Handling Imbalance in Javanese Manuscript Character Dataset using Skeleton-based Balancing Generative Adversarial Networks

Megavoltage computed tomography (MVCT) is an essential imaging modality for verifying patient positioning in helical tomotherapy. However, its clinical application in daily anatomical monitoring and adaptive radiotherapy is hindered by inherent image artifacts and poor soft-tissue contrast. This issue is particularly pronounced in pelvic radiotherapy, where the intra- and interfraction anatomical variations necessitate high-quality image guidance to ensure precise dose delivery. We developed a deep-learning-based framework for MVCT enhancement to improve anatomicalvisualizationand facilitate accurate adaptive treatment planning for cervical cancer. This study analyzed a retrospective cohort of 170 patients with cervical cancer who underwent helical tomotherapy. The proposed deep-learning-based algorithm employed a generative adversarial network (GAN) that integrated deformable convolution and a self-attention mechanism (SADC-EGAN) to improve MVCT image quality. Comparative analyses were conducted against representative baseline methods, including U-Net, Attention U-Net, U-Net++, Swin-UNet, CycleGAN, and Pix2Pix. Model performance was assessed using quantitative metrics, including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Fréchet inception distance (FID). The synthetic computed tomography (sCT) images generated by the proposed SADC-EGAN method demonstrated superior Hounsfield unit (HU) accuracy and structural similarity comparedto the original MVCT. Specifically, the MAE between the sCT and kilovoltage computed tomography (kVCT) was reduced to 36.32±6.69 HU, compared with 56.72±9.09 HU for MVCT. In terms of image quality, the sCT images exhibited notable enhancements over MVCT images, with higher PSNR (32.54±2.31 vs. 29.40±1.56dB), improved SSIM (0.93±0.01vs. 0.89±0.02), and substantially lower FID (66.68±22.31vs. 153.52±28.77). The proposed SADC-EGAN framework, integrating deformable convolutions and self-attention, effectively generated high-quality kVCT-like images from MVCT, improving both HU accuracy and image quality. This approachhas clinical potential to enable online adaptive helical tomotherapy for cervical cancer.

Generative Artificial Intelligence (AI) has shown significant promise in healthcare, particularly in medical imaging, by improving data augmentation, diagnostic accuracy, and model generalization. However, existing models such as Generative Adversarial Networks (GANs) and Diffusion Models face challenges in balancing image realism, structural fidelity, and computational efficiency. GANs often suffer from mode collapse and limited diversity, while diffusion models, though high in fidelity, are computationally intensive and slow to sample. To address these limitations, we propose a Hybrid GAN–Diffusion approach that synergistically combines the strengths of both architectures. Our pipeline first pretrains a StyleGAN2-ADA model to capture coarse-to-fine radiographic structure efficiently, then refines the generated samples using a Denoising Diffusion Probabilistic Model (DDPM) to enhance anatomical plausibility and diversity. This sequential design fuses the sharpness and speed of GANs with the coverage and robustness of diffusion models, yielding synthetic images of superior quality and clinical utility. We evaluate the framework on the Kaggle Chest X-Ray Pneumonia dataset for training and perform external validation on NIH ChestXray14 to assess cross-dataset generalization. Experimental results demonstrate that the hybrid model achieves an ROC-AUC of 0.984 in-distribution and 0.892 on the external dataset, outperforming classical augmentation, GAN-only, and diffusion-only baselines. The synthetic data quality is further validated by a simulated Fréchet Inception Distance (FID) of 16.2, indicating high realism and diversity. The proposed method establishes a new state-of-the-art in medical image augmentation, demonstrating that hybrid generative pipelines can effectively overcome data scarcity while improving model robustness and generalization.

