Method learns to synthesize eye fundus images from vessel trees.
problem Synthesizing images of the eye fundus is challenging.
method Adversarial learning technique to map vessel trees to retinal images.
result Synthetic images retain high quality of true images.
MI-GAN generates synthetic medical images for supervised analysis.
problem Lack of large datasets and overfitting in medical image analysis.
method Generative Adversarial Network (GAN) for generating synthetic medical images and masks.
result MI-GAN achieves state-of-the-art performance with dice coefficient of 0.837 on STARE and 0.832 on DRIVE datasets.
Deep learning improves retinal fundus image analysis for eye diseases.
problem Improving accuracy in diagnosing eye diseases using retinal images.
method Review of deep learning models and datasets for retinal image analysis.
result Deep learning enhances detection and classification of eye diseases.
OTRE uses OT to improve retinal images, outperforming existing methods.
problem Improving quality of non-mydriatic retinal images for accurate diagnoses.
method OT theory for image-to-image translation, regularization by enhancing.
result OTRE outperforms state-of-the-art methods on various retinal image tasks.
Deep neural networks classify T2D from retinal images with high accuracy.
problem Detecting early-stage Type 2 Diabetes from retinal images.
method Employed deep neural networks and multi-target learning to differentiate T2D from healthy individuals.
result Classification performance improved to AUC = 0.758 [±0.003] using images from both eyes. Paper proposes a method to enhance low-quality retinal images using optimal transport.
problem Artifacts and imperfections in retinal images lead to diagnostic inaccuracies.
method Leveraging optimal transport theory, an unpaired image-to-image translation scheme is proposed.
result The method improves perceptually and quantitatively the quality of low-quality retinal images.
A new method tracks retinal vessels more accurately than existing methods.
problem Tracking retinal vessels accurately in spherical images.
method Computing cusp-free, crossing-preserving geodesics on spherical positions and orientations.
result Crossing-preserving tracking shows clear advantages over non-crossing-preserving tracking.
AI generates retinal blood flow maps from standard OCT images.
problem Limited expert-generated labels in medical imaging.
method Training AI on OCTA images to infer perfusion from structural OCT.
result AI-generated maps have similar fidelity to OCTA and better than expert clinicians.
Novel approach localizes optic disc and fovea centers efficiently.
problem Localizing optic disc and fovea centers in retinal images.
method Simultaneously process optic disc and fovea, modeling their relative geometry and appearance.
result Improves localization and recognition by incorporating object-object relations.
The paper presents algorithms for diagnosing Pathological Myopia and detecting retinal structures.
problem Diagnosing Pathological Myopia and detecting retinal structures in fundus images.
method The approach uses Deep Learning techniques, including transfer learning with Xception and YOLO architecture.
result The method has shown satisfactory results in the Pathologic Myopia Challenge.
Bayesian U-Net exploits epistemic uncertainty for anomaly detection in retinal OCT images.
problem Anomaly detection in retinal OCT images using weak labels of healthy anatomy.
method Bayesian U-Net trained on weak labels of healthy anatomy, using Monte Carlo dropout for uncertainty estimation, and post-processing to transfer uncertainty to anomaly segmentations.
result Achieved a Dice index of 0.789 in an independent test set of AMD cases.
In this paper, an ensemble-based method for the screening of diabetic retinopathy (DR) is proposed. This approach is based on features extracted from the output of several retinal image processing algorithms, such as image-level (quality assessment, pre-screening, AM/FM), lesion-specific (microaneurysms, exudates) and …
Novel neural network improves retinal blood vessel segmentation accuracy.
problem Lack of effective low-level and high-level features in existing approaches.
method Proposes a convolutional neural network using atrous convolution for multi-scale features.
result Significantly outperforms existing approaches in accuracy and speed.
Researchers shrink U-Net to find limits of retinal vessel segmentation.
problem Improving retinal vessel segmentation with deep learning.
method Modified U-Net with functional blocks, then simplified to extreme conditions.
result U-Net does not degrade until very minimal configurations.
UOLO detects and segments objects in medical images, achieving state-of-the-art performance.
problem Automatic detection and segmentation of objects in medical images.
method UOLO combines object segmentation and detection using a novel loss function.
result UOLO achieves state-of-the-art performance on optic disc and fovea detection and segmentation from retinal images.
