This study addresses challenges related to privacy issues in utilizing medical data, particularly the protection of personal information. To overcome this obstacle, the research focuses on data synthesis using real-world time-series generative adversarial networks (RTSGAN). A total of 53,005 data were synthesized using the dataset of 15,799 patients with colorectal cancer. The results of the quantitative evaluation of the synthetic data\'s quality are as follows: the Hellinger distance ranged from 0 to 0.25; the train on synthetic, test on real (TSTR) and train on real, test on synthetic (TRTS) results showed an average area under the curve of 0.99 and 0.98; a propensity mean squared error was 0.223. The synthetic and real data were similar in the qualitative methods including t-SNE and histogram analyses. The application of synthetic data in predicting five-year survival in colorectal cancer patients demonstrates comparable performance to models based on real data. This study employs distance to closest records and membership inference test to assess potential privacy exposure, revealing minimal risk. This study demonstrated that it is feasible to synthesize medical data, including time-series data, using the RTSGAN, and the synthetic data can be evaluated to accurately reflect the characteristics of real data through quantitative and qualitative methods as well as by utilizing real-world artificial intelligence models.

Human pluripotent stem cell (hPSC)-derived cardiac organoid is the most recent three-dimensional tissue structure that mimics the structure and functionality of the human heart and plays a pivotal role in modeling heart development and disease. The hPSC-derived cardiac organoids are commonly characterized by bright-field microscopic imaging for tracking daily organoid differentiation and morphology formation. Although the brightfield microscope provides essential information about hPSC-derived cardiac organoids, such as morphology, size, and general structure, it does not extend our understanding of cardiac organoids on cell type-specific distribution and structure. Then, fluorescence microscopic imaging is required to identify the specific cardiovascular cell types in the hPSC-derived cardiac organoids by fluorescence immunostaining fixed organoid samples or fluorescence reporter imaging of live organoids. Both approaches require extra steps of experiments and techniques and do not provide general information on hPSC-derived cardiac organoids from different batches of differentiation and characterization, which limits the biomedical applications of hPSC-derived cardiac organoids. This research addresses this limitation by proposing a comprehensive workflow for colorizing phase contrast images of cardiac organoids from brightfield microscopic imaging using conditional Generative Adversarial Networks (GANs) to provide cardiovascular cell type-specific information in hPSC-derived cardiac organoids. By infusing these phase contrast images with accurate fluorescence colorization, our approach aims to unlock the hidden wealth of cell type, structure, and further quantifications of fluorescence intensity and area, for better characterizing hPSC-derived cardiac organoids.

With the popularity of Internet applications, a large amount of Internet behavior log data is generated. Abnormal behaviors of corporate employees may lead to internet security issues and data leakage incidents. To ensure the safety of information systems, it is important to research on anomaly prediction of Internet behaviors. Due to the high cost of labeling big data manually, an unsupervised generative model-Anomaly Prediction of Internet behavior based on Generative Adversarial Networks (APIBGAN), which works only with a small amount of labeled data, is proposed to predict anomalies of Internet behaviors. After the input Internet behavior data is preprocessed by the proposed method, the data-generating generative adversarial network (DGGAN) in APIBGAN learns the distribution of real Internet behavior data by leveraging neural networks\' powerful feature extraction from the data to generate Internet behavior data with random noise. The APIBGAN utilizes these labeled generated data as a benchmark to complete the distance-based anomaly prediction. Three categories of Internet behavior sampling data from corporate employees are employed to train APIBGAN: (1) Online behavior data of an individual in a department. (2) Online behavior data of multiple employees in the same department. (3) Online behavior data of multiple employees in different departments. The prediction scores of the three categories of Internet behavior data are 87.23%, 85.13%, and 83.47%, respectively, and are above the highest score of 81.35% which is obtained by the comparison method based on Isolation Forests in the CCF Big Data & Computing Intelligence Contest (CCF-BDCI). The experimental results validate that APIBGAN predicts the outlier of Internet behaviors effectively through the GAN, which is composed of a simple three-layer fully connected neural networks (FNNs). We can use APIBGAN not only for anomaly prediction of Internet behaviors but also for anomaly prediction in many other applications, which have big data infeasible to label manually. Above all, APIBGAN has broad application prospects for anomaly prediction, and our work also provides valuable input for anomaly prediction-based GAN.

