OBJECTIVE: The purpose of this study was to generate radiographs including dentigerous cysts by applying the latest generative adversarial network (GAN; StyleGAN3) to panoramic radiography.
METHODS: A total of 459 cystic lesions were selected, and 409 images were randomly assigned as training data and 50 images as test data. StyleGAN3 training was performed for 500 000 images. Fifty generated images were objectively evaluated by comparing them with 50 real images according to four metrics: Fréchet inception distance (FID), kernel inception distance (KID), precision and recall, and inception score (IS). A subjective evaluation of the generated images was performed by three specialists who compared them with the real images in a visual Turing test.
RESULTS: The results of the metrics were as follows: FID, 199.28; KID, 0.14; precision, 0.0047; recall, 0.00; and IS, 2.48. The overall results of the visual Turing test were 82.3%. No significant difference was found in the human scoring of root resorption.
CONCLUSIONS: The images generated by StyleGAN3 were of such high quality that specialists could not distinguish them from the real images.

Fibrosis, a pathological increase in extracellular matrix proteins, is a significant health issue that hinders the function of many organs in the body, in some cases fatally. In the heart, fibrosis impacts on electrical propagation in a complex and poorly predictable fashion, potentially serving as a substrate for dangerous arrhythmias. Individual risk depends on the spatial manifestation of fibrotic tissue, and learning the spatial arrangement on the fine scale in order to predict these impacts still relies upon invasive ex vivo procedures. As a result, the effects of spatial variability on the symptomatic impact of cardiac fibrosis remain poorly understood. In this work, we address the issue of availability of such imaging data via a computational methodology for generating new realisations of cardiac fibrosis microstructure. Using the Perlin noise technique from computer graphics, together with an automated calibration process that requires only a single training image, we demonstrate successful capture of collagen texturing in four types of fibrosis microstructure observed in histological sections. We then use this generator to quantitatively analyse the conductive properties of these different types of cardiac fibrosis, as well as produce three-dimensional realisations of histologically-observed patterning. Owing to the generator\'s flexibility and automated calibration process, we also anticipate that it might be useful in producing additional realisations of other physiological structures.

Machine learning has been employed in recognizing protein localization at the subcellular level, which highly facilitates the protein function studies, especially for those multi-label proteins that localize in more than one organelle. However, existing works mostly study the qualitative classification of protein subcellular locations, ignoring fraction of one multi-label protein in different locations. Actually, about 50 % proteins are multi-label proteins, and the ignorance of quantitative information highly restricts the understanding of their spatial distribution and functional mechanism. One reason of the lack of quantitative study is the insufficiency of quantitative annotations. To address the data shortage problem, here we proposed a generative model, PLocGAN, which could generate cell images with conditional quantitative annotation of the fluorescence distribution. The model was a conditional generative adversarial network, in which the condition learning utilized partial label learning to overcome the lack of training labels and allowed training with only qualitative labels. Meanwhile, it used contrastive learning to enhance diversity of the generated images. We assessed the PLocGAN on four pixel-fused synthetic datasets and one real dataset, and demonstrated that the model could generate images with good fidelity and diversity, outperforming existing state-of-the-art generative methods. To verify the utility of PLocGAN in the quantitative prediction of protein subcellular locations, we replaced the training images with generated quantitative images and built prediction models, and found that they had a boosting effect on the quantitative estimation. This work demonstrates the effectiveness of deep generative models in bioimage analysis, and provides a new solution for quantitative subcellular proteomics.

Objective.Head and neck radiotherapy planning requires electron densities from different tissues for dose calculation. Dose calculation from imaging modalities such as MRI remains an unsolved problem since this imaging modality does not provide information about the density of electrons.Approach.We propose a generative adversarial network (GAN) approach that synthesizes CT (sCT) images from T1-weighted MRI acquisitions in head and neck cancer patients. Our contribution is to exploit new features that are relevant for improving multimodal image synthesis, and thus improving the quality of the generated CT images. More precisely, we propose a Dual branch generator based on the U-Net architecture and on an augmented multi-planar branch. The augmented branch learns specific 3D dynamic features, which describe the dynamic image shape variations and are extracted from different view-points of the volumetric input MRI. The architecture of the proposed model relies on an end-to-end convolutional U-Net embedding network.Results.The proposed model achieves a mean absolute error (MAE) of18.76±5.167in the target Hounsfield unit (HU) space on sagittal head and neck patients, with a mean structural similarity (MSSIM) of0.95±0.09and a Frechet inception distance (FID) of145.60±8.38. The model yields a MAE of26.83±8.27to generate specific primary tumor regions on axial patient acquisitions, with a Dice score of0.73±0.06and a FID distance equal to122.58±7.55. The improvement of our model over other state-of-the-art GAN approaches is of 3.8%, on a tumor test set. On both sagittal and axial acquisitions, the model yields the best peak signal-to-noise ratio of27.89±2.22and26.08±2.95to synthesize MRI from CT input.Significance.The proposed model synthesizes both sagittal and axial CT tumor images, used for radiotherapy treatment planning in head and neck cancer cases. The performance analysis across different imaging metrics and under different evaluation strategies demonstrates the effectiveness of our dual CT synthesis model to produce high quality sCT images compared to other state-of-the-art approaches. Our model could improve clinical tumor analysis, in which a further clinical validation remains to be explored.