CNNs reveal retinal ganglion cell features, linking visual processing to neuroscience.
problem Understanding what CNNs learn about retinal neuronal circuits.
method Trained CNNs on white noise images to predict neural responses from salamander retinas.
result CNN filters resemble biological retinal components and ganglion cell receptive fields.
Improved retinal vessel segmentation with topology preservation trade-off.
problem Retinal vessel segmentation accuracy and topology preservation trade-off.
method Topology preserving term in the loss function and orientation score guided convolutional module.
result Model achieves higher topological accuracy at the expense of lower overlap metrics.
Paper tackles depth estimation and optic disc-cup segmentation from color fundus images.
problem Depth estimation and optic disc-cup segmentation from color fundus images.
method Uses fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation.
result Demonstrates improved accuracy in depth estimation and optic disc-cup segmentation.
Framework synthesizes geological images minimizing patch distribution discrepancy.
problem Synthesizing realistic geological images from a single exemplar.
method Uses kernel discrepancies and generative neural networks for efficient synthesis.
result Synthesized images match visual patterns and spatial statistics of the exemplar.
New method evaluates text-to-image synthesis for realism, variety, and semantic accuracy.
problem Lack of metrics revealing semantic accuracy in text-to-image synthesis.
method Uses Inception network representations and t-SNE visualization for semantic evaluation.
result Classification accuracy of generated images to real images' visual concepts correlates with semantic accuracy.
Proposes GANs using Capsule Networks for faster image synthesis.
problem Faster image synthesis with fewer training samples and epochs.
method Capsule Networks for image synthesis using GAN architectures.
result Learn data manifold faster and synthesize visually accurate images.
Spatial GAN improves texture synthesis quality and scalability.
problem Texture synthesis quality and scalability issues.
method Spatial Generative Adversarial Networks (SGAN) with extended noise distribution.
result High quality textures, scalability, real-time generation, and fusion of diverse images.
Improved GANs generate high-res images with class information.
problem Synthesizing high-resolution photorealistic images.
method Conditional GANs with label conditioning for improved image synthesis.
result 128x128 resolution samples are more discriminable and diverse than lower resolutions.
Deep learning predicts diabetic macular edema from fundus photos.
problem Diabetic macular edema diagnosis from fundus photos is inaccurate.
method Trained deep learning model on color fundus photographs.
result Deep learning model has higher sensitivity and PPV than human specialists.
Diffusion models outperform GANs in image synthesis quality.
problem Improving image synthesis quality using generative models.
method Developed and optimized diffusion models, and introduced classifier guidance for conditional synthesis.
result Achieved superior image synthesis quality with diffusion models, matching or exceeding GANs in FID scores.
Generative model creates realistic scenes from pixel-wise labels.
problem Creating photo-realistic scenes from pixel-wise labels.
method Semantic bottleneck GAN model combining conditional and unconditional generation networks.
result Model outperforms state-of-the-art models in unsupervised image synthesis.
GANs improve image generation from text and other images.
problem Improving image generation from text and other images.
method Adversarial training to estimate real data distribution and generate synthetic data.
result GANs outperform conventional methods in image generation.
Method treats pseudo healthy synthesis as a factor decomposition problem.
problem Creating a healthy-looking image from a pathological one.
method Adversarial training with paired or unpaired settings, combining two factors (healthy and disease) to reconstruct the input.
result Method outperforms conditional GAN and CycleGAN in generating pseudo healthy images.
A single robust classifier handles complex image synthesis tasks.
problem Challenging image synthesis tasks.
method Adversarial robustness training of a single classifier.
result Direct manipulation of salient features in input images.
This study shows how EEG can be used to generate fMRI data.
problem Mapping fMRI from EEG signals.
method Deep learning approaches (Autoencoders, GANs, Pairwise Learning).
result Feasibility of EEG to fMRI brain image mappings.
Single-stage neural architecture improves text-to-image synthesis.
problem Combining text and image generation is challenging.
method Used deep residual networks and sentence interpolation.
result Achieved state-of-the-art performance with single-stage training.
