GENERATIVE ADVERSARIAL NETWORKS AS CREATIVE PARTNERS IN DIGITAL PAINTING AND ILLUSTRATION WORKFLOWS

All the recent developments in the use of Generative Adversarial Networks (GANs) for breast cancer imaging are aimed at improving diagnostic accuracy and treatment strategies. Breast cancer is among the types of cancers that affect women and cause mortality worldwide. Detection and diagnosis have become quite an issue to survival chances, but many recent applications like X-ray mammograms, ultrasound, or magnetic resonance imaging have their problems including unclear images and outlining tumors and less data to work with it. These challenges can be solved through GANs. A new framework for breast cancer imaging is presented that utilizes different GANs architectures in addressing important issues regarding breast cancer imaging. The significant steps of the presented framework include a type of GAN that is particularly beneficial for doing data augmentation is CycleGANs. It can synthesize mammograms without the need for paired images, enabling augmentation of the available data set. Small and unbalanced datasets raise many challenges that sometimes hinder image processing techniques on mammograms. The features in images with low resolutions can be observed more clearly and diagnostic features can be better visualized through improvement by Super Resolution GANs. Tumor segmentation is also defined by conditional GANs that produce very accurate and high-quality masks that outline the boundaries of tumors, allowing for effective treatment planning. This would mean identifying parameters that maximize the potential of GANs technologies, not only in breast cancer diagnosis and management but also in other areas.

Generative adversarial networks in dental imaging: a systematic review.

Designing game levels that appropriately match a player's skill level remains a fundamental challenge in procedural content generation, as mismatches in difficulty can lead to player boredom, frustration, and reduced engagement. While deep generative models enable automatic level synthesis at scale, the comparative effectiveness of different GAN architectures for skill-conditioned and personalized level generation remains insufficiently explored. In this work, we investigate the use of generative adversarial networks (GANs) for skill-conditioned procedural content generation by evaluating five architectures: U-Net GAN, StyleGAN, Deep Convolutional GAN (DCGAN), ResNet-GAN, and Spectral Normalization GAN (SN-GAN). Player behavior is clustered into discrete skill groups using Spectral Clustering, and the resulting labels are employed as conditioning signals for level generation. The selected architectures span different convolutional depths, normalization strategies, and regularization mechanisms, enabling a broad and systematic comparison. All models are evaluated using consistent quantitative metrics, including tile distribution entropy, diversity score, discriminator accuracy, generation speed, and pairwise Hamming distance. Quantitative analysis demonstrates that as player skill increases, generated levels exhibit fewer deaths and shorter completion times, while encouraging more complex interactions such as higher jumps and coin collection. Experimental results indicate that ResNet-based and U-Net-style GAN architectures achieve the most favorable balance between level diversity, playability, and training stability, corroborating both qualitative and quantitative assessments. The spectral clustering-based skill-conditioning approach successfully produced personalized levels aligned with each player's abilities, supporting adaptive procedural content generation across different skill groups.

Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish partnerships with specialized technology companies that deliver software services in order to monitor the networks and identify faults and respective solutions. A common barrier faced by these specialized companies is the lack of data to develop and test their products. This paper investigates the use of generative adversarial networks (GANs), which are state-of-the-art generative models, for generating synthetic telecommunication data related to Wi-Fi signal quality. We developed, trained, and compared two of the most used GAN architectures: the Vanilla GAN and the Wasserstein GAN (WGAN). Both models presented satisfactory results and were able to generate synthetic data similar to the real ones. In particular, the distribution of the synthetic data overlaps the distribution of the real data for all of the considered features. Moreover, the considered generative models can reproduce the same associations observed for the synthetic features. We chose the WGAN as the final model, but both models are suitable for addressing the problem at hand.

Generative Adversarial Networks (GANs) have been widely applied in various domains, including medical image analysis. GANs have been utilized in classification and segmentation tasks, aiding in the detection and diagnosis of diseases and disorders. However, medical image datasets often suffer from insufficiency and imbalanced class distributions. To overcome these limitations, researchers have employed GANs to generate augmented medical images, effectively expanding datasets and balancing class distributions. This review follows the PRISMA guidelines and systematically collects peer-reviewed articles on the development of GAN-based augmentation models. Automated searches were conducted on electronic databases such as IEEE, Scopus, Science Direct, and PubMed, along with forward and backward snowballing. Out of numerous articles, 52 relevant ones published between 2018 and February 2022 were identified. The gathered information was synthesized to determine common GAN architectures, medical image modalities, body organs of interest, augmentation tasks, and evaluation metrics employed to assess model performance. Results indicated that cGAN and DCGAN were the most popular GAN architectures in the reviewed studies. Medical image modalities such as MRI, CT, X-ray, and ultrasound, along with body organs like the brain, chest, breast, and lung, were frequently used. Furthermore, the developed models were evaluated, and potential challenges and future directions for GAN-based medical image augmentation were discussed. This review presents a comprehensive overview of the current state-of-the-art in GAN-based medical image augmentation and emphasizes the potential advantages and challenges associated with GAN utilization in this domain.

