Deep generative denoising networks enhance quality and accuracy of gated cardiac PET data.

BACKGROUND: Cardiac positron emission tomography (PET) can visualize and quantify the molecular and physiological pathways of cardiac function. However, cardiac and respiratory motion can introduce blurring that reduces PET image quality and quantitative accuracy. Dual cardiac- and respiratory-gated PET reconstruction can mitigate motion artifacts but increases noise as only a subset of data are used for each time frame of the cardiac cycle. AIM: The objective of this study is to create a zero-shot image denoising framework using a conditional generative adversarial networks (cGANs) for improving image quality and quantitative accuracy in non-gated and dual-gated cardiac PET images. METHODS: Our study included retrospective list-mode data from 40 patients who underwent an 18F-fluorodeoxyglucose (18F-FDG) cardiac PET study. We initially trained and evaluated a 3D cGAN-known as Pix2Pix-on simulated non-gated low-count PET data paired with corresponding full-count target data, and then deployed the model on an unseen test set acquired on the same PET/CT system including both non-gated and dual-gated PET data. RESULTS: Quantitative analysis demonstrated that the 3D Pix2Pix network architecture achieved significantly (p value<0.05) enhanced image quality and accuracy in both non-gated and gated cardiac PET images. At 5%, 10%, and 15% preserved count statistics, the model increased peak signal-to-noise ratio (PSNR) by 33.7%, 21.2%, and 15.5%, structural similarity index (SSIM) by 7.1%, 3.3%, and 2.2%, and reduced mean absolute error (MAE) by 61.4%, 54.3%, and 49.7%, respectively. When tested on dual-gated PET data, the model consistently reduced noise, irrespective of cardiac/respiratory motion phases, while maintaining image resolution and accuracy. Significant improvements were observed across all gates, including a 34.7% increase in PSNR, a 7.8% improvement in SSIM, and a 60.3% reduction in MAE. CONCLUSION: The findings of this study indicate that dual-gated cardiac PET images, which often have post-reconstruction artifacts potentially affecting diagnostic performance, can be effectively improved using a generative pre-trained denoising network.

FetalBrainAwareNet: Bridging GANs with anatomical insight for fetal ultrasound brain plane synthesis.

Over the past decade, deep-learning (DL) algorithms have become a promising tool to aid clinicians in identifying fetal head standard planes (FHSPs) during ultrasound (US) examination. However, the adoption of these algorithms in clinical settings is still hindered by the lack of large annotated datasets. To overcome this barrier, we introduce FetalBrainAwareNet, an innovative framework designed to synthesize anatomically accurate images of FHSPs. FetalBrainAwareNet introduces a cutting-edge approach that utilizes class activation maps as a prior in its conditional adversarial training process. This approach fosters the presence of the specific anatomical landmarks in the synthesized images. Additionally, we investigate specialized regularization terms within the adversarial training loss function to control the morphology of the fetal skull and foster the differentiation between the standard planes, ensuring that the synthetic images faithfully represent real US scans in both structure and overall appearance. The versatility of our FetalBrainAwareNet framework is highlighted by its ability to generate high-quality images of three predominant FHSPs using a singular, integrated framework. Quantitative (Fréchet inception distance of 88.52) and qualitative (t-SNE) results suggest that our framework generates US images with greater variability compared to state-of-the-art methods. By using the synthetic images generated with our framework, we increase the accuracy of FHSP classifiers by 3.2% compared to training the same classifiers solely with real acquisitions. These achievements suggest that using our synthetic images to increase the training set could provide benefits to enhance the performance of DL algorithms for FHSPs classification that could be integrated in real clinical scenarios.

Data-driven crop growth simulation on time-varying generated images using multi-conditional generative adversarial networks.