Generative model creates meal images from ingredient descriptions.
problem Synthesize photo-realistic meal images from ingredient descriptions.
method Attention-based ingredients-image association model, cycle-consistent constraint.
result Model generates meal images corresponding to ingredient descriptions.
EnhanceNet improves image quality through automated texture synthesis.
problem Traditional image super-resolution methods produce over-smoothed images.
method Automated texture synthesis in adversarial training setting.
result Achieves state-of-the-art results in image quality benchmarks.
CNNs accurately model retinal responses to natural scenes.
problem Understanding neural computations in retinal responses to natural stimuli.
method Deep convolutional neural networks (CNNs) were used to model retinal responses to natural scenes.
result CNNs are more accurate than linear models in predicting retinal responses to natural scenes.
MetalGAN synthesizes images across multiple domains without labels.
problem Synthesizing images across multiple domains using a single network.
method Combines cGAN for image generation and Meta-Learning for domain switch.
result MetalGAN successfully produces multi-domain images without hard-coded labels.
BigGAN achieves state-of-the-art image synthesis on ImageNet.
problem Generating high-fidelity images from complex datasets like ImageNet.
method Trained a large-scale GAN with orthogonal regularization and a truncation trick.
result Improved Inception Score (IS) of 166.5 and Frechet Inception Distance (FID) of 7.4.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
Improved image synthesis with user scribbles and text prompts.
problem Inadequate details in generated images due to domain shift.
method Optimization problem formulation and cross-attention for control.
result Significant improvement in user satisfaction (85.32% higher).
Algorithm finds connected components on Lie groups for multi-orientation image analysis.
problem Finding connected components in complex, multi-orientation images.
method Iterative algorithm using morphological dilations and Hamilton-Jacobi-Bellman kernels on Lie groups.
result Algorithm converges in finitely many steps and can differentiate between crossing and aligned structures.
Worldsheet wraps a 3D mesh sheet onto a single image to synthesize novel views.
problem Synthesizing novel views from a single image with large viewpoint changes.
method Shrink-wrapping a planar mesh sheet onto the input image, consistent with learned depth.
result Worldsheet consistently outperforms prior methods on single-image view synthesis.
This paper learns hierarchical compositional models for image synthesis.
problem Creating interpretable and hierarchical image representations.
method Sparsifying a generator network to induce an AND-OR hierarchy.
result The method learns meaningful and interpretable hierarchical representations.
Generative models learn complex spatial patterns using program synthesis.
problem Capturing complex global structure in data, especially in images.
method Incorporates programs representing global structure into generative models and learns these models through program synthesis.
result Significantly better at generating and completing images with global structure compared to state-of-the-art methods.
Program synthesis struggles with complex spatial relationships in image classification.
problem Challenges in solving Synthetic Visual Reasoning Test problems.
method Quantitative reanalysis of human and machine performance, improved program synthesis classifier, categorization of SVRT problems.
result Program synthesis is constrained by spatial relationships in images, not just shape specification.
GANs generate biological cell images capturing protein relationships.
problem Synthesize cells from fluorescence microscopy images.
method Adapted GANs with casual dependencies for multi-channel image generation.
result Demonstrated ability to predict temporal evolution from static images.
Paper introduces PSGAN for texture synthesis with manifold properties.
problem Texture synthesis with limited ability to handle diverse data.
method Generative adversarial networks (GAN) with extended noise tensor structure.
result PSGAN can smoothly interpolate and generate novel textures.
StrokeSave app diagnoses stroke via mobile sensors and AI.
problem Inadequate stroke diagnosis in areas without quality medical facilities.
method Mobile app with sensors, facial and retinal images, deep learning model.
result Deep learning model achieves 95% accuracy in diagnosing stroke.
New data-driven Cartan connection tracks complex vascular structures.
problem Tracking complex vascular structures in multi-orientation images.
method Formulated a data-driven Cartan connection on M2 for geodesic tracking. result Improved geodesic tracking of vascular trees with globally optimal curves.
Enhances VAEs for sharper image synthesis.
problem Blurriness in generated images from VAEs.
method Integrates a downscaled version of the original image into the VAE framework and uses it as input to the decoder.
result Improves FID score in image synthesis while maintaining similar log-likelihood performance.