Search Results for author:
Found 195 papers, 62 papers with code
Data-driven approaches to inverse problems
The first part of these notes will provide an introduction to inverse problems, discuss classical solution strategies, and present some applications.
Conservation-preserved Fourier Neural Operator through Adaptive Correction
It ensures that the outputs exactly satisfy the goal conservation law and allow for more flexibility and adaptivity for the model to correct the outputs.
Smooth Model Compression without Fine-Tuning
Compressing and pruning large machine learning models has become a critical step towards their deployment in real-world applications.
Deep Spectral Prior
We introduce Deep Spectral Prior (DSP), a new formulation of Deep Image Prior (DIP) that redefines image reconstruction as a frequency-domain alignment problem.
Multi-Level Monte Carlo Training of Neural Operators
Our numerical experiments on a range of state-of-the-art models and test-cases demonstrate improved computational efficiency compared to traditional single-resolution training approaches, and highlight the existence of a Pareto curve between accuracy and computational time, related to the number of samples per resolution.
Approximation theory for 1-Lipschitz ResNets
In this paper, we focus on 1-Lipschitz residual networks (ResNets) based on explicit Euler steps of negative gradient flows and study their approximation capabilities.
Potential Contrast: Properties, Equivalences, and Generalization to Multiple Classes
Potential contrast is typically used as an image quality measure and quantifies the maximal possible contrast between samples from two classes of pixels in an image after an arbitrary grayscale transformation.
Brain Foundation Models with Hypergraph Dynamic Adapter for Brain Disease Analysis
Brain diseases, such as Alzheimer's disease and brain tumors, present profound challenges due to their complexity and societal impact.
On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes.
FLASH: Flexible Learning of Adaptive Sampling from History in Temporal Graph Neural Networks
Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs.
SurvSurf: a partially monotonic neural network for first-hitting time prediction of intermittently observed discrete and continuous sequential events
We propose a neural-network based survival model (SurvSurf) specifically designed for direct and simultaneous probabilistic prediction of the first hitting time of sequential events from baseline.
D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
Variations in Magnetic resonance imaging (MRI) scanners and acquisition protocols cause distribution shifts that degrade reconstruction performance on unseen data.
Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
Graph Neural Networks (GNNs) have emerged as a powerful tool for learning and inferring from graph-structured data, and are widely used in a variety of applications, often considering large amounts of data and large graphs.
Enhancing Fourier Neural Operators with Local Spatial Features
To address this limitation, we introduce a convolutional neural network (CNN)-based feature pre-extractor to capture LSFs directly from input data, resulting in a hybrid architecture termed \textit{Conv-FNO}.
Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling
The inherent ill-posed nature of image reconstruction problems, due to limitations in the physical acquisition process, is typically addressed by introducing a regularisation term that incorporates prior knowledge about the underlying image.
Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation
In the SONO-MultiKAN phase, we integrate the second-order NODEs and MultiKAN layer as the core computational block to enhance interpretability and representation power.
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
Pre-trained Vision Transformers now serve as powerful tools for computer vision.
Generalized Lie Symmetries in Physics-Informed Neural Operators
Physics-informed neural operators (PINOs) have emerged as powerful tools for learning solution operators of partial differential equations (PDEs).
Generative Unordered Flow for Set-Structured Data Generation
Flow-based generative models have demonstrated promising performance across a broad spectrum of data modalities (e. g., image and text).
Inverse Evolution Data Augmentation for Neural PDE Solvers
In this paper, we propose a novel data augmentation method specifically designed for training neural operators on evolution equations.
Review and Recommendations for using Artificial Intelligence in Intracoronary Optical Coherence Tomography Analysis
Artificial intelligence (AI) methodologies hold great promise for the rapid and accurate diagnosis of coronary artery disease (CAD) from intravascular optical coherent tomography (IVOCT) images.
GRAMA: Adaptive Graph Autoregressive Moving Average Models
Graph State Space Models (SSMs) have recently been introduced to enhance Graph Neural Networks (GNNs) in modeling long-range interactions.
Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs
To develop a preliminary understanding towards Graph Foundation Models, we study the extent to which pretrained Graph Neural Networks can be applied across datasets, an effort requiring to be agnostic to dataset-specific features and their encodings.
Symplectic Neural Flows for Modeling and Discovery
SympFlow allows for two key applications: (i) providing a time-continuous symplectic approximation of the exact flow of a Hamiltonian system--purely based on the differential equations it satisfies, and (ii) approximating the flow map of an unknown Hamiltonian system relying on trajectory data.