BACKGROUND: Image-based crop growth modeling can substantially contribute to precision agriculture by revealing spatial crop development over time, which allows an early and location-specific estimation of relevant future plant traits, such as leaf area or biomass. A prerequisite for realistic and sharp crop image generation is the integration of multiple growth-influencing conditions in a model, such as an image of an initial growth stage, the associated growth time, and further information about the field treatment. While image-based models provide more flexibility for crop growth modeling than process-based models, there is still a significant research gap in the comprehensive integration of various growth-influencing conditions. Further exploration and investigation are needed to address this gap. METHODS: We present a two-stage framework consisting first of an image generation model and second of a growth estimation model, independently trained. The image generation model is a conditional Wasserstein generative adversarial network (CWGAN). In the generator of this model, conditional batch normalization (CBN) is used to integrate conditions of different types along with the input image. This allows the model to generate time-varying artificial images dependent on multiple influencing factors. These images are used by the second part of the framework for plant phenotyping by deriving plant-specific traits and comparing them with those of non-artificial (real) reference images. In addition, image quality is evaluated using multi-scale structural similarity (MS-SSIM), learned perceptual image patch similarity (LPIPS), and Fréchet inception distance (FID). During inference, the framework allows image generation for any combination of conditions used in training; we call this generation data-driven crop growth simulation. RESULTS: Experiments are performed on three datasets of different complexity. These datasets include the laboratory plant Arabidopsis thaliana (Arabidopsis) and crops grown under real field conditions, namely cauliflower (GrowliFlower) and crop mixtures consisting of faba bean and spring wheat (MixedCrop). In all cases, the framework allows realistic, sharp image generations with a slight loss of quality from short-term to long-term predictions. For MixedCrop grown under varying treatments (different cultivars, sowing densities), the results show that adding these treatment information increases the generation quality and phenotyping accuracy measured by the estimated biomass. Simulations of varying growth-influencing conditions performed with the trained framework provide valuable insights into how such factors relate to crop appearances, which is particularly useful in complex, less explored crop mixture systems. Further results show that adding process-based simulated biomass as a condition increases the accuracy of the derived phenotypic traits from the predicted images. This demonstrates the potential of our framework to serve as an interface between a data-driven and a process-based crop growth model. CONCLUSION: The realistic generation and simulation  of future plant appearances is adequately feasible by multi-conditional CWGAN. The presented framework complements process-based models and overcomes their limitations, such as the reliance on assumptions and the low exact field-localization specificity, by realistic visualizations of the spatial crop development that directly lead to a high explainability of the model predictions.

Enhancing Building Point Cloud Reconstruction from RGB UAV Data with Machine-Learning-Based Image Translation.

The performance of three-dimensional (3D) point cloud reconstruction is affected by dynamic features such as vegetation. Vegetation can be detected by near-infrared (NIR)-based indices; however, the sensors providing multispectral data are resource intensive. To address this issue, this study proposes a two-stage framework to firstly improve the performance of the 3D point cloud generation of buildings with a two-view SfM algorithm, and secondly, reduce noise caused by vegetation. The proposed framework can also overcome the lack of near-infrared data when identifying vegetation areas for reducing interferences in the SfM process. The first stage includes cross-sensor training, model selection and the evaluation of image-to-image RGB to color infrared (CIR) translation with Generative Adversarial Networks (GANs). The second stage includes feature detection with multiple feature detector operators, feature removal with respect to the NDVI-based vegetation classification, masking, matching, pose estimation and triangulation to generate sparse 3D point clouds. The materials utilized in both stages are a publicly available RGB-NIR dataset, and satellite and UAV imagery. The experimental results indicate that the cross-sensor and category-wise validation achieves an accuracy of 0.9466 and 0.9024, with a kappa coefficient of 0.8932 and 0.9110, respectively. The histogram-based evaluation demonstrates that the predicted NIR band is consistent with the original NIR data of the satellite test dataset. Finally, the test on the UAV RGB and artificially generated NIR with a segmentation-driven two-view SfM proves that the proposed framework can effectively translate RGB to CIR for NDVI calculation. Further, the artificially generated NDVI is able to segment and classify vegetation. As a result, the generated point cloud is less noisy, and the 3D model is enhanced.

Medical image synthesis via conditional GANs: Application to segmenting brain tumours.

Accurate brain tumour segmentation is critical for tasks such as surgical planning, diagnosis, and analysis, with magnetic resonance imaging (MRI) being the preferred modality due to its excellent visualisation of brain tissues. However, the wide intensity range of voxel values in MR scans often results in significant overlap between the density distributions of different tumour tissues, leading to reduced contrast and segmentation accuracy. This paper introduces a novel framework based on conditional generative adversarial networks (cGANs) aimed at enhancing the contrast of tumour subregions for both voxel-wise and region-wise segmentation approaches. We present two models: Enhancement and Segmentation GAN (ESGAN), which combines classifier loss with adversarial loss to predict central labels of input patches, and Enhancement GAN (EnhGAN), which generates high-contrast synthetic images with reduced inter-class overlap. These synthetic images are then fused with corresponding modalities to emphasise meaningful tissues while suppressing weaker ones. We also introduce a novel generator that adaptively calibrates voxel values within input patches, leveraging fully convolutional networks. Both models employ a multi-scale Markovian network as a GAN discriminator to capture local patch statistics and estimate the distribution of MR images in complex contexts. Experimental results on publicly available MR brain tumour datasets demonstrate the competitive accuracy of our models compared to current brain tumour segmentation techniques.