Microplastic particle ingestion or inhalation by humans is a problem of growing concern. Unfortunately, current research methods that use machine learning to understand their potential harms are obstructed by a lack of available data. Deep learning techniques in particular are challenged by such domains where only small or imbalanced data sets are available. Overcoming this challenge often involves oversampling underrepresented classes or augmenting the existing data to improve model performance. This paper proposes GANsemble: a two-module framework connecting data augmentation with conditional generative adversarial networks (cGANs) to generate class-conditioned synthetic data. First, the data chooser module automates augmentation strategy selection by searching for the best data augmentation strategy. Next, the cGAN module uses this strategy to train a cGAN for generating enhanced synthetic data. We experiment with the GANsemble framework on a small and imbalanced microplastics data set. A Microplastic-cGAN (MPcGAN) algorithm is introduced, and baselines for synthetic microplastics (SYMP) data are established in terms of Fréchet Inception Distance (FID) and Inception Scores (IS). We also provide a synthetic microplastics filter (SYMP-Filter) algorithm to increase the quality of generated SYMP. Additionally, we show the best amount of oversampling with augmentation to fix class imbalance in small microplastics data sets. To our knowledge, this study is the first application of generative AI to synthetically create microplastics data.

Generative adversarial networks (GANs) with gaming abilities have been widely applied in image generation. However, gamistic generators and discriminators may reduce the robustness of the obtained GANs in image generation under varying scenes. Enhancing the relation of hierarchical information in a generation network and enlarging differences of different network architectures can facilitate more structural information to improve the generation effect for image generation. In this paper, we propose an enhanced GAN via improving a generator for image generation (EIGGAN). EIGGAN applies a spatial attention to a generator to extract salient information to enhance the truthfulness of the generated images. Taking into relation the context account, parallel residual operations are fused into a generation network to extract more structural information from the different layers. Finally, a mixed loss function in a GAN is exploited to make a tradeoff between speed and accuracy to generate more realistic images. Experimental results show that the proposed method is superior to popular methods, i.e., Wasserstein GAN with gradient penalty (WGAN-GP) in terms of many indexes, i.e., Frechet Inception Distance, Learned Perceptual Image Patch Similarity, Multi-Scale Structural Similarity Index Measure, Kernel Inception Distance, Number of Statistically-Different Bins, Inception Score and some visual images for image generation.

BackgroundMalignant melanoma (MM) is the most aggressive skin cancer, requiring early diagnosis for better outcomes. While deep learning models have shown promise in dermatological image analysis, their performance is constrained by limited training data. Generative Adversarial Networks (GANs) offer a solution by generating synthetic images for data augmentation. However, assessing their clinical reliability remains difficult as automated metrics may not fully capture visual realism or clinical usability.The ObjectiveThis study presents a comprehensive framework for creating high-quality synthetic dermatoscopic pictures of MM lesions, as well as a holistic validation methodology that uses quantitative metrics and qualitative dermatologist assessment to provide a full clinical evaluation of the generated images. Three GAN architectures (DCGAN, StyleGAN2, and StyleGAN3-t) are explored. Lesions on the face, palms, and soles are excluded due to their unique dermoscopic patterns.Materials and MethodsA dataset of 1,774 dermatoscopic body MM images was used to train the models, assessed with Fréchet Inception Distance (FID), Kernel Inception Distance (KID), precision, and recall. Afterwards, a panel of 17 dermatologists with different levels of expertise assessed image quality using a 7-point Likert scale, with accuracy, sensitivity, specificity, and inter-rater agreement analysed.ResultsStyleGAN2 achieved the best image fidelity (FID: 18.89, KID: 0.0025), while StyleGAN3-t demonstrated stable but slower convergence. Both StyleGAN models outperformed DCGAN in diversity and fidelity. The validation study showed that StyleGAN2-generated images were often indistinguishable from real ones, reflected in low specificity and accuracy values among evaluators.ConclusionsThe study highlights the effectiveness of GANs in generating high-quality synthetic images, proposing a validation framework that integrates expert assessments with state-of-the-art quantitative metrics. This approach advances standardisation in GAN evaluation, ensuring synthetic images are clinically relevant for dermatological AI applications.