Cross-Modal Few-Shot Learning with Second-Order Neural Ordinary Differential Equations
We introduce SONO, a novel method leveraging Second-Order Neural Ordinary Differential Equations (Second-Order NODEs) to enhance cross-modal few-shot learning.
Benchmarking learned algorithms for computed tomography image reconstruction tasks
With this benchmarking study, we provide an evaluation of a range of algorithms representative for different categories of learned reconstruction methods on a recently published dataset of real-world experimental CT measurements.
Training Data Reconstruction: Privacy due to Uncertainty?
We demonstrate that our formulation as well as previous approaches highly depend on the initialisation of the training images $x$ to reconstruct.
Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings
Recent advances in integrating positional and structural encodings (PSEs) into graph neural networks (GNNs) have significantly enhanced their performance across various graph learning tasks.
You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
The use of Plug-and-Play (PnP) methods has become a central approach for solving inverse problems, with denoisers serving as regularising priors that guide optimisation towards a clean solution.
Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey
This survey serves as a roadmap for researchers, offering practical guidance for future exploration in the field of INRs.
On the Utilization of Unique Node Identifiers in Graph Neural Networks
Graph Neural Networks have inherent representational limitations due to their message-passing structure.
Parameter choices in HaarPSI for IQA with medical images
So far, these parameters have been aligned for natural images.
Hamiltonian Matching for Symplectic Neural Integrators
Hamilton's equations of motion form a fundamental framework in various branches of physics, including astronomy, quantum mechanics, particle physics, and climate science.
Pullback Flow Matching on Data Manifolds
We propose Pullback Flow Matching (PFM), a novel framework for generative modeling on data manifolds.
Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
In the context of PDE solvers, recent works have shown that Lie point symmetries can be a useful inductive bias for Physics-Informed Neural Networks (PINNs) through data and loss augmentation.
Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs
Partial differential equations (PDEs) are widely used to model complex physical systems, but solving them efficiently remains a significant challenge.
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
Through numerical experiments on diverse datasets, including image data, we demonstrate that the proposed framework produces high-quality geodesics passing through the data support, reliably estimates the intrinsic dimension of the data manifold, and provides a global chart of the manifold.
Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space
To address this, we introduce Bellman Diffusion, a novel DGM framework that maintains linearity in MDPs through gradient and scalar field modeling.
Learning Regularization for Graph Inverse Problems
In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks.
Deep Generative Classification of Blood Cell Morphology
Accurate classification of haematological cells is critical for diagnosing blood disorders, but presents significant challenges for machine automation owing to the complexity of cell morphology, heterogeneities of biological, pathological, and imaging characteristics, and the imbalance of cell type frequencies.
Learned denoising with simulated and experimental low-dose CT data
The study furthermore suggests the need for more sophisticated noise simulation approaches to bridge the gap between simulated and real-world data in CT image denoising applications and gives insights into the challenges and opportunities in leveraging simulated data for machine learning in computational imaging.
Blessing of Dimensionality for Approximating Sobolev Classes on Manifolds
The manifold hypothesis says that natural high-dimensional data lie on or around a low-dimensional manifold.
Contrastive Learning with Adaptive Neighborhoods for Brain Age Prediction on 3D Stiffness Maps
In the field of neuroimaging, accurate brain age prediction is pivotal for uncovering the complexities of brain aging and pinpointing early indicators of neurodegenerative conditions.
Artificial Immunofluorescence in a Flash: Rapid Synthetic Imaging from Brightfield Through Residual Diffusion
This paper presents a novel method for the conditional synthesis of IF images directly from BF images along with cell segmentation masks.
NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning
To fully leverage both visual and textual modalities and estimate class prototypes more effectively and accurately, we divide our method into two stages: cross-modal prototype construction and cross-modal prototype optimization using neural ordinary differential equations.
G-Adaptivity: optimised graph-based mesh relocation for finite element methods
Classical r-adaptivity relies on the solution of a separate nonlinear "meshing" PDE to determine mesh point locations.
DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs).
Can Generative AI Replace Immunofluorescent Staining Processes? A Comparison Study of Synthetically Generated CellPainting Images from Brightfield
Cell imaging assays utilizing fluorescence stains are essential for observing sub-cellular organelles and their responses to perturbations.