ProGleason-GAN: Conditional progressive growing GAN for prostatic cancer Gleason grade patch synthesis.

BACKGROUND AND OBJECTIVE: Prostate cancer is one of the most common diseases affecting men. The main diagnostic and prognostic reference tool is the Gleason scoring system. An expert pathologist assigns a Gleason grade to a sample of prostate tissue. As this process is very time-consuming, some artificial intelligence applications were developed to automatize it. The training process is often confronted with insufficient and unbalanced databases which affect the generalisability of the models. Therefore, the aim of this work is to develop a generative deep learning model capable of synthesising patches of any selected Gleason grade to perform data augmentation on unbalanced data and test the improvement of classification models. METHODOLOGY: The methodology proposed in this work consists of a conditional Progressive Growing GAN (ProGleason-GAN) capable of synthesising prostate histopathological tissue patches by selecting the desired Gleason Grade cancer pattern in the synthetic sample. The conditional Gleason Grade information is introduced into the model through the embedding layers, so there is no need to add a term to the Wasserstein loss function. We used minibatch standard deviation and pixel normalisation to improve the performance and stability of the training process. RESULTS: The reality assessment of the synthetic samples was performed with the Frechet Inception Distance (FID). We obtained an FID metric of 88.85 for non-cancerous patterns, 81.86 for GG3, 49.32 for GG4 and 108.69 for GG5 after post-processing stain normalisation. In addition, a group of expert pathologists was selected to perform an external validation of the proposed framework. Finally, the application of our proposed framework improved the classification results in SICAPv2 dataset, proving its effectiveness as a data augmentation method. CONCLUSIONS: ProGleason-GAN approach combined with a stain normalisation post-processing provides state-of-the-art results regarding Frechet's Inception Distance. This model can synthesise samples of non-cancerous patterns, GG3, GG4 or GG5. The inclusion of conditional information about the Gleason grade during the training process allows the model to select the cancerous pattern in a synthetic sample. The proposed framework can be used as a data augmentation method.

Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images.

Background: Ultra-Wide-Field (UWF) fundus imaging is an essential diagnostic tool for identifying ophthalmologic diseases, as it captures detailed retinal structures within a wider field of view (FOV). However, the presence of eyelashes along the edge of the eyelids can cast shadows and obscure the view of fundus imaging, which hinders reliable interpretation and subsequent screening of fundus diseases. Despite its limitations, there are currently no effective methods or datasets available for removing eyelash artifacts from UWF fundus images. This research aims to develop an effective approach for eyelash artifact removal and thus improve the visual quality of UWF fundus images for accurate analysis and diagnosis. Methods: To address this issue, we first constructed two UWF fundus datasets: the paired synthetic eyelashes (PSE) dataset and the unpaired real eyelashes (uPRE) dataset. Then we proposed a deep learning architecture called Joint Conditional Generative Adversarial Networks (JcGAN) to remove eyelash artifacts from UWF fundus images. JcGAN employs a shared generator with two discriminators for joint learning of both real and synthetic eyelash artifacts. Furthermore, we designed a background refinement module that refines background information and is trained with the generator in an end-to-end manner. Results: Experimental results on both PSE and uPRE datasets demonstrate the superiority of the proposed JcGAN over several state-of-the-art deep learning approaches. Compared with the best existing method, JcGAN improves PSNR and SSIM by 4.82% and 0.23%, respectively. In addition, we also verified that eyelash artifact removal via JcGAN could significantly improve vessel segmentation performance in UWF fundus images. Assessment via vessel segmentation illustrates that the sensitivity, Dice coefficient and area under curve (AUC) of ResU-Net have respectively increased by 3.64%, 1.54%, and 1.43% after eyelash artifact removal using JcGAN. Conclusion: The proposed JcGAN effectively removes eyelash artifacts in UWF images, resulting in improved visibility of retinal vessels. Our method can facilitate better processing and analysis of retinal vessels and has the potential to improve diagnostic outcomes.

