arXiv subjects

Paul Wright

Publications and source records attributed to Paul Wright.

At least 19 recordsLinked to original sources

arXiv2026

Metadata Supervised MRI Representations for Modelling and Controlling Acquisition Variability

Magnetic resonance imaging exhibits substantial acquisition variability, where identical anatomy can appear markedly different across scanners and imaging protocols. Consequently, learned representations entangle biological structure with acquisition-dependent appearance, limiting interpretability, generalisation, and clinical deployment. We show that these sources of variation can be separated by jointly modelling MRI images and DICOM metadata. Using large-scale clinical brain MRI data, we learn representations that separate anatomical structure from contrast-dependent appearance. Resulting contrast representations organise heterogeneous acquisitions, support sequence understanding, and detect image--metadata inconsistencies, whereas anatomical representations suppress acquisition-specific variation while preserving biologically relevant information. Building on these disentangled representations, we introduce a unified anatomy-preserving harmonisation model for cross-modality and cross-site adaptation, conditioned on image or acquisition metadata. Our findings suggest that acquisition variability is a structured component of the imaging process that can be modelled, audited, and controlled, providing a foundation for acquisition-aware representation learning in large-scale medical imaging.

cs.CV↗

arXiv2025

DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations

Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This is particularly true in Magnetic Resonance Imaging, where scanner hardware differences, diverse acquisition protocols, and varying sequence parameters introduce substantial domain shifts that obscure underlying biological signals. Data harmonization methods aim to reduce these instrumental and acquisition variability, but existing approaches remain insufficient. When applied to imaging data, image-based harmonization approaches are often restricted by the need for target images, while existing text-guided methods rely on simplistic labels that fail to capture complex acquisition details or are typically restricted to datasets with limited variability, failing to capture the heterogeneity of real-world clinical environments. To address these limitations, we propose DIST-CLIP (Disentangled Style Transfer with CLIP Guidance), a unified framework for MRI harmonization that flexibly uses either target images or DICOM metadata for guidance. Our framework explicitly disentangles anatomical content from image contrast, with the contrast representations being extracted using pre-trained CLIP encoders. These contrast embeddings are then integrated into the anatomical content via a novel Adaptive Style Transfer module. We trained and evaluated DIST-CLIP on diverse real-world clinical datasets, and showed significant improvements in performance when compared against state-of-the-art methods in both style translation fidelity and anatomical preservation, offering a flexible solution for style transfer and standardizing MRI data. Our code and weights will be made publicly available upon publication.

cs.CV↗

arXiv2025

Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control

Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely limits large-scale automated analysis. A unified representation of MRI contrast would enable a wide range of downstream utilities, from automatic sequence recognition to harmonization and quality control, without relying on manual annotations. To this end, we introduce MR-CLIP, a metadata-guided framework that learns MRI contrast representations by aligning volumetric images with their DICOM acquisition parameters. The resulting embeddings shows distinct clusters of MRI sequences and outperform supervised 3D baselines under data scarcity in few-shot sequence classification. Moreover, MR-CLIP enables unsupervised data quality control by identifying corrupted or inconsistent metadata through image-metadata embedding distances. By transforming routinely available acquisition metadata into a supervisory signal, MR-CLIP provides a scalable foundation for label-efficient MRI analysis across diverse clinical datasets.

cs.CV↗

arXiv2025

MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations

Accurate interpretation of Magnetic Resonance Imaging scans in clinical systems is based on a precise understanding of image contrast. This contrast is primarily governed by acquisition parameters, such as echo time and repetition time, which are stored in the DICOM metadata. To simplify contrast identification, broad labels such as T1-weighted or T2-weighted are commonly used, but these offer only a coarse approximation of the underlying acquisition settings. In many real-world datasets, such labels are entirely missing, leaving raw acquisition parameters as the only indicators of contrast. Adding to this challenge, the available metadata is often incomplete, noisy, or inconsistent. The lack of reliable and standardized metadata complicates tasks such as image interpretation, retrieval, and integration into clinical workflows. Furthermore, robust contrast-aware representations are essential to enable more advanced clinical applications, such as achieving modality-invariant representations and data harmonization. To address these challenges, we propose MR-CLIP, a multimodal contrastive learning framework that aligns MR images with their DICOM metadata to learn contrast-aware representations, without relying on manual labels. Trained on a diverse clinical dataset that spans various scanners and protocols, MR-CLIP captures contrast variations across acquisitions and within scans, enabling anatomy-invariant representations. We demonstrate its effectiveness in cross-modal retrieval and contrast classification, highlighting its scalability and potential for further clinical applications. The code and weights are publicly available at https://github.com/myigitavci/MR-CLIP.