Spatiotemporal Graph Neural Network Modelling Perfusion MRI
Perfusion MRI (pMRI) offers valuable insights into tumor vascularity and promises to predict tumor genotypes, thus benefiting prognosis for glioma patients, yet effective models tailored to 4D pMRI are still lacking.
Optimised ProPainter for Video Diminished Reality Inpainting
In this paper, part of the DREAMING Challenge - Diminished Reality for Emerging Applications in Medicine through Inpainting, we introduce a refined video inpainting technique optimised from the ProPainter method to meet the specialised demands of medical imaging, specifically in the context of oral and maxillofacial surgery.
A study on the adequacy of common IQA measures for medical images
Image quality assessment (IQA) is standard practice in the development stage of novel machine learning algorithms that operate on images.
FedMAP: Unlocking Potential in Personalized Federated Learning through Bi-Level MAP Optimization
This study contributes to PFL by establishing a solid theoretical foundation for the proposed method and offering a robust, ready-to-use framework that effectively addresses the challenges posed by non-IID data in FL.
A study of why we need to reassess full reference image quality assessment with medical images
Image quality assessment (IQA) is indispensable in clinical practice to ensure high standards, as well as in the development stage of machine learning algorithms that operate on medical images.
Full reference image quality assessment
Full-Reference Image Quality Assessment
+1
Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba
In this study, we introduce MambaMIR, an Arbitrary-Masked Mamba-based model with wavelet decomposition for joint medical image reconstruction and uncertainty estimation.
When AI Eats Itself: On the Caveats of AI Autophagy
Generative Artificial Intelligence (AI) technologies and large models are producing realistic outputs across various domains, such as images, text, speech, and music.
Continuous Learned Primal Dual
Neural ordinary differential equations (Neural ODEs) propose the idea that a sequence of layers in a neural network is just a discretisation of an ODE, and thus can instead be directly modelled by a parameterised ODE.
Tackling Graph Oversquashing by Global and Local Non-Dissipativity
A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes.
GRANOLA: Adaptive Normalization for Graph Neural Networks
In recent years, significant efforts have been made to refine the design of Graph Neural Network (GNN) layers, aiming to overcome diverse challenges, such as limited expressive power and oversmoothing.
Unsupervised Training of Convex Regularizers using Maximum Likelihood Estimation
However, many such methods require the availability of ground truth data, which may be unavailable or expensive, leading to a fundamental barrier that can not be bypassed by choice of architecture.
Bilevel Hypergraph Networks for Multi-Modal Alzheimer's Diagnosis
Early detection of Alzheimer's disease's precursor stages is imperative for significantly enhancing patient outcomes and quality of life.
Biophysics Informed Pathological Regularisation for Brain Tumour Segmentation
Recent advances in deep learning have significantly improved brain tumour segmentation techniques; however, the results still lack confidence and robustness as they solely consider image data without biophysical priors or pathological information.
MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation
The recent Mamba model has shown remarkable adaptability for visual representation learning, including in medical imaging tasks.
HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
We present a novel graph transformer framework, HAMLET, designed to address the challenges in solving partial differential equations (PDEs) using neural networks.
Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation
Variational regularisation is the primary method for solving inverse problems, and recently there has been considerable work leveraging deeply learned regularisation for enhanced performance.
On The Temporal Domain of Differential Equation Inspired Graph Neural Networks
Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling complex relationships in graph-structured data.
The curious case of the test set AUROC
Whilst the size and complexity of ML models have rapidly and significantly increased over the past decade, the methods for assessing their performance have not kept pace.
TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios
Multi-object tracking in traffic videos is a crucial research area, offering immense potential for enhancing traffic monitoring accuracy and promoting road safety measures through the utilisation of advanced machine learning algorithms.
Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation
In this paper we rigorously describe the range of dynamics and approximations that arise when training score-based diffusion models, including the true SDE dynamics, the neural approximations, the various approximate particle dynamics that result, as well as their associated Fokker--Planck equations and the neural network approximations of these Fokker--Planck equations.
Single-Shot Plug-and-Play Methods for Inverse Problems
In this work, we introduce Single-Shot PnP methods (SS-PnP), shifting the focus to solving inverse problems with minimal data.
TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations
Implicit neural representations (INRs) have garnered significant interest recently for their ability to model complex, high-dimensional data without explicit parameterisation.
Traffic Video Object Detection using Motion Prior
In this work, we propose two innovative methods to exploit the motion prior and boost the performance of both fully-supervised and semi-supervised traffic video object detection.
Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach
Graph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks.
Provably Convergent Data-Driven Convex-Nonconvex Regularization
An emerging new paradigm for solving inverse problems is via the use of deep learning to learn a regularizer from data.
Recent Methodological Advances in Federated Learning for Healthcare
We give detailed recommendations to help improve the quality of the methodology development for federated learning in healthcare.
Riemannian geometry for efficient analysis of protein dynamics data
First, it comes with a rich structure to account for a wide range of geometries that can be modelled after an energy landscape.
MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain Multi-Center Breast Cancer Screening
This work devises MammoDG, a novel deep-learning framework for generalisable and reliable analysis of cross-domain multi-center mammography data.
Reinterpreting survival analysis in the universal approximator age
We aim to provide the tools needed to fully harness the potential of survival analysis in deep learning.
Convergent regularization in inverse problems and linear plug-and-play denoisers
While a significant amount of research has gone into establishing the convergence of the PnP iteration for different regularity conditions on the denoisers, not much is known about the asymptotic properties of the converged solution as the noise level in the measurement tends to zero, i. e., whether PnP methods are provably convergent regularization schemes under reasonable assumptions on the denoiser.
Inverse Evolution Layers: Physics-informed Regularizers for Deep Neural Networks
Traditional image processing methods employing partial differential equations (PDEs) offer a multitude of meaningful regularizers, along with valuable theoretical foundations for a wide range of image-related tasks.
Designing Stable Neural Networks using Convex Analysis and ODEs
Motivated by classical work on the numerical integration of ordinary differential equations we present a ResNet-styled neural network architecture that encodes non-expansive (1-Lipschitz) operators, as long as the spectral norms of the weights are appropriately constrained.
CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
Different from conventional diffusion models, the degradation operation of our CDiffMR is based on \textit{k}-space undersampling instead of adding Gaussian noise, and the restoration network is trained to harness a de-aliaseing function.
Dis-AE: Multi-domain & Multi-task Generalisation on Real-World Clinical Data
Clinical data is often affected by clinically irrelevant factors such as discrepancies between measurement devices or differing processing methods between sites.
Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models
This issue stems from the unrealistic assumption that approximates the conditional data distribution, $p(\textbf{x} | \textbf{z})$, as an isotropic Gaussian.
DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
However, while a substantial amount of diffusion-based research has focused on generative tasks, few studies have applied diffusion models to general medical image classification.
HGIB: Prognosis for Alzheimer's Disease via Hypergraph Information Bottleneck
We demonstrate, through extensive experiments on ADNI, that our proposed HGIB framework outperforms existing state-of-the-art hypergraph neural networks for Alzheimer's disease prognosis.
Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels
Image-to-image reconstruction problems with free or inexpensive metadata in the form of class labels appear often in biological and medical image domains.
Learning Homeomorphic Image Registration via Conformal-Invariant Hyperelastic Regularisation
We propose a novel framework for deformable image registration.
CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting
Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome.
Provably Convergent Plug-and-Play Quasi-Newton Methods
Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA or ADMM, with applications in inverse problems and imaging.
Hidden Knowledge: Mathematical Methods for the Extraction of the Fingerprint of Medieval Paper from Digital Images
This imprint includes chain lines, laid lines and watermarks which are often visible on the sheet.
Implicit neural representations for unsupervised super-resolution and denoising of 4D flow MRI
4D flow MRI is a non-invasive imaging method that can measure blood flow velocities over time.
Can Physics-Informed Neural Networks beat the Finite Element Method?
In terms of solution time and accuracy, physics-informed neural networks have not been able to outperform the finite element method in our study.
Continuous U-Net: Faster, Greater and Noiseless
Despite the powerful performance reported by existing U-Net type networks, they suffer from several major limitations.
Your diffusion model secretly knows the dimension of the data manifold
A diffusion model approximates the score function i. e. the gradient of the log density of a noise-corrupted version of the target distribution for varying levels of corruption.
SCOTCH and SODA: A Transformer Video Shadow Detection Framework
In this work, we argue that accounting for shadow deformation is essential when designing a video shadow detection method.
Navigating the challenges in creating complex data systems: a development philosophy
In this perspective, we argue that despite the democratization of powerful tools for data science and machine learning over the last decade, developing the code for a trustworthy and effective data science system (DSS) is getting harder.