Enhanced dataset synthesis using conditional generative adversarial networks.

Biomedical data acquisition, and reaching sufficient samples of participants are difficult and time ans effort consuming processes. On the other hand, the success rates of computer aided diagnosis (CAD) algorithms are sample and feature space depended. In this paper, conditional generative adversarial network (CGAN) based enhanced feature generation is proposed to synthesize large sample datasets having higher class separability. Twenty five percent of five medical datasets are used to train CGAN, and the synthetic datasets with any sample size are evaluated and compared to originals. Thus, new datasets can be generated with the help of the CGAN model and lower sample collection. It helps physicians decreasing sample collection processes, and it increases accuracy rates of the CAD systems using generated enhanced data with enhanced feature vectors. The synthesized datasets are classified using nearest neighbor, radial basis function support vector machine and artificial neural network to analyze the effectiveness of the proposed CGAN model.

LAC-GAN: Lesion attention conditional GAN for Ultra-widefield image synthesis.

Automatic detection of retinal diseases based on deep learning technology and Ultra-widefield (UWF) images plays an important role in clinical practices in recent years. However, due to small lesions and limited data samples, it is not easy to train a detection-accurate model with strong generalization ability. In this paper, we propose a lesion attention conditional generative adversarial network (LAC-GAN) to synthesize retinal images with realistic lesion details to improve the training of the disease detection model. Specifically, the generator takes the vessel mask and class label as the conditional inputs, and processes the random Gaussian noise by a series of residual block to generate the synthetic images. To focus on pathological information, we propose a lesion feature attention mechanism based on random forest (RF) method, which constructs its reverse activation network to activate the lesion features. For discriminator, a weight-sharing multi-discriminator is designed to improve the performance of model by affine transformations. Experimental results on multi-center UWF image datasets demonstrate that the proposed method can generate retinal images with reasonable details, which helps to enhance the performance of the disease detection model.

Modeling families of particle distributions with conditional GAN for Monte Carlo SPECT simulations.

Objective.We propose a method to model families of distributions of particles exiting a phantom with a conditional generative adversarial network (condGAN) during Monte Carlo simulation of single photon emission computed tomography imaging devices.Approach.The proposed condGAN is trained on a low statistics dataset containing the energy, the time, the position and the direction of exiting particles. In addition, it also contains a vector of conditions composed of four dimensions: the initial energy and the position of emitted particles within the phantom (a total of 12 dimensions). The information related to the gammas absorbed within the phantom is also added in the dataset. At the end of the training process, one component of the condGAN, the generator (G), is obtained.Main results.Particles with specific energies and positions of emission within the phantom can then be generated withGto replace the tracking of particle within the phantom, allowing reduced computation time compared to conventional Monte Carlo simulation.Significance.The condGAN generator is trained only once for a given phantom but can generate particles from various activity source distributions.

DualG-GAN, a Dual-channel Generator based Generative Adversarial Network for text-to-face synthesis.

Text-to-image synthesis is a fundamental and challenging task in computer vision, which aims to synthesize realistic images from given descriptions. Recently, text-to-image synthesis methods have achieved great improvements in the quality of synthesized images. However, very few works have explored its application in the scenario of face synthesis, which is of great potentials in face-related applications and the public safety domain. On the other side, the faces generated by existing methods are generally of poor quality and have low consistency to the given text. To tackle this issue, in this paper, we build a novel end-to-end dual-channel generator based generative adversarial network, named DualG-GAN, to improve the quality of the generated images and the consistency to the text description. In DualG-GAN, to improve the consistency between the synthesized image and the input description, a dual-channel generator block is introduced, and a novel loss is designed to improve the similarity between the generated image and the ground-truth in three different semantic levels. Extensive experiments demonstrate that DualG-GAN achieves state-of-the-art results on SCU-Text2face dataset. To further verify the performance of DualG-GAN, we compare it with the current optimal methods on text-to-image synthesis tasks, where quantitative and qualitative results show that the proposed DualG-GAN achieves optimal performance in both Fréchet inception distance (FID) and R-precision metrics. As only a few works are focusing on text-to-face synthesis, this work can be seen as a baseline for future research.

Retrospective motion correction for preclinical/clinical magnetic resonance imaging based on a conditional generative adversarial network with entropy loss.