cs.CV↗

arXiv2025

Generalizable automated ischaemic stroke lesion segmentation with vision transformers

Ischaemic stroke, a leading cause of death and disability, critically relies on neuroimaging for characterising the anatomical pattern of injury. Diffusion-weighted imaging (DWI) provides the highest expressivity in ischemic stroke but poses substantial challenges for automated lesion segmentation: susceptibility artefacts, morphological heterogeneity, age-related comorbidities, time-dependent signal dynamics, instrumental variability, and limited labelled data. Current U-Net-based models therefore underperform, a problem accentuated by inadequate evaluation metrics that focus on mean performance, neglecting anatomical, subpopulation, and acquisition-dependent variability. Here, we present a high-performance DWI lesion segmentation tool addressing these challenges through optimized vision transformer-based architectures, integration of 3563 annotated lesions from multi-site data, and algorithmic enhancements, achieving state-of-the-art results. We further propose a novel evaluative framework assessing model fidelity, equity (across demographics and lesion subtypes), anatomical precision, and robustness to instrumental variability, promoting clinical and research utility. This work advances stroke imaging by reconciling model expressivity with domain-specific challenges and redefining performance benchmarks to prioritize equity and generalizability, critical for personalized medicine and mechanistic research.

eess.IV↗

arXiv2025

Deep generative computed perfusion-deficit mapping of ischaemic stroke

Focal deficits in ischaemic stroke result from impaired perfusion downstream of a critical vascular occlusion. While parenchymal lesions are traditionally used to predict clinical deficits, the underlying pattern of disrupted perfusion provides information upstream of the lesion, potentially yielding earlier predictive and localizing signals. Such perfusion maps can be derived from routine CT angiography (CTA) widely deployed in clinical practice. Analysing computed perfusion maps from 1,393 CTA-imaged-patients with acute ischaemic stroke, we use deep generative inference to localise neural substrates of NIHSS sub-scores. We show that our approach replicates known lesion-deficit relations without knowledge of the lesion itself and reveals novel neural dependents. The high achieved anatomical fidelity suggests acute CTA-derived computed perfusion maps may be of substantial clinical-and-scientific value in rich phenotyping of acute stroke. Using only hyperacute imaging, deep generative inference could power highly expressive models of functional anatomical relations in ischaemic stroke within the pre-interventional window.

q-bio.QM↗

arXiv2024

Framework to generate perfusion map from CT and CTA images in patients with acute ischemic stroke: A longitudinal and cross-sectional study

Stroke is a leading cause of disability and death. Effective treatment decisions require early and informative vascular imaging. 4D perfusion imaging is ideal but rarely available within the first hour after stroke, whereas plain CT and CTA usually are. Hence, we propose a framework to extract a predicted perfusion map (PPM) derived from CT and CTA images. In all eighteen patients, we found significantly high spatial similarity (with average Spearman's correlation = 0.7893) between our predicted perfusion map (PPM) and the T-max map derived from 4D-CTP. Voxelwise correlations between the PPM and National Institutes of Health Stroke Scale (NIHSS) subscores for L/R hand motor, gaze, and language on a large cohort of 2,110 subjects reliably mapped symptoms to expected infarct locations. Therefore our PPM could serve as an alternative for 4D perfusion imaging, if the latter is unavailable, to investigate blood perfusion in the first hours after hospital admission.

