Study compares handcrafted and deep neural network features for OCT image classification.
problem Classifying OCT images for disease detection.
method Comparison of Histogram of Oriented Gradient (HOG), Local Binary Pattern (LBP), DenseNet-169, and ResNet50.
result Deep neural network methods outperform handcrafted features with higher accuracy and better underrepresented class performance.
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.
Deep convolutional neural networks (CNNs) have demonstrated impressive performance on visual object classification tasks. In addition, it is a useful model for predication of neuronal responses recorded in visual system. However, there is still no clear understanding of what CNNs learn in terms of visual neuronal circu…
RETINA Benchmark evaluates Bayesian deep learning on diabetic retinopathy detection.
problem Reliable uncertainty quantification for deep learning models in medical applications.
method Design and evaluation of a real-world diabetic retinopathy dataset and tasks.
result Benchmarking of Bayesian deep learning methods on diabetic retinopathy detection tasks.
Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational ima…
Convolutional neural network localizes OD and fovea in UWFoV-SLO images.
problem Localizing optic disc and fovea centers in ultra-widefield retinal images.
method Convolutional neural network trained on reflectance and autofluorescence images.
result 99.4% OD localisation accuracy and 99.1% fovea localisation accuracy.
Adds a precortical module to CNNs for improved robustness to light variations.
problem Robustness of CNNs to global light intensity and contrast variations.
method Developed a mathematical model of the mammalian visual pathway, inspired by CNNs, and added a preliminary convolutional module.
result Significantly more robust CNNs achieved with added module on MNIST, FashionMNIST, and SVHN databases.
Retina-VAE models macular disease spectrum using clinical data.
problem Representing the spectrum of macular diseases clinically.
method Variational autoencoder (VAE) model trained on patient profiles.
result Latent vectors cluster into 14 subtypes, suggesting treatment responses.
A fundamental challenge in calcium imaging has been to infer the timing of action potentials from the measured noisy calcium fluorescence traces. We systematically evaluate a range of spike inference algorithms on a large benchmark dataset recorded from varying neural tissue (V1 and retina) using different calcium indi…
Despite significant advances in artificial intelligence (AI) for computer vision, its application in medical imaging has been limited by the burden and limits of expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures perfusion of the…
Deep learning system improves diabetic retinopathy and macular edema grading.
problem Manual screening of diabetic retinopathy and macular edema images is labor-intensive and error-prone.
method Used deep learning on fundus images, achieving comparable or better performance than previous studies.
result Deep learning system can accurately classify images according to clinical grading scales.
New mechanisms from primate vision improve neural network robustness.
problem Demonstrating robust neural networks to small adversarial perturbations.
method Investigated two biologically plausible mechanisms: non-uniform retina sampling and receptive field diversity.
result Non-uniform retina sampling and receptive field diversity improve adversarial robustness.
Robots learn spatial perception from sensorimotor invariants.
problem Developing autonomous robots that perceive space without human intuition.
method Study how a robot's motor commands relate to changes in exteroceptive inputs to deduce its spatial configuration.
result Robots can learn the configuration space of their sensors, revealing a planar position and orientation.
Paper uses deep Q-network to correct eye movement artifacts in OCT volumes.
problem Unsupervised correction of inter-frame misalignments in OCT volumes due to eye movement artifacts.
method Dueling deep Q-network trained to maximize reward signals based on intensity-based image similarity metrics.
result Average normalized mutual information and correlation coefficient of 0.985 and 0.914, respectively.
New benchmark evaluates BDL methods in medical retinopathy diagnosis.
problem Evaluate robustness and scalability of BDL methods in medical applications.
method Developed a new benchmark with real-world diabetic retinopathy tasks.
result Some BDL techniques overfit uncertainty to datasets, underperforming on new benchmark.
New method for predicting neuron activity with unknown stimuli.
problem Statistical inference of neuron activity with missing data and unknown sources.
method Maximum likelihood estimation with fixed-point iteration.
result Model increases system likelihood and reveals neural connections.
Neural connectomics has begun producing massive amounts of data, necessitating new analysis methods to discover the biological and computational structure. It has long been assumed that discovering neuron types and their relation to microcircuitry is crucial to understanding neural function. Here we developed a nonpara…
Approach to develop visual perception in robots through sensorimotor interactions.
problem Developing autonomous perception in robots.
method Sensorimotor contingencies theory applied to robot exploration and learning.
result Captured sensorimotor regularities in a predictive model for visual field discovery.
Neural circuits contain heterogeneous groups of neurons that differ in type, location, connectivity, and basic response properties. However, traditional methods for dimensionality reduction and clustering are ill-suited to recovering the structure underlying the organization of neural circuits. In particular, they do n…
We present two Bayesian procedures to infer the interactions and external currents in an assembly of stochastic integrate-and-fire neurons from the recording of their spiking activity. The first procedure is based on the exact calculation of the most likely time courses of the neuron membrane potentials conditioned by …
Modeling curvature-sensitive cells in visual cortex with geometric structures.
problem Understanding the functional architecture of curvature-sensitive cells in the visual cortex.
method Geometric model based on Engel structure and SIM(2) symmetry.
result Identified SIM(2) as the natural symmetry group for curvature-sensitive cells.
Novel method combines wavelet transform and FCNN for retinal vessel segmentation.
problem Automatic vessel segmentation for retinal vascular diseases.
method Combines multiscale Stationary Wavelet Transform with multiscale FCNN, using rotation operations for data augmentation and prediction.
result Achieved high accuracy and robustness on multiple databases.
STNMF method uncovers neural circuit components in retinal ganglion cells.
problem Deciphering complex neuronal circuit components in the brain.
method Spike-triggered non-negative matrix factorization (STNMF) method.
result STNMF can detect various properties of upstream bipolar cells and recover synaptic connection strengths.