Multishot scan magnetic resonance imaging (MRI) acquisition is inherently sensitive to motion, and motion artifact reduction is essential for improving the image quality in MRI. This work proposes and validates a new end-to-end motion-correction method for the multishot sequence that incorporates a conditional generative adversarial network with minimum entropy (cGANME) of MR images. The cGANME contains an encoder-decoder generator to obtain motion-corrected images and a PatchGAN discriminator to classify the image as either real (motion-free) or fake (motion-corrected). The entropy of the images is set as one loss item in the cGAN's loss as the entropy increases monotonically with the motion artifacts. An ablation experiment of the different weights of entropy loss was performed to evaluate the function of entropy loss. The preclinical dataset was acquired with a fast spin echo pulse sequence on a 7.0-T scanner. After the simulation, we had 10,080/2880/1440 slices for training, testing, and validating, respectively. The clinical dataset was downloaded from the Human Connection Project website, and 11,300/3500/2000 slices were used for training, testing, and validating after simulation, respectively. Extensive experiments for different motion patterns, motion levels, and protocol parameters demonstrate that cGANME outperforms traditional and some state-of-the-art, deep learning-based methods. In addition, we tested cGANME on in vivo awake rats and mitigated the motion artifacts, indicating that the model has some generalizability.

CTTGAN: Traffic Data Synthesizing Scheme Based on Conditional GAN.

Most machine learning algorithms only have a good recognition rate on balanced datasets. However, in the field of malicious traffic identification, benign traffic on the network is far greater than malicious traffic, and the network traffic dataset is imbalanced, which makes the algorithm have a low identification rate for small categories of malicious traffic samples. This paper presents a traffic sample synthesizing model named Conditional Tabular Traffic Generative Adversarial Network (CTTGAN), which uses a Conditional Tabular Generative Adversarial Network (CTGAN) algorithm to expand the small category traffic samples and balance the dataset in order to improve the malicious traffic identification rate. The CTTGAN model expands and recognizes feature data, which meets the requirements of a machine learning algorithm for training and prediction data. The contributions of this paper are as follows: first, the small category samples are expanded and the traffic dataset is balanced; second, the storage cost and computational complexity are reduced compared to models using image data; third, discrete variables and continuous variables in traffic feature data are processed at the same time, and the data distribution is described well. The experimental results show that the recognition rate of the expanded samples is more than 0.99 in MLP, KNN and SVM algorithms. In addition, the recognition rate of the proposed CTTGAN model is better than the oversampling and undersampling schemes.

Deep Learning-Based Prediction of the 3D Postorthodontic Facial Changes.

With the increase of the adult orthodontic population, there is a need for an accurate and evidence-based prediction of the posttreatment face in 3 dimensions (3D). The objectives of this study are 1) to develop a 3D postorthodontic face prediction method based on a deep learning network using the patient-specific factors and orthodontic treatment conditions and 2) to validate the accuracy and clinical usability of the proposed method. Paired sets (n = 268) of pretreatment (T1) and posttreatment (T2) cone-beam computed tomography (CBCT) of adult patients were trained with a conditional generative adversarial network to generate 3D posttreatment facial data based on the patient's gender, age, and the changes of upper (ΔU1) and lower incisor position (ΔL1) as input. The accuracy was calculated with prediction error and mean absolute distances between real T2 (T2) and predicted T2 (PT2) near 6 perioral landmark regions, as well as percentage of prediction error less than 2 mm using test sets (n = 44). For qualitative evaluation, an online survey was conducted with experienced orthodontists as panels (n = 56). Overall, PT2 indicated similar 3D changes to the T2 face, with the most apparent changes simulated in the perioral regions. The mean prediction error was 1.2 ± 1.01 mm with 80.8% accuracy. More than 50% of the experienced orthodontists were unable to distinguish between real and predicted images. In this study, we proposed a valid 3D postorthodontic face prediction method by applying a deep learning algorithm trained with CBCT data sets.

[Sparse-view Cone-beam Breast CT Reconstruction via cGAN Constrained by Image Edges].