Dynamical systems' based neural networks
The structure of the neural network is then inferred from the properties of the ODE vector field.
Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness
This is the question that we address in this work.
Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels
We propose WS-DINO as a novel framework to use weak label information in learning phenotypic representations from high-content fluorescent images of cells.
Spectral decomposition of atomic structures in heterogeneous cryo-EM
The dataset contains noisy tomographic projections of the electrostatic potential of the macromolecule, taken from different viewing directions, and in the heterogeneous case, each image corresponds to a different conformation of the macromolecule.
Imaging with Equivariant Deep Learning
From early image processing to modern computational imaging, successful models and algorithms have relied on a fundamental property of natural signals: symmetry.
Practical Operator Sketching Framework for Accelerating Iterative Data-Driven Solutions in Inverse Problems
These IDR schemes are currently the state-of-the-art solutions for imaging inverse problems.
Tree species classification from hyperspectral data using graph-regularized neural networks
We propose a novel graph-regularized neural network (GRNN) algorithm for tree species classification.
Joint reconstruction-segmentation on graphs
Practical image segmentation tasks concern images which must be reconstructed from noisy, distorted, and/or incomplete observations.
Stochastic Primal-Dual Three Operator Splitting Algorithm with Extension to Equivariant Regularization-by-Denoising
In this work we propose a stochastic primal-dual three-operator splitting algorithm (TOS-SPDHG) for solving a class of convex three-composite optimization problems.
Non-Uniform Diffusion Models
We show that non-uniform diffusion leads to multi-scale diffusion models which have similar structure to this of multi-scale normalizing flows.
Classification of datasets with imputed missing values: does imputation quality matter?
Classifying samples in incomplete datasets is a common aim for machine learning practitioners, but is non-trivial.
Learned reconstruction methods with convergence guarantees
In recent years, deep learning has achieved remarkable empirical success for image reconstruction.
Unsupervised Learning of the Total Variation Flow
Inspired by and extending the framework of physics-informed neural networks (PINNs), we propose the TVflowNET, an unsupervised neural network approach, to approximate the solution of the TV flow given an initial image and a time instance.
Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification
We demonstrate, through our experiments, that our framework is able to outperform current techniques for Alzheimer's disease diagnosis.
Operator Sketching for Deep Unrolling Networks
In this work we propose a new paradigm for designing efficient deep unrolling networks using operator sketching.
Multi-modal learning for predicting the genotype of glioma
In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks.
Unsupervised Clustering of Roman Potsherds via Variational Autoencoders
In this paper we propose an artificial intelligence imaging solution to support archaeologists in the classification task of Roman commonware potsherds.
PC-SwinMorph: Patch Representation for Unsupervised Medical Image Registration and Segmentation
The core of our framework is two patch-based strategies, where we demonstrate that patch representation is key for performance gain.
Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading
In this proposed scheme, we design a normalized modality contrastive loss (NMC-loss), which could promote to disentangle multi-modality complementary representation of FFPE and frozen sections from the same patient.
Predicting conversion of mild cognitive impairment to Alzheimer's disease
In this study, we develop a self-supervised contrastive learning approach to generate structural brain networks from routine anatomical MRI under the guidance of diffusion MRI.
Simultaneous Semantic and Instance Segmentation for Colon Nuclei Identification and Counting
In this work, we present a solution framed as a simultaneous semantic and instance segmentation framework.
Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma
Further, the collaborative learning model achieves better performance than either the CNN or the GNN alone.
AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis
Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process.
A Continuous-time Stochastic Gradient Descent Method for Continuous Data
Optimization problems with continuous data appear in, e. g., robust machine learning, functional data analysis, and variational inference.
Conditional Image Generation with Score-Based Diffusion Models
Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling.
Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses.
Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentation
However, it is well known that the DSC loss is poorly calibrated, resulting in overconfident predictions that cannot be usefully interpreted in biomedical and clinical practice.
Incorporating Boundary Uncertainty into loss functions for biomedical image segmentation
Manual segmentation is used as the gold-standard for evaluating neural networks on automated image segmentation tasks.
Focal Attention Networks: optimising attention for biomedical image segmentation
In recent years, there has been increasing interest to incorporate attention into deep learning architectures for biomedical image segmentation.
Learning convex regularizers satisfying the variational source condition for inverse problems
Variational regularization has remained one of the most successful approaches for reconstruction in imaging inverse problems for several decades.
Invertible Learned Primal-Dual
We propose invertible Learned Primal-Dual as a method for tomographic image reconstruction.