The paper demonstrates a novel methodology for Content-Based Image Retrieval (CBIR), which shifts the focus from conventional domain-specific image queries to more complex text-based query processing. Latent diffusion models are employed to interpret complex textual prompts and address the requirements of effectively interpreting the complex textual query. Latent Diffusion models successfully transform complex textual queries into visually engaging representations, establishing a seamless connection between textual descriptions and visual content. Custom triplet network design is at the heart of our retrieval method. When trained well, a triplet network will represent the generated query image and the different images in the database. The cosine similarity metric is used to assess the similarity between the feature representations in order to find and retrieve the relevant images. Our experiments results show that latent diffusion models can successfully bridge the gap between complex textual prompts for image retrieval without relying on labels or metadata that are attached to database images. This advancement sets the stage for future explorations in image retrieval, leveraging the generative AI capabilities to cater to the ever-evolving demands of big data and complex query interpretations.

In light of growing concerns about the misuse of personal data resulting from the widespread use of artificial intelligence technology, it is necessary to implement robust privacy-protection methods. However, existing methods for protecting facial privacy suffer from issues such as poor visual quality, distortion and limited reusability. To tackle this challenge, we propose a novel approach called Diffusion Models for Face Privacy Protection (DIFP). Our method utilizes a face generator that is conditionally controlled and reality-guided to produce high-resolution encrypted faces that are photorealistic while preserving the naturalness and recoverability of the original facial information. We employ a two-stage training strategy to generate protected faces with guidance on identity and style, followed by an iterative technique for improving latent variables to enhance realism. Additionally, we introduce diffusion model denoising for identity recovery, which facilitates the removal of encryption and restoration of the original face when required. Experimental results demonstrate the effectiveness of our method in qualitative privacy protection, achieving high success rates in evading face-recognition tools and enabling near-perfect restoration of occluded faces.

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.
CONCLUSIONS: 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.

The cast thin sections of tight oil reservoirs contain important parameters such as rock mineral composition and content, porosity, permeability and stratigraphic characteristics, which are of great significance for reservoir evaluation. The use of deep learning technology for intelligent identification of thin section images is a development trend of mineral identification. However, the difficulty of making cast thin sections, the complexity of the making process and the high cost of thin section annotation have led to a lack of cast thin section images, which cannot meet the training requirements of deep learning image recognition models. In order to increase the sample size and improve the training effect of deep learning model, we proposed a generation and annotation method of thin section images of tight oil reservoir based on deep learning, by taking Fuyu reservoir in Sanzhao Sag as the target area. Firstly, the Augmentor strategy space was used to preliminarily augment the original images while preserving the original image features to meet the requirements of the model. Secondly, the category attention mechanism was added to the original StyleGAN network to avoid the influence of the uneven number of components in thin sections on the quality of the generated images. Then, the SALM annotation module was designed to achieve semi-automatic annotation of the generated images. Finally, experiments on image sharpness, distortion, standard accuracy and annotation efficiency were designed to verify the advantages of the method in image quality and annotation efficiency.

The generation of images from electroencephalography (EEG) signals has become a popular research topic in recent research because it can bridge the gap between brain signals and visual stimuli and has wide application prospects in neuroscience and computer vision. However, due to the high complexity of EEG signals, the reconstruction of visual stimuli through EEG signals continues to pose a challenge. In this work, we propose an EEG-ConDiffusion framework that involves three stages: feature extraction, fine-tuning of the pretrained model, and image generation. In the EEG-ConDiffusion framework, classification features of EEG signals are first obtained through the feature extraction block. Then, the classification features are taken as conditions to fine-tune the stable diffusion model in the image generation block to generate images with corresponding semantics. This framework combines EEG classification and image generation means to enhance the quality of generated images. Our proposed framework was tested on an EEG-based visual classification dataset. The performance of our framework is measured by classification accuracy, 50-way top-k accuracy, and inception score. The results indicate that the proposed EEG-Condiffusion framework can extract effective classification features and generate high-quality images from EEG signals to realize EEG-to-image conversion.

OBJECTIVE: Brain-Computer Interface (BCI) technology has recently been advancing rapidly, bringing significant hope for improving human health and quality of life. Decoding and visualizing visually evoked electroencephalography (EEG) signals into corresponding images plays a crucial role in the practical application of BCI technology. The recent emergence of diffusion models provides a good modeling basis for this work. However, the existing diffusion models still have great challenges in generating high-quality images from EEG, due to the low signal-to-noise ratio and strong randomness of EEG signals. The purpose of this study is to address the above-mentioned challenges by proposing a framework named NeuroDM that can decode human brain responses to visual stimuli from EEG-recorded brain activity.
METHODS: In NeuroDM, an EEG-Visual-Transformer (EV-Transformer) is used to extract the visual-related features with high classification accuracy from EEG signals, then an EEG-Guided Diffusion Model (EG-DM) is employed to synthesize high-quality images from the EEG visual-related features.
RESULTS: We conducted experiments on two EEG datasets (one is a forty-class dataset, and the other is a four-class dataset). In the task of EEG decoding, we achieved average accuracies of 99.80% and 92.07% on two datasets, respectively. In the task of EEG visualization, the Inception Score of the images generated by NeuroDM reached 15.04 and 8.67, respectively. All the above results outperform existing methods.
CONCLUSIONS: The experimental results on two EEG datasets demonstrate the effectiveness of the NeuroDM framework, achieving state-of-the-art performance in terms of classification accuracy and image quality. Furthermore, our NeuroDM exhibits strong generalization capabilities and the ability to generate diverse images.