On the application of image augmentation for plant disease detection: A systematic literature review

Now a days creating cartoon characters having animated features is quite interesting and challenging. It takes a lot of effort to sketch animated features to bring it to live. It takes time and requires specialized knowledge. It takes a lot of effort to build a cartoon character from scratch, and the end result is usually an ungainly design with low polygon intensity. This process can be simplified with the use of generative adversarial network (GAN) architecture, GAN can be trained using a library of cartoon images. GANs are made up of two networks: a generating network and a discriminator network. GANs have a lot of potential in the field of image processing due to deep networks' proclivity to create realistic images and the competitiveness of the training approach. This strategy appears to be a powerful tool for improving fuzzy photos. The basic concept underlying GAN is that it consists of a discriminator and a generator, two neural networks that compete in a zero-sum game.

The purpose of the work is to analyze the features of generative adversarial networks. The object of research is the process of machine learning algorithmization. The subject of the research is mathematical methods used in the generation of semantically related text. This article explores the architecture and mathematical justification of such a type of generative models as generative adversarial networks. Generative adversarial networks are a powerful tool in the field of artificial intelligence, capable of generating realistic data, including photos, videos, sounds, etc. The architecture of generative competition defines its structure, the interaction of components and a general description of the learning process. Mathematical justification, in turn, includes a theoretical analysis of the principles, algorithms and functions underlying these networks. The article examines the general architecture of generative adversarial networks, examines each of its components (namely, the two main network models – generator and discriminator, their input and output data vectors) and its role in the operation of the algorithm. The author also defined the mathematical principles of generative adversarial networks, focusing on game theory and optimization methods (in particular, special attention is paid to minimax and maximin problems, zero-sum game, saddle points, Nash equilibrium) used in their study. The cost function and the process of deriving it using the Nash equilibrium in a zero-sum game for generative adversarial networks are described, and the learning algorithm using the method of stochastic gradient descent and the mini-batch approach in the form of a pseudocode, its iterations, is visualized network architecture. Finally, the conclusion that generative adversarial networks is an effective tool for creating realistic and believable data samples based on the use of elements of game theory is substantiated. Due to the high quality of generated data, generative adversarial networks can be used in various fields, including: cyber security, medicine, commerce, science, art, etc.

BackgroundResearch on the diagnosis of COVID-19 using lung images is limited by the scarcity of imaging data. Generative adversarial networks (GANs) are popular for synthesis and data augmentation. GANs have been explored for data augmentation to enhance the performance of artificial intelligence (AI) methods for the diagnosis of COVID-19 within lung computed tomography (CT) and X-ray images. However, the role of GANs in overcoming data scarcity for COVID-19 is not well understood.ObjectiveThis review presents a comprehensive study on the role of GANs in addressing the challenges related to COVID-19 data scarcity and diagnosis. It is the first review that summarizes different GAN methods and lung imaging data sets for COVID-19. It attempts to answer the questions related to applications of GANs, popular GAN architectures, frequently used image modalities, and the availability of source code.MethodsA search was conducted on 5 databases, namely PubMed, IEEEXplore, Association for Computing Machinery (ACM) Digital Library, Scopus, and Google Scholar. The search was conducted from October 11-13, 2021. The search was conducted using intervention keywords, such as “generative adversarial networks” and “GANs,” and application keywords, such as “COVID-19” and “coronavirus.” The review was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines for systematic and scoping reviews. Only those studies were included that reported GAN-based methods for analyzing chest X-ray images, chest CT images, and chest ultrasound images. Any studies that used deep learning methods but did not use GANs were excluded. No restrictions were imposed on the country of publication, study design, or outcomes. Only those studies that were in English and were published from 2020 to 2022 were included. No studies before 2020 were included.ResultsThis review included 57 full-text studies that reported the use of GANs for different applications in COVID-19 lung imaging data. Most of the studies (n=42, 74%) used GANs for data augmentation to enhance the performance of AI techniques for COVID-19 diagnosis. Other popular applications of GANs were segmentation of lungs and superresolution of lung images. The cycleGAN and the conditional GAN were the most commonly used architectures, used in 9 studies each. In addition, 29 (51%) studies used chest X-ray images, while 21 (37%) studies used CT images for the training of GANs. For the majority of the studies (n=47, 82%), the experiments were conducted and results were reported using publicly available data. A secondary evaluation of the results by radiologists/clinicians was reported by only 2 (4%) studies.ConclusionsStudies have shown that GANs have great potential to address the data scarcity challenge for lung images in COVID-19. Data synthesized with GANs have been helpful to improve the training of the convolutional neural network (CNN) models trained for the diagnosis of COVID-19. In addition, GANs have also contributed to enhancing the CNNs’ performance through the superresolution of the images and segmentation. This review also identified key limitations of the potential transformation of GAN-based methods in clinical applications.

