimize the amount of time spent in manually annotating images for segmentation. It involves using an efficient and open source annotation tool, the artificial increase of the training data set with data augmentation, the creation of an artificial data set with a conditional generative adversarial network and the combination of semantic and instance segmentations. We evaluate the impact of each of these approaches for the segmentation of nuclei in 2D widefield images of human precancerous polyp biopsies in order to define an optimal strategy.

scholarly journals An image-computable model of human visual shape similarity

2020 ◽  
Author(s):  
Yaniv Morgenstern ◽  
Frieder Hartmann ◽  
Filipp Schmidt ◽  
Henning Tiedemann ◽  
Eugen Prokott ◽  
...  
Keyword(s):  
Shape Similarity ◽  
Computable Model ◽  
Object Representations ◽  
Shape Features ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Wide Range ◽  
Different Shapes ◽  
Similarity Judgments ◽  
Visual Shape

AbstractShape is a defining feature of objects. Yet, no image-computable model accurately predicts how similar or different shapes appear to human observers. To address this, we developed a model (‘ShapeComp’), based on over 100 shape features (e.g., area, compactness, Fourier descriptors). When trained to capture the variance in a database of >25,000 animal silhouettes, ShapeComp predicts human shape similarity judgments almost perfectly (r2>0.99) without fitting any parameters to human data. To test the model, we created carefully selected arrays of complex novel shapes using a Generative Adversarial Network trained on the animal silhouettes, which we presented to observers in a wide range of tasks. Our findings show that human shape perception is inherently multidimensional and optimized for comparing natural shapes. ShapeComp outperforms conventional metrics, and can also be used to generate perceptually uniform stimulus sets, making it a powerful tool for investigating shape and object representations in the human brain.

scholarly journals Predicting sites of epitranscriptome modifications using unsupervised representation learning based on generative adversarial networks

2020 ◽  
Author(s):  
Sirajul Salekin ◽  
Milad Mostavi ◽  
Yu-Chiao Chiu ◽  
Yidong Chen ◽  
Jianqiu (Michelle) Zhang ◽  
...  
Keyword(s):  
Prediction Models ◽  
Representation Learning ◽  
Prediction Algorithm ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Sequence Motifs ◽  
Generative Adversarial Network ◽  
Robust Algorithms ◽  
Adversarial Network ◽  
Low Dimensional

ABSTRACTEpitranscriptome is an exciting area that studies different types of modifications in transcripts and the prediction of such modification sites from the transcript sequence is of significant interest. However, the scarcity of positive sites for most modifications imposes critical challenges for training robust algorithms. To circumvent this problem, we propose MR-GAN, a generative adversarial network (GAN) based model, which is trained in an unsupervised fashion on the entire pre-mRNA sequences to learn a low dimensional embedding of transcriptomic sequences. MR-GAN was then applied to extract embeddings of the sequences in a training dataset we created for eight epitranscriptome modifications, including m6A, m1A, m1G, m2G, m5C, m5U, 2′-O-Me, Pseudouridine (Ψ) and Dihydrouridine (D), of which the positive samples are very limited. Prediction models were trained based on the embeddings extracted by MR-GAN. We compared the prediction performance with the one-hot encoding of the training sequences and SRAMP, a state-of-the-art m6A site prediction algorithm and demonstrated that the learned embeddings outperform one-hot encoding by a significant margin for up to 15% improvement. Using MR-GAN, we also investigated the sequence motifs for each modification type and uncovered known motifs as well as new motifs not possible with sequences directly. The results demonstrated that transcriptome features extracted using unsupervised learning could lead to high precision for predicting multiple types of epitranscriptome modifications, even when the data size is small and extremely imbalanced.

Sign in / Sign up

Export Citation Format

Share Document