Search Results for author:
Found 108 papers, 58 papers with code
Measuring axiomatic soundness of counterfactual image models
We present a general framework for evaluating image counterfactuals.
Understanding metric-related pitfalls in image analysis validation
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice.
Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation
Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress.
Image To Tree with Recursive Prompting
Extracting complex structures from grid-based data is a common key step in automated medical image analysis.
Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding
In this work, we design a paced curriculum by label smoothing (P-CBLS) using paced learning with uniform label smoothing (ULS) for classification tasks and fuse uniform and spatially varying label smoothing (SVLS) for semantic segmentation tasks in a curriculum manner.
Context Label Learning: Improving Background Class Representations in Semantic Segmentation
The results demonstrate that CoLab can guide the segmentation model to map the logits of background samples away from the decision boundary, resulting in significantly improved segmentation accuracy.
Analysing the effectiveness of a generative model for semi-supervised medical image segmentation
In such settings, semi-supervised learning (SSL) attempts to leverage the abundance of unlabelled data to obtain more robust and reliable models.
A Comparative Study of Graph Neural Networks for Shape Classification in Neuroimaging
Graph neural networks have emerged as a promising approach for the analysis of non-Euclidean data such as meshes.
Visual Debates
Thus, our framework answers the question: why did the classifier make a certain prediction?, by allowing players to argue for and against the classifier's decision.
Frequency Dropout: Feature-Level Regularization via Randomized Filtering
Both high and low frequencies can be characteristic of the underlying noise distribution caused by the image acquisition rather than in relation to the task-relevant information about the image content.
Risk of Bias in Chest X-ray Foundation Models
Foundation models are considered a breakthrough in all applications of AI, promising robust and reusable mechanisms for feature extraction, alleviating the need for large amounts of high quality annotated training data for task-specific prediction models.
Deep Structural Causal Shape Models
Causal reasoning provides a language to ask important interventional and counterfactual questions beyond purely statistical association.
Evaluation of 3D GANs for Lung Tissue Modelling in Pulmonary CT
This makes high-quality GANs useful for unsupervised anomaly detection in medical imaging.
Automatic lesion analysis for increased efficiency in outcome prediction of traumatic brain injury
We compare the predictive power of our proposed features to the Marshall score, independently and when paired with classic TBI biomarkers.
Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores
If we could estimate the performance that a pre-trained model would achieve on data from a specific deployment setting, for example a certain clinic, we could judge whether the model could safely be deployed or if its performance degrades unacceptably on the specific data.
Vector Quantisation for Robust Segmentation
The reliability of segmentation models in the medical domain depends on the model's robustness to perturbations in the input space.
Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models
We achieve this by using the natural properties of \emph{hyperbolic geometry} to more efficiently model a hierarchy of symbolic features and generate \emph{hierarchical symbolic rules} as part of our explanations.
GLANCE: Global to Local Architecture-Neutral Concept-based Explanations
Specifically, we provide a generator to visualize the `effect' of interactions among features in latent space and draw feature importance therefrom as local explanations.
Distributional Gaussian Processes Layers for Out-of-Distribution Detection
Moreover, by applying the same segmentation model to out-of-distribution data (i. e., images with pathology such as brain tumors), we show that our uncertainty estimates result in out-of-distribution detection that outperforms the capabilities of previous Bayesian networks and reconstruction-based approaches that learn normative distributions.
Metrics reloaded: Pitfalls and recommendations for image analysis validation
The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint - a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output.
Failure Detection in Medical Image Classification: A Reality Check and Benchmarking Testbed
Failure detection in automated image classification is a critical safeguard for clinical deployment.
Structured Uncertainty in the Observation Space of Variational Autoencoders
In contrast, improving the model for the observational distribution is rarely considered and typically defaults to a pixel-wise independent categorical or normal distribution.
Federated Learning Enables Big Data for Rare Cancer Boundary Detection
Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data.
Investigating underdiagnosis of AI algorithms in the presence of multiple sources of dataset bias
Deep learning models have shown great potential for image-based diagnosis assisting clinical decision making.
CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137).
A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration
We propose a novel variational Bayesian formulation for diffeomorphic non-rigid registration of medical images, which learns in an unsupervised way a data-specific similarity metric.
Matrix Inversion free variational inference in Conditional Student's T Processes
We propose a new variational lower bound for performing inference in sparse Student's T Processes that does not require computationally intensive operations such as matrix inversions or log determinants of matrices.