Clinical applications of cone-beam breast CT(CBBCT) are hindered by relatively higher radiation dose and longer scan time. This study proposes sparse-view CBBCT, i.e. with a small number of projections, to overcome the above bottlenecks. A deep learning method - conditional generative adversarial network constrained by image edges (ECGAN) - is proposed to suppress artifacts on sparse-view CBBCT images reconstructed by filtered backprojection (FBP). The discriminator of the ECGAN is the combination of patchGAN and LSGAN for preserving high frequency information, with a modified U-net as the generator. To further preserve subtle structures and micro calcifications which are particularly important for breast cancer screening and diagnosis, edge images of CBBCT are added to both the generator and the discriminator to guide the learning. The proposed algorithm has been evaluated on 20 clinical raw datasets of CBBCT. ECGAN substantially improves the image qualities of sparse-view CBBCT, with a performance superior to those of total variation (TV) based iterative reconstruction and FBPConvNet based post-processing. On one CBBCT case with the projection number reduced from 300 to 100, ECGAN enhances peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) on FBP reconstruction from 24.26 and 0.812 to 37.78 and 0.963, respectively. These results indicate that ECGAN successfully reduces radiation dose and scan time of CBBCT by 1/3 with only small image degradations.

A Comprehensive Evaluation of Generating a Mobile Traffic Data Scheme without a Coarse-Grained Process Using CSR-GAN.

Large-scale mobile traffic data analysis is important for efficiently planning mobile base station deployment plans and public transportation plans. However, the storage costs of preserving mobile traffic data are becoming much higher as traffic increases enormously population density of target areas. To solve this problem, schemes to generate a large amount of mobile traffic data have been proposed. In the state-of-the-art of the schemes, generative adversarial networks (GANs) are used to transform a large amount of traffic data into a coarse-grained representation and generate the original traffic data from the coarse-grained data. However, the scheme still involves a storage cost, since the coarse-grained data must be preserved in order to generate the original traffic data. In this paper, we propose a scheme to generate the mobile traffic data by using conditional-super-resolution GAN (CSR-GAN) without requiring a coarse-grained process. Through experiments using two real traffic data, we assessed the accuracy and the amount of storage data needed. The results show that the proposed scheme, CSR-GAN, can reduce the storage cost by up to 45% compared to the traditional scheme, and can generate the original mobile traffic data with 94% accuracy. We also conducted experiments by changing the architecture of CSR-GAN, and the results show an optimal relationship between the amount of traffic data and the model size.

Efficient link prediction in the protein-protein interaction network using topological information in a generative adversarial network machine learning model.

BACKGROUND: The investigation of possible interactions between two proteins in intracellular signaling is an expensive and laborious procedure in the wet-lab, therefore, several in silico approaches have been implemented to narrow down the candidates for future experimental validations. Reformulating the problem in the field of network theory, the set of proteins can be represented as the nodes of a network, while the interactions between them as the edges. The resulting protein-protein interaction (PPI) network enables the use of link prediction techniques in order to discover new probable connections. Therefore, here we aimed to offer a novel approach to the link prediction task in PPI networks, utilizing a generative machine learning model. RESULTS: We created a tool that consists of two modules, the data processing framework and the machine learning model. As data processing, we used a modified breadth-first search algorithm to traverse the network and extract induced subgraphs, which served as image-like input data for our model. As machine learning, an image-to-image translation inspired conditional generative adversarial network (cGAN) model utilizing Wasserstein distance-based loss improved with gradient penalty was used, taking the combined representation from the data processing as input, and training the generator to predict the probable unknown edges in the provided induced subgraphs. Our link prediction tool was evaluated on the protein-protein interaction networks of five different species from the STRING database by calculating the area under the receiver operating characteristic, the precision-recall curves and the normalized discounted cumulative gain (AUROC, AUPRC, NDCG, respectively). Test runs yielded the averaged results of AUROC = 0.915, AUPRC = 0.176 and NDCG = 0.763 on all investigated species. CONCLUSION: We developed a software for the purpose of link prediction in PPI networks utilizing machine learning. The evaluation of our software serves as the first demonstration that a cGAN model, conditioned on raw topological features of the PPI network, is an applicable solution for the PPI prediction problem without requiring often unavailable molecular node attributes. The corresponding scripts are available at https://github.com/semmelweis-pharmacology/ppi_pred .