Abstract. We propose a stochastic framework for wildfire spread prediction using deep generative diffusion models with ensemble sampling. In contrast to traditional deterministic approaches that struggle to capture the inherent uncertainty and variability of wildfire dynamics, our method generates probabilistic forecasts by sampling multiple plausible future scenarios conditioned on the same initial state. As a proof-of-concept, the model is trained on synthetic wildfire data generated by a probabilistic cellular automata simulator conditioned on canopy cover, vegetation density, and terrain slope for two real fires, namely the Chimney Fire in 2016 and the Ferguson Fire in 2018, both in California. To assess predictive performance and uncertainty representation under an identical neural network architecture, we compare a conventional supervised regression training paradigm against a conditional diffusion framework that employs ensemble sampling, and evaluate both approaches on independent ensemble test datasets. Across independent ensemble test sets, the diffusion surrogate consistently outperforms the deterministic baseline. It delivers lower errors in standard accuracy metrics such as mean squared error (MSE), exhibits higher spatial coherence as reflected by improved structural similarity index measure (SSIM) values, and generates samples of superior distributional quality according to the Fréchet inception distance (FID). Moreover, the diffusion-based model shows stronger probabilistic capability, as evidenced by higher scores in the hit rate (HR) metric, which we introduce as an uncertainty-aware verification measure. These results demonstrate that diffusion-based ensemble modelling provides a more flexible and effective approach for wildfire forecasting and, by capturing the distributional characteristics of future fire states, supports the generation of fire susceptibility maps that convey probabilistic risk information useful for assessment and operational planning in fire-prone environments.

We present a novel approach to developing robust AI in light of context-varying situations. This methodology harnesses a suite of indicators to establish a Robustness Assurance Quotient (RAQ) tailored to address environmentally noisy data while maintaining parity with current standards, namely the Fréchet Inception Distance (FID) metric. While the FID metric successfully indicates the closeness of highly structured data, it is less successful measuring closeness of inherently noisy data. A score for ascertaining the closeness between Generative Adversarial Network (GAN)-simulated, inherently noisy radiofrequnecy data and original GAN signals are proposed by focusing on the subject and context of the image. The RAQ demonstrably improved our GAN’s generated content similarity to original waterfall images of radiofrequency signal. We believe our Robustness Assurance Quotient can have a profound impact on improving the robustness of various AI models, in diverse application domains ultimately reducing the negative impact of noisy data.

Accurate diagnosis of melanoma using hematoxylin and eosin (H&E)-stained histological images is often challenged by the scarcity and imbalance of biomedical datasets, limiting the performance of deep learning models. This study investigates the impact of synthetic image generation, via generative adversarial networks (GAN), on training automatic classifiers based on the ResNet-18 architecture. Two experimental setups were designed: one using only real images and another combining real images with synthetic ones of the melanocytic nevus class to balance the dataset. Models were trained and evaluated at resolutions up to 1024 × 1024 pixels, employing standard classification metrics and the Fréchet Inception Distance (FID) to assess the quality of the generated images. The results suggest that although mixed models do not consistently outperform those trained exclusively on real data, they achieve competitive performance, particularly in terms of specificity and reduction in false negatives. This study supports the use of synthetic data as a complementary tool in scenarios where the acquisition of new samples is limited and lays the groundwork for future research in conditional generation and synthesis of malignant samples. In our best-performing model (1024 × 1024 px, 50 epochs, mixed dataset), we achieved an accuracy of 96.00%, a specificity of 97.00%, and a reduction in false negatives from 80 to 75 cases compared with real-only training. These results highlight the potential of synthetic augmentation to improve clinically relevant outcomes, particularly in reducing missed melanoma diagnoses.

Chinese watercolor painting, celebrated for its delicate brushwork, smooth tonal gradients, and expressive ink diffusion, embodies a rich historical and cultural heritage. This article introduces a hierarchical multi-scale generative framework for producing high-quality traditional watercolor paintings. The model is trained on a curated collection of high-resolution artworks from public museum archives and employs a pyramid of patch-based generative adversarial networks (GANs), each dedicated to learning visual features at a specific spatial scale. Residual learning across scales enables progressive refinement from coarse composition to intricate brushstroke details. Quantitative evaluation using Fréchet Inception Distance (FID) and Diversity Score shows significant performance gains over other well-known GAN-based models. Qualitative results further demonstrate the framework’s ability to emulate the stylistic nuances of classical Chinese art, capturing brushwork precision, ink diffusion effects, and compositional harmony, while preserving both global structure and local texture.