cs.CV↗

arXiv2023

Unsupervised 3D out-of-distribution detection with latent diffusion models

Methods for out-of-distribution (OOD) detection that scale to 3D data are crucial components of any real-world clinical deep learning system. Classic denoising diffusion probabilistic models (DDPMs) have been recently proposed as a robust way to perform reconstruction-based OOD detection on 2D datasets, but do not trivially scale to 3D data. In this work, we propose to use Latent Diffusion Models (LDMs), which enable the scaling of DDPMs to high-resolution 3D medical data. We validate the proposed approach on near- and far-OOD datasets and compare it to a recently proposed, 3D-enabled approach using Latent Transformer Models (LTMs). Not only does the proposed LDM-based approach achieve statistically significant better performance, it also shows less sensitivity to the underlying latent representation, more favourable memory scaling, and produces better spatial anomaly maps. Code is available at https://github.com/marksgraham/ddpm-ood

cs.CV↗

arXiv2023

London quantum-secured metro network

We describe a London Quantum-Secured Metro Network using Quantum Key Distribution between three London nodes together with customer access tails. The commercially- eady solution is fully integrated into the BT network and on-boarded its first customer.

quant-ph↗

arXiv2023

Transformer-based out-of-distribution detection for clinically safe segmentation

In a clinical setting it is essential that deployed image processing systems are robust to the full range of inputs they might encounter and, in particular, do not make confidently wrong predictions. The most popular approach to safe processing is to train networks that can provide a measure of their uncertainty, but these tend to fail for inputs that are far outside the training data distribution. Recently, generative modelling approaches have been proposed as an alternative; these can quantify the likelihood of a data sample explicitly, filtering out any out-of-distribution (OOD) samples before further processing is performed. In this work, we focus on image segmentation and evaluate several approaches to network uncertainty in the far-OOD and near-OOD cases for the task of segmenting haemorrhages in head CTs. We find all of these approaches are unsuitable for safe segmentation as they provide confidently wrong predictions when operating OOD. We propose performing full 3D OOD detection using a VQ-GAN to provide a compressed latent representation of the image and a transformer to estimate the data likelihood. Our approach successfully identifies images in both the far- and near-OOD cases. We find a strong relationship between image likelihood and the quality of a model's segmentation, making this approach viable for filtering images unsuitable for segmentation. To our knowledge, this is the first time transformers have been applied to perform OOD detection on 3D image data. Code is available at github.com/marksgraham/transformer-ood.

cs.CV↗

arXiv2022

Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models

Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, dispensing with the necessity for manual labelling. Recently, autoregressive transformers have achieved state-of-the-art performance for anomaly detection in medical imaging. Nonetheless, these models still have some intrinsic weaknesses, such as requiring images to be modelled as 1D sequences, the accumulation of errors during the sampling process, and the significant inference times associated with transformers. Denoising diffusion probabilistic models are a class of non-autoregressive generative models recently shown to produce excellent samples in computer vision (surpassing Generative Adversarial Networks), and to achieve log-likelihoods that are competitive with transformers while having fast inference times. Diffusion models can be applied to the latent representations learnt by autoencoders, making them easily scalable and great candidates for application to high dimensional data, such as medical images. Here, we propose a method based on diffusion models to detect and segment anomalies in brain imaging. By training the models on healthy data and then exploring its diffusion and reverse steps across its Markov chain, we can identify anomalous areas in the latent space and hence identify anomalies in the pixel space. Our diffusion models achieve competitive performance compared with autoregressive approaches across a series of experiments with 2D CT and MRI data involving synthetic and real pathological lesions with much reduced inference times, making their usage clinically viable.

cs.CV↗

arXiv2021

Neuradicon: operational representation learning of neuroimaging reports

Radiological reports typically summarize the content and interpretation of imaging studies in unstructured form that precludes quantitative analysis. This limits the monitoring of radiological services to throughput undifferentiated by content, impeding specific, targeted operational optimization. Here we present Neuradicon, a natural language processing (NLP) framework for quantitative analysis of neuroradiological reports. Our framework is a hybrid of rule-based and artificial intelligence models to represent neurological reports in succinct, quantitative form optimally suited to operational guidance. We demonstrate the application of Neuradicon to operational phenotyping of a corpus of 336,569 reports, and report excellent generalizability across time and two independent healthcare institutions.