Sparse-view Cone-beam Breast CT Reconstruction via cGAN Constrained by Image Edges / 中国医疗器械杂志

Clinical applications of cone-beam breast CT(CBBCT) are hindered by relatively higher radiation dose and longer scan time. This study proposes sparse-view CBBCT, i.e. with a small number of projections, to overcome the above bottlenecks. A deep learning method - conditional generative adversarial network constrained by image edges (ECGAN) - is proposed to suppress artifacts on sparse-view CBBCT images reconstructed by filtered backprojection (FBP). The discriminator of the ECGAN is the combination of patchGAN and LSGAN for preserving high frequency information, with a modified U-net as the generator. To further preserve subtle structures and micro calcifications which are particularly important for breast cancer screening and diagnosis, edge images of CBBCT are added to both the generator and the discriminator to guide the learning. The proposed algorithm has been evaluated on 20 clinical raw datasets of CBBCT. ECGAN substantially improves the image qualities of sparse-view CBBCT, with a performance superior to those of total variation (TV) based iterative reconstruction and FBPConvNet based post-processing. On one CBBCT case with the projection number reduced from 300 to 100, ECGAN enhances peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) on FBP reconstruction from 24.26 and 0.812 to 37.78 and 0.963, respectively. These results indicate that ECGAN successfully reduces radiation dose and scan time of CBBCT by 1/3 with only small image degradations.

Emulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks.

Weak gravitational lensing mass maps play a crucial role in understanding the evolution of structures in the Universe and our ability to constrain cosmological models. The prediction of these mass maps is based on expensive N-body simulations, which can create a computational bottleneck for cosmological analyses. Simulation-based emulators of map summary statistics, such as the matter power spectrum and its covariance, are starting to play increasingly important role, as the analytical predictions are expected to reach their precision limits for upcoming experiments. Creating an emulator of the cosmological mass maps themselves, rather than their summary statistics, is a more challenging task. Modern deep generative models, such as Generative Adversarial Networks (GAN), have demonstrated their potential to achieve this goal. Most existing GAN approaches produce simulations for a fixed value of the cosmological parameters, which limits their practical applicability. We propose a novel conditional GAN model that is able to generate mass maps for any pair of matter density Ω m and matter clustering strength σ 8, parameters which have the largest impact on the evolution of structures in the Universe, for a given source galaxy redshift distribution n(z). Our results show that our conditional GAN can interpolate efficiently within the space of simulated cosmologies, and generate maps anywhere inside this space with good visual quality high statistical accuracy. We perform an extensive quantitative comparison of the N-body and GAN -generated maps using a range of metrics: the pixel histograms, peak counts, power spectra, bispectra, Minkowski functionals, correlation matrices of the power spectra, the Multi-Scale Structural Similarity Index (MS-SSIM) and our equivalent of the Fréchet Inception Distance. We find a very good agreement on these metrics, with typical differences are <5% at the center of the simulation grid, and slightly worse for cosmologies at the grid edges. The agreement for the bispectrum is slightly worse, on the <20% level. This contribution is a step toward building emulators of mass maps directly, capturing both the cosmological signal and its variability. We make the code and the data publicly available.

Multi-Channel Generative Framework and Supervised Learning for Anomaly Detection in Surveillance Videos.

Recently, most state-of-the-art anomaly detection methods are based on apparent motion and appearance reconstruction networks and use error estimation between generated and real information as detection features. These approaches achieve promising results by only using normal samples for training steps. In this paper, our contributions are two-fold. On the one hand, we propose a flexible multi-channel framework to generate multi-type frame-level features. On the other hand, we study how it is possible to improve the detection performance by supervised learning. The multi-channel framework is based on four Conditional GANs (CGANs) taking various type of appearance and motion information as input and producing prediction information as output. These CGANs provide a better feature space to represent the distinction between normal and abnormal events. Then, the difference between those generative and ground-truth information is encoded by Peak Signal-to-Noise Ratio (PSNR). We propose to classify those features in a classical supervised scenario by building a small training set with some abnormal samples of the original test set of the dataset. The binary Support Vector Machine (SVM) is applied for frame-level anomaly detection. Finally, we use Mask R-CNN as detector to perform object-centric anomaly localization. Our solution is largely evaluated on Avenue, Ped1, Ped2, and ShanghaiTech datasets. Our experiment results demonstrate that PSNR features combined with supervised SVM are better than error maps computed by previous methods. We achieve state-of-the-art performance for frame-level AUC on Ped1 and ShanghaiTech. Especially, for the most challenging Shanghaitech dataset, a supervised training model outperforms up to 9% the state-of-the-art an unsupervised strategy.