In order to analyze the influence of deep learning model on detecting denial-of-service (DoS) attacks, this article first examines the concepts and attack strategies of DoS assaults before looking into the present detection methodologies for DoS attacks. A distributed DoS attack detection system based on deep learning is established in response to the investigation\'s limitations. This system can quickly and accurately identify the traffic of distributed DoS attacks in the network that needs to be detected and then promptly send an alarm signal to the system. Then, a model called the Improved Conditional Wasserstein Generative Adversarial Network with Inverter (ICWGANInverter) is proposed in response to the characteristics of incomplete network traffic in DoS attacks. This model automatically learns the advanced abstract information of the original data and then employs the method of reconstruction error to identify the best classification label. It is then tested on the intrusion detection dataset NSL-KDD. The findings demonstrate that the mean square error of continuous feature reconstruction in the sub-datasets KDDTest+ and KDDTest-21 steadily increases as the noise factor increases. All of the receiver operating characteristic (ROC) curves are shown at the top of the diagonal, and the overall area under the ROC curve (AUC) values of the macro-average and micro-average are above 0.8, which demonstrates that the ICWGANInverter model has excellent detection performance in both single category attack detection and overall attack detection. This model has a greater detection accuracy than other models, reaching 87.79%. This demonstrates that the approach suggested in this article offers higher benefits for detecting DoS attacks.

License plate (LP) information is an important part of personal privacy, which is protected by law. However, in some publicly available transportation datasets, the LP areas in the images have not been processed. Other datasets have applied simple de-identification operations such as blurring and masking. Such crude operations will lead to a reduction in data utility. In this paper, we propose a method of LP de-identification based on a generative adversarial network (LPDi GAN) to transform an original image to a synthetic one with a generated LP. To maintain the original LP attributes, the background features are extracted from the background to generate LPs that are similar to the originals. The LP template and LP style are also fed into the network to obtain synthetic LPs with controllable characters and higher quality. The results show that LPDi GAN can perceive changes in environmental conditions and LP tilt angles, and control the LP characters through the LP templates. The perceptual similarity metric, Learned Perceptual Image Patch Similarity (LPIPS), reaches 0.25 while ensuring the effect of character recognition on de-identified images, demonstrating that LPDi GAN can achieve outstanding de-identification while preserving strong data utility.

In low-light environments, the amount of light captured by the camera sensor is reduced, resulting in lower image brightness. This makes it difficult to recognize or completely lose details in the image, which affects subsequent processing of low-light images. Low-light image enhancement methods can increase image brightness while better-restoring color and detail information. A generative adversarial network is proposed for low-quality image enhancement to improve the quality of low-light images. This network consists of a generative network and an adversarial network. In the generative network, a multi-scale feature extraction module, which consists of dilated convolutions, regular convolutions, max pooling, and average pooling, is designed. This module can extract low-light image features from multiple scales, thereby obtaining richer feature information. Secondly, an illumination attention module is designed to reduce the interference of redundant features. This module assigns greater weight to important illumination features, enabling the network to extract illumination features more effectively. Finally, an encoder-decoder generative network is designed. It uses the multi-scale feature extraction module, illumination attention module, and other conventional modules to enhance low-light images and improve quality. Regarding the adversarial network, a dual-discriminator structure is designed. This network has a global adversarial network and a local adversarial network. They determine if the input image is actual or generated from global and local features, enhancing the performance of the generator network. Additionally, an improved loss function is proposed by introducing color loss and perceptual loss into the conventional loss function. It can better measure the color loss between the generated image and a normally illuminated image, thus reducing color distortion during the enhancement process. The proposed method, along with other methods, is tested using both synthesized and real low-light images. Experimental results show that, compared to other methods, the images enhanced by the proposed method are closer to normally illuminated images for synthetic low-light images. For real low-light images, the images enhanced by the proposed method retain more details, are more apparent, and exhibit higher performance metrics. Overall, compared to other methods, the proposed method demonstrates better image enhancement capabilities for both synthetic and real low-light images.

OBJECTIVE: To generate perfusion parameter maps from Time-of-flight magnetic resonance angiography (TOF-MRA) images using artificial intelligence to provide an alternative to traditional perfusion imaging techniques.
METHODS: This retrospective study included a total of 272 patients with cerebrovascular diseases; 200 with acute stroke (from 2010 to 2018), and 72 with steno-occlusive disease (from 2011 to 2014). For each patient the TOF MRA image and the corresponding Dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) were retrieved from the datasets. The authors propose an adapted generative adversarial network (GAN) architecture, 3D pix2pix GAN, that generates common perfusion maps (CBF, CBV, MTT, TTP, Tmax) from TOF-MRA images. The performance was evaluated by the structural similarity index measure (SSIM). For a subset of 20 patients from the acute stroke dataset, the Dice coefficient was calculated to measure the overlap between the generated and real hypoperfused lesions with a time-to-maximum (Tmax) > 6 s.
RESULTS: The GAN model exhibited high visual overlap and performance for all perfusion maps in both datasets: acute stroke (mean SSIM 0.88-0.92, mean PSNR 28.48-30.89, mean MAE 0.02-0.04 and mean NRMSE 0.14-0.37) and steno-occlusive disease patients (mean SSIM 0.83-0.98, mean PSNR 23.62-38.21, mean MAE 0.01-0.05 and mean NRMSE 0.03-0.15). For the overlap analysis for lesions with Tmax>6 s, the median Dice coefficient was 0.49.
CONCLUSIONS: Our AI model can successfully generate perfusion parameter maps from TOF-MRA images, paving the way for a non-invasive alternative for assessing cerebral hemodynamics in cerebrovascular disease patients. This method could impact the stratification of patients with cerebrovascular diseases. Our results warrant more extensive refinement and validation of the method.