Algorithmic encoding of protected characteristics in image-based models for disease detection
We explore test set resampling, transfer learning, multitask learning, and model inspection to assess the relationship between the encoding of protected characteristics and disease detection performance across subgroups.
Uncertainty quantification in non-rigid image registration via stochastic gradient Markov chain Monte Carlo
We develop a new Bayesian model for non-rigid registration of three-dimensional medical images, with a focus on uncertainty quantification.
Is MC Dropout Bayesian?
We question the properties of MC Dropout for approximate inference, as in fact MC Dropout changes the Bayesian model; its predictive posterior assigns $0$ probability to the true model on closed-form benchmarks; the multimodality of its predictive posterior is not a property of the true predictive posterior but a design artefact.
DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization
In recent years, the research landscape of machine learning in medical imaging has changed drastically from supervised to semi-, weakly- or unsupervised methods.
Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition
In CDA-TS, the scalar temperature value is replaced with the CDA temperature vector encoded with class frequency to compensate for the over-confidence.
Active label cleaning for improved dataset quality under resource constraints
Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance.
The Pitfalls of Sample Selection: A Case Study on Lung Nodule Classification
Using publicly available data to determine the performance of methodological contributions is important as it facilitates reproducibility and allows scrutiny of the published results.
The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data
Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging.
Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data
This mismatch is known as sampling bias.
Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
Despite technological and medical advances, the detection, interpretation, and treatment of cancer based on imaging data continue to pose significant challenges.
Transductive image segmentation: Self-training and effect of uncertainty estimation
It focuses on the quality of predictions made on the unlabeled data of interest when they are included for optimization during training, rather than improving generalization.
Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification
To aid radiological reading, we propose an auxiliary task-based multiple instance learning approach (ATMIL) for MM classification with the ability to localize sites of disease.
Learning from Partially Overlapping Labels: Image Segmentation under Annotation Shift
Scarcity of high quality annotated images remains a limiting factor for training accurate image segmentation models.
Confidence-based Out-of-Distribution Detection: A Comparative Study and Analysis
Image classification models deployed in the real world may receive inputs outside the intended data distribution.
Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound via Disease-specific Atlas Maps
Fetal ultrasound screening during pregnancy plays a vital role in the early detection of fetal malformations which have potential long-term health impacts.
Distributional Gaussian Process Layers for Outlier Detection in Image Segmentation
We propose a parameter efficient Bayesian layer for hierarchical convolutional Gaussian Processes that incorporates Gaussian Processes operating in Wasserstein-2 space to reliably propagate uncertainty.
Common Limitations of Image Processing Metrics: A Picture Story
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation.
Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations
The task of image segmentation is inherently noisy due to ambiguities regarding the exact location of boundaries between anatomical structures.
Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation
In particular, in image segmentation neural networks may overfit to the foreground samples from small structures, which are often heavily under-represented in the training set, leading to poor generalization.
Atlas-ISTN: Joint Segmentation, Registration and Atlas Construction with Image-and-Spatial Transformer Networks
We propose Atlas-ISTN, a framework that jointly learns segmentation and registration on 2D and 3D image data, and constructs a population-derived atlas in the process.
Decoupled Sparse Gaussian Processes Components]{Decoupled Sparse Gaussian Processes Components : Separating Decision Making from Data Manifold Fitting
We propose a decoupling in Reproducing Kernel Hilbert Space of the parametric and non-parametric components of Sparse Gaussian Processes.
Hierarchical Gaussian Processes with Wasserstein-2 Kernels
Stacking Gaussian Processes severely diminishes the model's ability to detect outliers, which when combined with non-zero mean functions, further extrapolates low non-parametric variance to low training data density regions.
Cranial Implant Design via Virtual Craniectomy with Shape Priors
Our direct estimation method outperforms the baselines provided by the organizers, while the model with shape priors shows superior performance when dealing with out-of-distribution cases.
Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy
Decompressive craniectomy (DC) is a common surgical procedure consisting of the removal of a portion of the skull that is performed after incidents such as stroke, traumatic brain injury (TBI) or other events that could result in acute subdural hemorrhage and/or increasing intracranial pressure.
Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders
We introduce Post-DAE, a post-processing method based on denoising autoencoders (DAE) to improve the anatomical plausibility of arbitrary biomedical image segmentation algorithms.