Study limits of circadian synchronization under different light signals.
problem Disruption of circadian rhythms due to misalignment with external light signals.
method Matrix-free approach for locating periodic steady states, numerical continuation, bifurcation diagrams, unsupervised learning.
result Limits of circadian synchronization to external light signals of different frequency and duty cycle.
POSCMs extend SCMs for causal modeling with latent contexts.
problem Causal modeling with latent contexts and endogenous mechanisms.
method Kolmogorov-Arnold-Sprecher edge-functional decomposition for explicit parametrization.
result Identifiability of structure and mechanisms under latent context.
CatSIM measures image similarity robustly to small changes.
problem Measuring similarity between images, especially with small perturbations.
method Uses structural similarity image quality paradigm, robust to small location changes.
result Structural similarity between images rated higher when not entirely overlapping.
Develops statistical guarantees for image-to-image regression models.
problem Current image-to-image regression models lack statistical guarantees for model mistakes and hallucinations.
method Uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems.
result Derives uncertainty intervals around each pixel with formal mathematical guarantees.
AugurOne trains single image generators without GANs using image warps.
problem Training end-to-end single image generators without GANs.
method Non-affine augmentations of single input images for training an upscaling neural network.
result End-to-end training yields state-of-the-art performance on conditional generation tasks.
Paper analyzes learning from ghost imaging without reconstruction bottleneck.
problem High-speed cell classification bottleneck in ghost cytometry.
method Theoretical analysis of learning from ghost imaging without reconstruction.
result Theoretical analysis supports learning from ghost imaging without reconstruction.
Total variation denoising improves image quality adaptively.
problem Improving image quality from noisy data.
method Total variation regularization for image denoising.
result Denoised images converge to true images at a parametric rate.
Improves text-to-image generation with bidirectional capabilities.
problem Generating realistic images from text descriptions.
method Integrates text and image modalities using MMVR architecture with n-gram cost function and multiple sentences.
result Significant improvement in image quality over existing methods (over 20%).
Transmission imaging, as an important imaging technique widely used in astronomy, medical diagnosis, and biology science, has been shown in [49] quite different from reflection imaging used in our everyday life. Understanding the structures of images (the prior information) is important for designing, testing, and choo…
A new metric FRD improves comparing medical images.
problem Comparing medical images for distribution or domain differences.
method Developed a new metric FRD using standardized radiomic features.
result FRD outperforms other metrics in various medical imaging applications.
This study investigates how much knowledge from natural images can be transferred to pathology images.
problem Quantifying how much knowledge from natural images can be transferred to pathology images.
method Proposes a framework to quantify knowledge gain by a particular layer, conducts empirical investigation in pathology image centered transfer learning.
result Early layers of deep models can transfer knowledge to pathology image classification tasks.
Generates high-resolution images from low-resolution inputs.
problem Generating realistic images from low-resolution inputs.
method Latent Adversarial Generator (LAG) using perceptual loss.
result Samples of high-resolution images from low-resolution inputs.
Few-shot unsupervised image-to-image translation model learns from a few examples.
problem Current unsupervised image-to-image translation methods require many images at training time.
method Coupling adversarial training with a novel network design for few-shot learning.
result Model achieves effective few-shot image-to-image translation.
Generates synthetic laparoscopic images for training deep neural networks.
problem Lack of large labeled data sets for laparoscopic image processing.
method Unpaired image-to-image translation to generate realistic synthetic images.
result Synthetic data set improves liver segmentation performance without manual labeling.
Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo shari…
Generative Adversarial Networks optimize model parameters for image matching.
problem Optimizing model parameters for accurate image matching.
method Model-Assisted Generative Adversarial Network (GAN) to produce fake images matching true images.
result Best match model parameter values can minimize bias in image recognition.
PG-IM uses neural-symbolic programs to manipulate images.
problem Creating holistic image representations and manipulations.
method PG-IM detects patterns, induces symbolic programs, and manipulates images using a neural network.
result PG-IM learns from a single image and achieves superior performance.
Paper introduces LLISE for image structure learning using SSIM.
problem Image quality assessment using MSE or ℓ2 norm is not promising. method Locally Linear Image Structural Embedding (LLISE) using SSIM.
result LLISE captures image structure features and discriminates distortions.
Paper proposes method to generate images from text using GANs trained on uncaptioned images.
problem Limited captioned image datasets for text-to-image synthesis.
method Conditional GANs trained on uncaptioned images with an Image Captioning Module.
result Promising preliminary results compared to unconditional GANs.
Latent feature models are attractive for image modeling, since images generally contain multiple objects. However, many latent feature models ignore that objects can appear at different locations or require pre-segmentation of images. While the transformed Indian buffet process (tIBP) provides a method for modeling tra…
The paper analyzes relationships between various image models for restoration.
problem Unclear relationships among popular image models for restoration.
method Theoretical analysis and experimental study of image models.
result Improved denoising performance by combining multiple image models.
Deep models generate images with missing high-frequency details.
problem Malicious use of realistic deep-generated images.
method Analysis of Fourier spectrum discrepancies between real and generated images.
result Detection method achieves up to 99.2% accuracy in classifying real and generated images.
StrokeCoder uses Transformers to generate images from single examples.
problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.
New method reconstructs images from fMRI data using unlabeled data.
problem Challenges in acquiring labeled data for fMRI-to-image reconstruction.
method Self-supervised training with Encoder-Decoder and Decoder-Encoder networks.
result Reconstruction network adapts to new unlabeled test data.
Improved self-supervised learning for document images.
problem Performance of self-supervised pre-training on document images is poor.
method Proposed context-aware alternatives and a novel multi-modal method.
result Novel method outperforms other self-supervised methods on document image classification.