Generative Adversarial Networks in Digital Histopathology: Current Applications, Limitations, Ethical Considerations, and Future Directions

Generative Adversarial Networks (GANs) are a thriving unsupervised machine learning technique that has led to significant advances in various fields such as computer vision, natural language processing, among others. However, GANs are known to be difficult to train and usually suffer from mode collapse and the discriminator winning problem. To interpret the empirical observations of GANs and design better ones, we deconstruct the study of GANs into three components and make the following contributions. Formulation: we propose a perturbation view of the population target of GANs. Building on this interpretation, we show that GANs can be connected to the robust statistics framework, and propose a novel GAN architecture, termed as Cascade GANs, to provably recover meaningful low-dimensional generator approximations when the real distribution is high-dimensional and corrupted by outliers. Generalization: given a population target of GANs, we design a systematic principle, projection under admissible distance, to design GANs to meet the population requirement using only finite samples. We implement our principle in three cases to achieve polynomial and sometimes near-optimal sample complexities: (1) learning an arbitrary generator under an arbitrary pseudonorm; (2) learning a Gaussian location family under total variation distance, where we utilize our principle to provide a new proof for the near-optimality of the Tukey median viewed as GANs; (3) learning a low-dimensional Gaussian approximation of a high-dimensional arbitrary distribution under Wasserstein distance. We demonstrate a fundamental trade-off in the approximation error and statistical error in GANs, and demonstrate how to apply our principle in practice with only empirical samples to predict how many samples would be sufficient for GANs in order not to suffer from the discriminator winning problem. Optimization: we demonstrate alternating gradient descent is provably not locally asymptotically stable in optimizing the GAN formulation of PCA. We found that the minimax duality gap being non-zero might be one of the causes, and propose a new GAN architecture whose duality gap is zero, where the value of the game is equal to the previous minimax value (not the maximin value). We prove the new GAN architecture is globally asymptotically stable in solving PCA under alternating gradient descent.

Recurrence Prediction in Ductal Carcinoma In Situ (DCIS) Patients Using Generative Adversarial Network (GAN) Augmented Deep Learning Model Background: DCIS patients have an excellent overall survival rate and over-treatment is always a cause for concern due to potential side-effects. Standard clinicopathological factors (age, growth pattern, tumor size, margin status and grade) have been shown to have limited value in predicting recurrence and segregation of high and low risk patients. Early and accurate recurrence prediction would facilitate a more aggressive treatment policy for high-risk patients (mastectomy or adjuvant radiation therapy), and simultaneously reduce over-treatment of low-risk patients. In this work, we have developed a deep learning (DL) classification framework that predicts recurrence in DCIS patients from Tissue microarrays (TMAs) hematoxylin and eosin (H&E) images using a generative adversarial network (GAN) augmented deep learning (DL) classification model. A GAN is a class of DL models, in which two adversarial neural networks, generator and discriminator contest among each other to generate high quality images. During the adversarial training process, the generator learns to synthesize realistic images similar to those in the training set while the discriminator learns to distinguish between real and generated images. In recent years, high quality medical images have been generated by GAN models. To the best of our knowledge, this is the first time a GAN model has been used to generate H&E images to train a DL classification model to predict recurrence in DCIS patients. Materials and methods: The cohort was comprised of 68 DCIS patients, aged between 35-89 years, lesion size of 5-90 mm, with a mix of low (15%), intermediate (35%) and 50% high grade cases. Patients were treated with mastectomy and/or a combination of lumpectomy, radiation and hormone therapy. TMAs were constructed from 2mm cores (1-3 cores per patient) in consultation with a breast pathologist to create hematoxylin and eosin (H&E) images for further analysis. The cohort was split into independent training (n=50 patients, 10 with recurrences at 5years) and validation groups (n=18 patients, 6 with recurrences at 5years). TMA (H&E) images were divided into smaller image patches of size 256x256 to train a GAN to generate image patches. A DL classification network (Resnet-Inception v2) was trained using TMA image patches and aggressive image patches generated by GAN to predict recurrence. The ability to generate synthetic image patches of aggressive lesions permitted training of a large DL classification network and predict recurrence in DCIS patients. Importantly, manual annotation was not necessary for the process. Results: The DL classification model trained with both TMA and GAN generated image patches predicted recurrence with an AUC of 0.87, sensitivity of 0.83 and specificity of 0.91 in the validation dataset. The DL classification model trained with image patches from TMAs only predicted recurrence with an AUC of 0.81. Conclusions: The use of a GAN model to generate H&E images circumvents the needs for a large cohort and accurate labor-intensive manual annotation of histopathological images, which is often required for training a large DL classification model. The use of GAN generated aggressive image patches during training significantly improves recurrence prediction accuracy of the DL classification model. Validation in independent larger cohorts is ongoing, and if successful, could provide a novel assay for risk prediction that does not waste precious tissue samples. Citation Format: Ghose Soumya, Yesim Gokmen-Polar, Sanghee Cho, Elizabeth McDonough, Cynthia Davis, Jhimli Mitra, Zhanpan Zhang, Fiona Ginty, Sunil Badve. Recurrence Prediction in Ductal Carcinoma In Situ (DCIS) Patients from Tissue Microarrays (TMAs) [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P6-04-10.