The infrastructure industry consumes natural resources and produces construction waste, which has a detrimental impact on the environment. To mitigate these adverse effects and reduce raw material consumption, waste materials can be repurposed to achieve sustainability. However, recycled materials deteriorate the intrinsic properties of concrete. A suitable ratio of natural resources and recycled aggregates can produce the desired compressive strength. Compiling sufficient data in civil engineering laboratories to make reliable conclusions is time-consuming and costly. Therefore, this research proposes a novel approach for predicting compressive strengths using limited data. The generative adversarial network was employed to generate synthetic data. Hybrid training, utilizing either conventional loss or heuristic loss, prevents the model from overfitting by adaptively adjusting the regularization term. Random noise from a multivariate normal distribution is embedded heuristically into the training samples to capture intricate data variations. Sensitivity analysis indicated that the size of recycled coarse aggregate and water are the most significant features, aligning with their correlations. Interestingly, superplasticizer, density of recycled coarse aggregate, and water absorption ratio of recycled coarse aggregate contributed significantly to predictions despite their low correlations. The propounded method outperforms random forest, support vector regression, artificial neural network, and adaptive boosting by scoring a mean squared error of 7.97, a root mean squared error of 2.82, a mean absolute error of 2.13, and a coefficient of determination of 0.96. These results suggest that the proposed technique can effectively contribute to sustainable construction practices by accurately predicting compressive strengths.

BACKGROUND: The blood-brain barrier (BBB) serves as a critical structural barrier and impedes the entry of most neurotherapeutic drugs into the brain. This poses substantial challenges for central nervous system (CNS) drug development, as there is a lack of efficient drug delivery technologies to overcome this obstacle. BBB penetrating peptides (BBBPs) hold promise in overcoming the BBB and facilitating the delivery of drug molecules to the brain. Therefore, precise identification of BBBPs has become a crucial step in CNS drug development. However, most computational methods are designed based on conventional models that inadequately capture the intricate interaction between BBBPs and the BBB. Moreover, the performance of these methods was further hampered by unbalanced datasets.
OBJECTIVE: This study addresses the problem of unbalanced datasets in BBBP prediction and proposes a powerful predictor for efficiently and accurately identifying BBBPs, as well as generating analogous BBBPs.
METHODS: A transformer-based deep learning model, DeepB3P, was proposed for predicting BBBP. The feedback generative adversarial network (FBGAN) model was employed to effectively generate analogous BBBPs, addressing data imbalance.
RESULTS: The FBGAN model possesses the ability to generate novel BBBP-like peptides, effectively mitigating the data imbalance in BBBP prediction. Extensive experiments on benchmarking datasets demonstrated that DeepB3P outperforms other BBBP prediction models by approximately 9.09%, 4.55% and 9.41% in terms of specificity, accuracy, and Matthew\'s correlation coefficient, respectively. For accelerating the progress in BBBP identification and CNS drug design, the proposed DeepB3P was implemented as a webserver, which is accessible at http://cbcb.cdutcm.edu.cn/deepb3p/.
CONCLUSIONS: The interpretable analyses provided by DeepB3P offer valuable insights and enhance downstream analyses for BBBP identification. Moreover, the BBBP-like peptides generated by FBGAN hold potential as candidates for CNS drug development.

With the development of digital pathology, deep learning is increasingly being applied to endometrial cell morphology analysis for cancer screening. And cytology images with different staining may degrade the performance of these analysis algorithms. To address the impact of staining patterns, many strategies have been proposed and hematoxylin and eosin (H&E) images have been transferred to other staining styles. However, none of the existing methods are able to generate realistic cytological images with preserved cellular layout, and many important clinical structural information is lost. To address the above issues, we propose a different staining transformation model, CytoGAN, which can quickly and realistically generate images with different staining styles. It includes a novel structure preservation module that preserves the cell structure well, even if the resolution or cell size between the source and target domains do not match. Meanwhile, a stain adaptive module is designed to help the model generate realistic and high-quality endometrial cytology images. We compared our model with ten state-of-the-art stain transformation models and evaluated by two pathologists. Furthermore, in the downstream endometrial cancer classification task, our algorithm improves the robustness of the classification model on multimodal datasets, with more than 20 % improvement in accuracy. We found that generating specified specific stains from existing H&E images improves the diagnosis of endometrial cancer. Our code will be available on github.