Stochastic Primal-Dual Deep Unrolling
We develop a stochastic (ordered-subsets) variant of the classical learned primal-dual (LPD), which is a state-of-the-art unrolling network for tomographic image reconstruction.
StyleGAN-induced data-driven regularization for inverse problems
Our proposed approach, which we refer to as learned Bayesian reconstruction with generative models (L-BRGM), entails joint optimization over the style-code and the input latent code, and enhances the expressive power of a pre-trained StyleGAN2 generator by allowing the style-codes to be different for different generator layers.
Predicting isocitrate dehydrogenase mutation status in glioma using structural brain networks and graph neural networks
Here we propose a method to predict IDH mutation using GNN, based on the structural brain network of patients.
Adaptive unsupervised learning with enhanced feature representation for intra-tumor partitioning and survival prediction for glioblastoma
In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction.
LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification
Semi-supervised learning has received a lot of recent attention as it alleviates the need for large amounts of labelled data which can often be expensive, requires expert knowledge and be time consuming to collect.
HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation
Using the learned affinities from the first stage, HERS builds a hierarchical tree structure that can produce any number of highly adaptive superpixels instantaneously.
End-to-end reconstruction meets data-driven regularization for inverse problems
We propose an unsupervised approach for learning end-to-end reconstruction operators for ill-posed inverse problems.
Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy
When evaluated on a combination of five public polyp datasets, our model similarly achieves state-of-the-art results with a mean DSC of 0. 878 and mean IoU of 0. 809, a 14% and 15% improvement over the previous state-of-the-art results of 0. 768 and 0. 702, respectively.
An end-to-end Optical Character Recognition approach for ultra-low-resolution printed text images
Our experiments have shown that it is possible to perform OCR on 60 dpi scanned images of English text, which is a significantly lower resolution than the state-of-the-art, and we achieved a mean character level accuracy (CLA) of 99. 7% and word level accuracy (WLA) of 98. 9% across a set of about 1000 pages of 60 dpi text in a wide range of fonts.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
Semi-supervised Superpixel-based Multi-Feature Graph Learning for Hyperspectral Image Data
In this work, we present a novel framework for the classification of HSI data in light of a very limited amount of labelled data, inspired by multi-view graph learning and graph signal processing.
Adversarially learned iterative reconstruction for imaging inverse problems
In numerous practical applications, especially in medical image reconstruction, it is often infeasible to obtain a large ensemble of ground-truth/measurement pairs for supervised learning.
Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
Wasserstein GANs are based on the idea of minimising the Wasserstein distance between a real and a generated distribution.
Equivariant neural networks for inverse problems
In this work, we demonstrate that group equivariant convolutional operations can naturally be incorporated into learned reconstruction methods for inverse problems that are motivated by the variational regularisation approach.
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization
An increasing number of models require the control of the spectral norm of convolutional layers of a neural network.
Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation
We compare our loss function performance against six Dice or cross entropy-based loss functions, across 2D binary, 3D binary and 3D multiclass segmentation tasks, demonstrating that our proposed loss function is robust to class imbalance and consistently outperforms the other loss functions.
Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma
EMReDL showed to effectively segment the infiltrated tumor from the partially labelled region of potential infiltration.
Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations
The current state-of-the-art approaches for medical image classification rely on using the de-facto method for ConvNets - fine-tuning.
Cancer-no cancer per image classification
image-classification
+4
Bayesian optimization assisted unsupervised learning for efficient intra-tumor partitioning in MRI and survival prediction for glioblastoma patients
Although successful in tumor sub-region segmentation and survival prediction, radiomics based on machine learning algorithms, is challenged by its robustness, due to the vague intermediate process and track changes.
A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation
The key idea of our technique is the extraction of the pseudo-masks statistical information to decrease uncertainty in the predicted probability whilst enforcing segmentation consistency in a multi-task fashion.
TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
In this work, we present a class of tuning-free PnP proximal algorithms that can determine parameters such as denoising strength, termination time, and other optimization-specific parameters automatically.
Contrastive Registration for Unsupervised Medical Image Segmentation
Secondly, we embed a contrastive learning mechanism into the registration architecture to enhance the discriminating capacity of the network in the feature-level.
Regularized Compression of MRI Data: Modular Optimization of Joint Reconstruction and Coding
In this work we propose a framework for joint optimization of the MRI reconstruction and lossy compression, producing compressed representations of medical images that achieve improved trade-offs between quality and bit-rate.
GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays
The creation of which is a heavily expensive and time consuming task, and especially imposes a great challenge for a novel disease.
A Linear Transportation $\mathrm{L}^p$ Distance for Pattern Recognition
The transportation $\mathrm{L}^p$ distance, denoted $\mathrm{TL}^p$, has been proposed as a generalisation of Wasserstein $\mathrm{W}^p$ distances motivated by the property that it can be applied directly to colour or multi-channelled images, as well as multivariate time-series without normalisation or mass constraints.
Unsupervised Image Restoration Using Partially Linear Denoisers
The ground truth images, however, are often unavailable or very expensive to acquire in real-world applications.
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans
Machine learning methods offer great promise for fast and accurate detection and prognostication of COVID-19 from standard-of-care chest radiographs (CXR) and computed tomography (CT) images.
Learned convex regularizers for inverse problems
We consider the variational reconstruction framework for inverse problems and propose to learn a data-adaptive input-convex neural network (ICNN) as the regularization functional.
Ground Truth Free Denoising by Optimal Transport
We present a learned unsupervised denoising method for arbitrary types of data, which we explore on images and one-dimensional signals.
Deeply Learned Spectral Total Variation Decomposition
To the best of our knowledge, this is the first approach towards learning a non-linear spectral decomposition of images.
SLIC-UAV: A Method for monitoring recovery in tropical restoration projects through identification of signature species using UAVs
To demonstrate SLIC-UAV, support vector machines and random forests were used to predict the species of hand-labelled crowns in a restoration concession in Indonesia.
Structure preserving deep learning
Over the past few years, deep learning has risen to the foreground as a topic of massive interest, mainly as a result of successes obtained in solving large-scale image processing tasks.
Unsupervised clustering of Roman pottery profiles from their SSAE representation
The partiality and the handcrafted variance of the shape fragments within this new database make their unsupervised clustering a very challenging problem: profile similarities are thus explored via the hierarchical clustering of non-linear features learned in the latent representation space of a stacked sparse autoencoder (SSAE) network, unveiling new profile matches.
Multi-task deep learning for image segmentation using recursive approximation tasks
The subproblems are handled by a framework that consists of 1) a segmentation task that learns from pixel-level ground truth segmentation masks of a small fraction of the images, 2) a recursive approximation task that conducts partial object regions learning and data-driven mask evolution starting from partial masks of each object instance, and 3) other problem oriented auxiliary tasks that are trained with sparse annotations and promote the learning of dedicated features.
3D deformable registration of longitudinal abdominopelvic CT images using unsupervised deep learning
This study showed the feasibility of deep learning based deformable registration of longitudinal abdominopelvic CT images via a novel incremental training strategy based on simulated deformations.
On Learned Operator Correction in Inverse Problems
We discuss the possibility to learn a data-driven explicit model correction for inverse problems and whether such a model correction can be used within a variational framework to obtain regularised reconstructions.
iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling
U-Nets have been established as a standard architecture for image-to-image learning problems such as segmentation and inverse problems in imaging.
SPRING: A fast stochastic proximal alternating method for non-smooth non-convex optimization
We introduce SPRING, a novel stochastic proximal alternating linearized minimization algorithm for solving a class of non-smooth and non-convex optimization problems.
Image Deconvolution
Stochastic Optimization
Optimization and Control
90C26
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
Moreover, we discuss the practical considerations of the plugged denoisers, which together with our learned policy yield state-of-the-art results.
Rethinking Medical Image Reconstruction via Shape Prior, Going Deeper and Faster: Deep Joint Indirect Registration and Reconstruction
We also introduce registration blocks based deep nets to predict the registration parameters and warp transformation accurately and efficiently.
Total Variation Regularisation with Spatially Variable Lipschitz Constraints
We introduce a first order Total Variation type regulariser that decomposes a function into a part with a given Lipschitz constant (which is also allowed to vary spatially) and a jump part.
Numerical Analysis Numerical Analysis 65J20, 65J22, 68U10, 94A08
Dynamic Spectral Residual Superpixels
We consider the problem of segmenting an image into superpixels in the context of $k$-means clustering, in which we wish to decompose an image into local, homogeneous regions corresponding to the underlying objects.
Variational Osmosis for Non-linear Image Fusion
We propose a new variational model for non-linear image fusion.