Generative Adversarial Networks (GANs) are a major advancement in generative modeling, surpassing traditional machine learning models in tasks such as image generation, super-resolution, and image-to-text translation. A GAN consists of two neural networks: a Generator (G), which creates data from noise or a latent vector, and a Discriminator (D), which determines whether the data is real or generated. These networks train competitively, improving each other iteratively to produce increasingly realistic outputs. However, GANs face challenges like mode collapse, unstable training, and convergence issues, leading to the adoption of strategies such as instance normalization and enhanced loss functions. Future research can focus on improving stability, developing novel loss functions, and applying GANs in unsupervised learning. Performance metrics like Inception Score, Fréchet Inception Distance (FID), and Structural Similarity Index (SSIM) are essential for evaluating and comparing GAN architectures. Additionally, ethical concerns, including the misuse of GANs for deepfakes and synthetic data, underscore the importance of transparency, accountability, and ethical standards in research and deployment. This review provides an accessible introduction to GANs for novice researchers, along with a detailed analysis of their limitations, applications, and future prospects, offering valuable insights and direction for advancing this field.

Generative adversarial networks (GANs), which can generate and transform data, have been attracting attention. However, the model must be lightweight and fast when applied in the field. As for the ternarization of GAN, (TernaryGAN,) which restricts the value of the weights to {−1, 0, +1} during forwarding propagation of the generator, has already been proposed. In this paper, we investigated by experiment how ternary generator and/or discriminator affects the training of GANs. To make not only generator ternary, but also discriminator, we propose the DGR (Decomposition with Gradient Retained) method, which can change discriminator's input images to binary. We trained GANs for the cases where the generator and the discriminator are ternarized, and for the case where only one of them is ternarized, and measured the degree of image degradation using the FID (Fréchet inception distance) score. Only the ternarized generator is showed the lowest accuracy degradation, implying that GANs contain some parts that are not suitable for ternarization. We found the useful insight that when reducing the weight of GAN, the generator can be compressed relatively more, while the discriminator should not be so much.

AimsTo develop a generative adversarial network (GAN) capable of generating realistic high-resolution anterior segment optical coherence tomography (AS-OCT) images.MethodsThis study included 142 628 AS-OCT B-scans from the American University of...

Generative Adversarial Networks (GANs) can be used for data augmentation in order to improve the outcome and performance of machine learning models for automatic information retrieval. We looked into the challenge faced with limited blurry and distorted digit images from expiry dates datasets, which is required to improve digit recognition tasks on medicine, consumables, cosmetic products and tube-type ointments. For our dataset, Wasserstein GAN with a gradient norm penalty (WGAN-GP) was effective for data augmentation among the state-of-the-art GANs by visible inspection and Fréchet Inception Distance (FID) value comparison.

Despite recent advances in digital banking around the world, the use of banknotes is still predominant. In this context, the detection of fake money bills is important due to the severe impact of their circulation on the economic system. Automating and making detecting counterfeited bills accessible to anyone is still an under-investigated issue, which is mainly based on the visual inspection of bills. In this paper, we propose a novel semi-supervised generative adversarial network (GAN)-based detection approach that, by visually inspecting a bill, can determine if the latter is authentic or fake. Our method originally combines a parallelized GAN to a semi-supervised GAN. On a dataset of Tunisian bills, our method is able to achieve 100% accuracy, with a Fréchet Inception Distance (FID) below 1, i.e., generating diversified fake images with good quality. These performances are proven superior to those of several benchmark approaches.

Currently there is no publicly available adequate dataset that could be used for training Generative Adversarial Networks (GANs) on car images. All available car datasets differ in noise, pose, and zoom levels. Thus, the objective of this work was to create an improved car image dataset that would be better suited for GAN training. To improve the performance of the GAN, we coupled the LSUN and Stanford car datasets. A new merged dataset was then pruned in order to adjust zoom levels and reduce the noise of images. This process resulted in fewer images that could be used for training, with increased quality though. This pruned dataset was evaluated by training the StyleGAN with original settings. Pruning the combined LSUN and Stanford datasets resulted in 2,067,710 images of cars with less noise and more adjusted zoom levels. The training of the StyleGAN on the LSUN-Stanford car dataset proved to be superior to the training with just the LSUN dataset by 3.7% using the Fréchet Inception Distance (FID) as a metric. Results pointed out that the proposed LSUN-Stanford car dataset is more consistent and better suited for training GAN neural networks than other currently available large car datasets.