Deep Generative Model-based Quality Control for Cardiac MRI Segmentation
Our approach provides a real-time and model-agnostic quality control for cardiac MRI segmentation, which has the potential to be integrated into clinical image analysis workflows.
Deep Structural Causal Models for Tractable Counterfactual Inference
We formulate a general framework for building structural causal models (SCMs) with deep learning components.
Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
In image segmentation, there is often more than one plausible solution for a given input.
VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images
Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf. io/nqjyw/, https://osf. io/t98fz/).
Unpaired Multi-modal Segmentation via Knowledge Distillation
We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy.
Causality matters in medical imaging
This article discusses how the language of causality can shed new light on the major challenges in machine learning for medical imaging: 1) data scarcity, which is the limited availability of high-quality annotations, and 2) data mismatch, whereby a trained algorithm may fail to generalize in clinical practice.
Universal Adversarial Robustness of Texture and Shape-Biased Models
Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise.
Domain Generalization via Model-Agnostic Learning of Semantic Features
Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions.
Ranked #52 on
Domain Generalization
on PACS
Vertebrae Detection and Localization in CT with Two-Stage CNNs and Dense Annotations
We propose a new, two-stage approach to the vertebrae centroid detection and localization problem.
Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects
This is an empirical study to investigate the impact of scanner effects when using machine learning on multi-site neuroimaging data.
Needles in Haystacks: On Classifying Tiny Objects in Large Images
In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images.
Is Texture Predictive for Age and Sex in Brain MRI?
Deep learning builds the foundation for many medical image analysis tasks where neuralnetworks are often designed to have a large receptive field to incorporate long spatialdependencies.
Overfitting of neural nets under class imbalance: Analysis and improvements for segmentation
Overfitting in deep learning has been the focus of a number of recent works, yet its exact impact on the behavior of neural networks is not well understood.
Image-and-Spatial Transformer Networks for Structure-Guided Image Registration
The goal is to learn a complex function that maps the appearance of input image pairs to parameters of a spatial transformation in order to align corresponding anatomical structures.
Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels
We propose a highly accurate and efficient one-stage lesion detector, by re-designing a RetinaNet to meet the particular challenges in medical imaging.
Ranked #9 on
Medical Object Detection
on DeepLesion
Medical Imaging with Deep Learning: MIDL 2019 -- Extended Abstract Track
This compendium gathers all the accepted extended abstracts from the Second International Conference on Medical Imaging with Deep Learning (MIDL 2019), held in London, UK, 8-10 July 2019.
Quantitative Error Prediction of Medical Image Registration using Regression Forests
This paper proposes a new automatic method to predict the registration error in a quantitative manner, and is applied to chest CT scans.
Graph Convolutional Gaussian Processes
We propose a novel Bayesian nonparametric method to learn translation-invariant relationships on non-Euclidean domains.
FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms
We present an implementation of a new approach to diffeomorphic non-rigid registration of medical images.
Automated Quality Control in Image Segmentation: Application to the UK Biobank Cardiac MR Imaging Study
Methods: To overcome this challenge, we explore an approach for predicting segmentation quality based on Reverse Classification Accuracy, which enables us to discriminate between successful and failed segmentations on a per-cases basis.
PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation
In this paper, we propose the PnPAdaNet (plug-and-play adversarial domain adaptation network) for adapting segmentation networks between different modalities of medical images, e. g., MRI and CT. We propose to tackle the significant domain shift by aligning the feature spaces of source and target domains in an unsupervised manner.
Towards continual learning in medical imaging
This work investigates continual learning of two segmentation tasks in brain MRI with neural networks.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
Revealing latent structure in data is an active field of research, having introduced exciting technologies such as variational autoencoders and adversarial networks, and is essential to push machine learning towards unsupervised knowledge discovery.
Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
AGs can be easily integrated into standard CNN models such as VGG or U-Net architectures with minimal computational overhead while increasing the model sensitivity and prediction accuracy.
Small Organ Segmentation in Whole-body MRI using a Two-stage FCN and Weighting Schemes
Our experiments show that the proposed approach can boost the segmentation accuracy of multiple small organs in whole-body MRI scans.
High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks
The ability to generate synthetic medical images is useful for data augmentation, domain transfer, and out-of-distribution detection.
Real-time Prediction of Segmentation Quality
Recent advances in deep learning based image segmentation methods have enabled real-time performance with human-level accuracy.
Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging
In this paper, we explore the feasibility of using state-of-the-art auto-encoder-based deep generative models, such as variational and adversarial auto-encoders, for one such task: abnormality detection in medical imaging.
NeuroNet: Fast and Robust Reproduction of Multiple Brain Image Segmentation Pipelines
NeuroNet is a deep convolutional neural network mimicking multiple popular and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM.
Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents
Navigating through target anatomy to find the required view plane is tedious and operator-dependent.
Semi-Supervised Learning via Compact Latent Space Clustering
We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation.
Nonparametric Density Flows for MRI Intensity Normalisation
With the adoption of powerful machine learning methods in medical image analysis, it is becoming increasingly desirable to aggregate data that is acquired across multiple sites.
Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
Graphs are widely used as a natural framework that captures interactions between individual elements represented as nodes in a graph.
Graph Saliency Maps through Spectral Convolutional Networks: Application to Sex Classification with Brain Connectivity
Graph convolutional networks (GCNs) allow to apply traditional convolution operations in non-Euclidean domains, where data are commonly modelled as irregular graphs.
Domain Adaptation for MRI Organ Segmentation using Reverse Classification Accuracy
The variations in multi-center data in medical imaging studies have brought the necessity of domain adaptation.
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
In this paper, we propose a general Riemannian formulation of the pose estimation problem.
Attention-Gated Networks for Improving Ultrasound Scan Plane Detection
We show that, when the base network has a high capacity, the incorporated attention mechanism can provide efficient object localisation while improving the overall performance.
Attention U-Net: Learning Where to Look for the Pancreas
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes.
Ranked #1 on
Pancreas Segmentation
on CT-150
Learning-Based Quality Control for Cardiac MR Images
The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e. g. on UK Biobank, sensitivity and specificity respectively 88% and 99% for heart coverage estimation, 85% and 95% for motion detection), allowing their exclusion from the analysed dataset or the triggering of a new acquisition.
DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images
We present DLTK, a toolkit providing baseline implementations for efficient experimentation with deep learning methods on biomedical images.
Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation
Deep learning approaches such as convolutional neural nets have consistently outperformed previous methods on challenging tasks such as dense, semantic segmentation.
Implicit Weight Uncertainty in Neural Networks
Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures.
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance on par with human experts in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images.
3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
We extensively evaluate the effectiveness of our approach quantitatively on simulated Magnetic Resonance Imaging (MRI), fetal brain imagery with synthetic motion and further demonstrate qualitative results on real fetal MRI data where our method is integrated into a full reconstruction and motion compensation pipeline.
Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation
However, in most recent and promising techniques such as CNN based segmentation it is not obvious how to incorporate such prior knowledge.
Efficient variational Bayesian neural network ensembles for outlier detection
In this work we perform outlier detection using ensembles of neural networks obtained by variational approximation of the posterior in a Bayesian neural network setting.
Spectral Graph Convolutions for Population-based Disease Prediction
We demonstrate the potential of the method on the challenging ADNI and ABIDE databases, as a proof of concept of the benefit from integrating contextual information in classification tasks.
Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks
Evaluating similarity between graphs is of major importance in several computer vision and pattern recognition problems, where graph representations are often used to model objects or interactions between elements.
Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion
Our approach is attractive in challenging imaging scenarios, where significant subject motion complicates reconstruction performance of 3D volumes from 2D slice data.
Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth
In RCA we take the predicted segmentation from a new image to train a reverse classifier which is evaluated on a set of reference images with available ground truth.
Reconstructing Subject-Specific Effect Maps
Analyses on the ADNI dataset show that RSM can also improve correlation between subject-specific detections in cortical thickness data and non-imaging markers of Alzheimer's Disease (AD), such as the Mini Mental State Examination Score and Cerebrospinal Fluid amyloid-$\beta$ levels.
Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
In this work we investigate unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more invariant to differences in the input data, and which does not require any annotations on the test domain.
Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation.
Ranked #1 on
Lesion Segmentation
on ISLES-2015
3D Medical Imaging Segmentation
Brain Lesion Segmentation From Mri
+2
Multi-Output Learning for Camera Relocalization
We formulate this problem as inversion of the generative rendering procedure, i. e., we want to find the camera pose corresponding to a rendering of the 3D scene model that is most similar with the observed input.
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image.