A multi-task U-net for segmentation with lazy labels
The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for image segmentation.
PDE-Inspired Algorithms for Semi-Supervised Learning on Point Clouds
In this paper we extend the labels by minimising the constrained discrete $p$-Dirichlet energy.
GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision
The task of classifying X-ray data is a problem of both theoretical and clinical interest.
Learning the Sampling Pattern for MRI
The discovery of the theory of compressed sensing brought the realisation that many inverse problems can be solved even when measurements are "incomplete".
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge.
Learning to segment microscopy images with lazy labels
In this paper, we introduce a deep convolutional neural network for microscopy image segmentation.
On the Connection Between Adversarial Robustness and Saliency Map Interpretability
Recent studies on the adversarial vulnerability of neural networks have shown that models trained to be more robust to adversarial attacks exhibit more interpretable saliency maps than their non-robust counterparts.
Deep learning as optimal control problems: models and numerical methods
We review the first order conditions for optimality, and the conditions ensuring optimality after discretisation.
Three-dimensional Segmentation of Trees Through a Flexible Multi-Class Graph Cut Algorithm (MCGC)
From these three-dimensional crowns, we are able to measure individual tree biomass.
Superpixel Contracted Graph-Based Learning for Hyperspectral Image Classification
A central problem in hyperspectral image classification is obtaining high classification accuracy when using a limited amount of labelled data.
A total variation based regularizer promoting piecewise-Lipschitz reconstructions
We introduce a new regularizer in the total variation family that promotes reconstructions with a given Lipschitz constant (which can also vary spatially).
Higher-Order Total Directional Variation. Part I: Imaging Applications
We introduce a new class of higher-order total directional variation regularizers.
Numerical Analysis 47A52, 49M30, 49N45, 65J22, 94A08
Anisotropic osmosis filtering for shadow removal in images
We present an anisotropic extension of the isotropic osmosis model that has been introduced by Weickert et al.~(Weickert, 2013) for visual computing applications, and we adapt it specifically to shadow removal applications.
Analysis of PDEs 68U10, 94A08, 49K20, 65M06,
Task adapted reconstruction for inverse problems
The paper considers the problem of performing a task defined on a model parameter that is only observed indirectly through noisy data in an ill-posed inverse problem.
Faster PET Reconstruction with Non-Smooth Priors by Randomization and Preconditioning
Uncompressed clinical data from modern positron emission tomography (PET) scanners are very large, exceeding 350 million data points (projection bins).
Adversarial Regularizers in Inverse Problems
Inverse Problems in medical imaging and computer vision are traditionally solved using purely model-based methods.
Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All? - A Tailored Approach to Single Image Reflection Removal
Removing reflection artefacts from a single image is a problem of both theoretical and practical interest, which still presents challenges because of the massively ill-posed nature of the problem.
Unveiling the invisible - mathematical methods for restoring and interpreting illuminated manuscripts
The last fifty years have seen an impressive development of mathematical methods for the analysis and processing of digital images, mostly in the context of photography, biomedical imaging and various forms of engineering.
Peekaboo - Where are the Objects? Structure Adjusting Superpixels
This paper addresses the search for a fast and meaningful image segmentation in the context of $k$-means clustering.
Blind Image Fusion for Hyperspectral Imaging with the Directional Total Variation
In this paper, we propose a method for increasing the spatial resolution of a hyperspectral image by fusing it with an image of higher spatial resolution that was obtained with a different imaging modality.
Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications
We propose a stochastic extension of the primal-dual hybrid gradient algorithm studied by Chambolle and Pock in 2011 to solve saddle point problems that are separable in the dual variable.
Nonlinear Spectral Image Fusion
In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks.
A Variational Model for Joint Motion Estimation and Image Reconstruction
The aim of this paper is to derive and analyze a variational model for the joint estimation of motion and reconstruction of image sequences, which is based on a time-continuous Eulerian motion model.
Graph clustering, variational image segmentation methods and Hough transform scale detection for object measurement in images
We consider the problem of scale detection in images where a region of interest is present together with a measurement tool (e. g. a ruler).
The structure of optimal parameters for image restoration problems
The analysis is done on the original -- in image restoration typically non-smooth variational problem -- as well as on a smoothed approximation set in Hilbert space which is the one considered in numerical computations.
Bilevel approaches for learning of variational imaging models
We review some recent learning approaches in variational imaging, based on bilevel optimisation, and emphasize the importance of their treatment in function space.