We propose using generative adversarial networks (GANs) for the classification of micro-Doppler signatures measured by the radar. Despite Deep Convolutional Neural Networks (DCNNs) having been used extensively in radar image classification in recent years, their performance could not be fully implemented in the radar field because of the deficiency of the training data set. This is a key issue because of the extremely high labor and monetary costs involved in obtaining radar images. As such, attempts have been made to resolve this issue via the production of radar data by simulation or by the use of transfer learning. In this letter, we propose the use of GANs to produce a large number of micro-Doppler signatures with which to increase the training data set. Once the GANs are trained, a large amount of similar data, with the same distribution as the original data, can be easily generated. The generated fake micro-Doppler images can then be included in the DCNN training process. The proposed method is applied to classifying human activities measured by the Doppler radar. For each human activity, corresponding GANs that generate micro-Doppler signatures for a particular activity are constructed. Using the micro-Doppler signatures produced by the GANs along with the original data, the DCNN is trained. According to the results, the use of GANs improves the accuracy of classification. Moreover, the use of GANs was found to be more effective than the use of transfer learning.

Generative Adversarial Networks (GANs) are considered to be disruptive models of computational creativity, especially in music style transfer and learning. This study examines how GAN architecture may be incorporated in translating pieces of music between different stylistic domains without compromising their time and harmonious integrity. The conventional approaches including Autoencoders, RNNs, and Variational Autoencoders (VAEs) have shown a low success rate in the fine-grained representations of music which has led to the adoption of GANs due to their better generative realism. The suggested model uses Conditional GANs and CycleGANs, which allows supervised and unpaired learning with various musical data. The data normalization and preprocessing is done using feature extraction methods that are Mel-frequency cepstral coefficient (MFCCs), chroma features, and spectral contrast. The architecture focuses on balanced loss optimization between the discriminator and the generator and makes sure that there is convergence stability and audio fidelity. The results of experimental analysis show significant enhancement of melody preservation, timbre adaptation, and rhythmic consistency of genres. Moreover, the paper describes the use in AI-assisted composition, intelligent sound design, and interactive music education systems. These results highlight the value of GANs as creative processes, as well as educational instruments, enabling real-time modification of the style and music specifically synthesized to the user. The study, with its developed methodology of learning musical style using GAN and cross-domain adaptation, adds to an area of investigation of machine learning, cognition of music and digital creativity, which is being recently reshaped.

The paper explores an important area of artificial intelligence — Generative Adversarial Networks (GANs), which are used to create high-quality artificial data samples. GANs have undergone significant development and application in various sectors, including the processing of graphical data. The report focuses on the practical use of GANs and their architecture. It discusses the fundamental principles of GAN operation, highlights the advantages and disadvantages, including issues with training, vanishing gradients, and convergence oscillations, and describes measures to overcome these problems. It also examines current research in the field of GANs and their applications in various domains, including cybersecurity, medicine, forensics, and computer vision. Practical results from the report's authors regarding their own GAN experiments, optimization, and architecture improvements are presented. The research aims to analyze the architectural features of GANs to enhance their training process