cs.CL↗

arXiv2021

5G Network Slicing with QKD and Quantum-Safe Security

We demonstrate how the 5G network slicing model can be extended to address data security requirements. In this work we demonstrate two different slice configurations, with different encryption requirements, representing two diverse use-cases for 5G networking: namely, an enterprise application hosted at a metro network site, and a content delivery network. We create a modified software-defined networking (SDN) orchestrator which calculates and provisions network slices according to the requirements, including encryption backed by quantum key distribution (QKD), or other methods. Slices are automatically provisioned by SDN orchestration of network resources, allowing selection of encrypted links as appropriate, including those which use standard Diffie-Hellman key exchange, QKD and quantum-resistant algorithms (QRAs), as well as no encryption at all. We show that the set-up and tear-down times of the network slices takes of the order of 1-2 minutes, which is an order of magnitude improvement over manually provisioning a link today.

cs.NI↗

arXiv2015

Differentiability of Hausdorff dimension of the non-wandering set in a planar open billiard

We consider open billiards in the plane satisfying the no-eclipse condition. We show that the points in the non-wandering set depend differentiably on deformations to the boundary of the billiard. We use Bowen's equation to estimate the Hausdorff dimension of the non-wandering set of the billiard. Finally we show that the Hausdorff dimension depends differentiably on sufficiently smooth deformations to the boundary of the billiard, and estimate the derivative with respect to such deformations.

math.DS↗

arXiv2014

Hausdorff Dimension of Average Conformal Hyperbolic Sets

The Hausdorff dimension of a conformal repeller or conformal hyperbolic set is well understood. For non-conformal maps, the Hausdorff dimension is only known in some special cases. Ban, Cao and Hu defined the concept of an average conformal repeller which generalises conformal, quasi-conformal and weakly conformal repellers, and they found an equation for the Hausdorff dimension for an average conformal repeller. In this paper we generalise this concept to average conformal hyperbolic sets, and obtain a similar equation for the Hausdorff dimension.

math.DS↗

arXiv2011

Estimates of Hausdorff dimension for non-wandering sets of higher dimensional open billiards

This article concerns a class of open billiards consisting of a finite number of strictly convex, non-eclipsing obstacles $K$. The non-wandering set $M_0$ of the billiard ball map is a topological Cantor set and its Hausdorff dimension has been previously estimated for billiards in $\mathbb{R}^2$, using well-known techniques. We extend these estimates to billiards in $\mathbb{R}^n$, and make various refinements to the estimates. These refinements also allow improvements to other results. We also show that in many cases, the non-wandering set is confined to a particular subset of $\mathbb{R}^n$ formed by the convex hull of points determined by period 2 orbits. This allows more accurate bounds on the constants used in estimating Hausdorff dimension.

math.DS↗

arXiv2011

Behavior of the Escape Rate Function in Hyperbolic Dynamical Systems

For a fixed initial reference measure, we study the dependence of the escape rate on the hole for a smooth or piecewise smooth hyperbolic map. First, we prove the existence and Holder continuity of the escape rate for systems with small holes admitting Young towers. Then we consider general holes for Anosov diffeomorphisms, without size or Markovian restrictions. We prove bounds on the upper and lower escape rates using the notion of pressure on the survivor set and show that a variational principle holds under generic conditions. However, we also show that the escape rate function forms a devil's staircase with jumps along sequences of regular holes and present examples to elucidate some of the difficulties involved in formulating a general theory.

math.DS↗

arXiv2011

Entropy, Lyapunov Exponents and Escape Rates in Open Systems

We study the relation between escape rates and pressure in general dynamical systems with holes, where pressure is defined to be the difference between entropy and the sum of positive Lyapunov exponents. Central to the discussion is the formulation of a class of invariant measures supported on the survivor set over which we take the supremum to measure the pressure. Upper bounds for escape rates are proved for general diffeomorphisms of manifolds, possibly with singularities, for arbitrary holes and natural initial distributions including Lebesgue and SRB measures. Lower bounds do not hold in such generality, but for systems admitting Markov tower extensions with spectral gaps, we prove the equality of the escape rate with the absolute value of the pressure and the existence of an invariant measure realizing the escape rate, i.e. we prove a full variational principle. As an application of our results, we prove a variational principle for the billiard map associated with a planar Lorentz gas of finite horizon with holes.

math.DS↗