A5061083764- Medical Imaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Radiation Detection and Scintillator Technologies
- Radiomics and Machine Learning in Medical Imaging
- Advanced Radiotherapy Techniques
- Parkinson's Disease Mechanisms and Treatments
- Atomic and Subatomic Physics Research
- Lung Cancer Diagnosis and Treatment
- Protein Structure and Dynamics
- Radiopharmaceutical Chemistry and Applications
- Pluripotent Stem Cells Research
- Cell Image Analysis Techniques
- COVID-19 Clinical Research Studies
- Neurological disorders and treatments
- COVID-19 and healthcare impacts
- Machine Learning in Bioinformatics
- Eosinophilic Disorders and Syndromes
- Artificial Intelligence in Healthcare and Education
- Computational Drug Discovery Methods
- Radiation Therapy and Dosimetry
- Amyloidosis: Diagnosis, Treatment, Outcomes
- Parathyroid Disorders and Treatments
- Medical Imaging and Pathology Studies
Google (United Kingdom)
2024
DeepMind (United Kingdom)
2024
Faculty (United Kingdom)
2020-2023
University College London
2015-2020
Eastman Dental Hospital
2019
IQVIA (United Kingdom)
2019
University of Leeds
2014-2016
Istituto Nazionale di Fisica Nucleare, Sezione di Pisa
2016
University of Pisa
2016
Abstract The introduction of AlphaFold 2 1 has spurred a revolution in modelling the structure proteins and their interactions, enabling huge range applications protein design 2–6 . Here we describe our 3 model with substantially updated diffusion-based architecture that is capable predicting joint complexes including proteins, nucleic acids, small molecules, ions modified residues. new demonstrates improved accuracy over many previous specialized tools: far greater for protein–ligand...
Transthyretin amyloidosis cardiomyopathy (ATTR-CM) is an increasingly recognized cause of heart failure in older individuals. We sought to characterize the natural history ATTR-CM and compare outcomes quality life among patients with acquired hereditary forms disease.We studied 711 wild-type ATTR-CM, 205 associated V1221 variant (V122I-hATTR-CM), 118 non-V122I-hATTR-CM at UK National Amyloidosis Center between 2000 2017. Patients underwent prospective protocolized evaluations comprising...
This work provides an insight into positron emission tomography (PET) joint image reconstruction/motion estimation (JRM) by maximization of the likelihood, where probabilistic model accounts for warped attenuation. Our analysis shows that maximum-likelihood (ML) JRM returns same reconstructed gates any attenuation map (μ-map) is a deformation given μ-map, regardless its alignment with PET gates. We derived optimization algorithm accordingly, and applied it to simulated patient gated data....
Patient respiratory motion during PET image acquisition leads to blurring in the reconstructed images and may cause significant artifacts, resulting decreased lesion detectability, inaccurate standard uptake value calculation incorrect treatment planning radiation therapy. To reduce these effects data can be regrouped into (nearly) 'motion-free' gates prior reconstruction by selecting events with respect breathing phase. This gating procedure therefore needs a signal: on current scanners it...
Abstract Parkinson’s disease is a common, incurable neurodegenerative disorder that clinically heterogeneous: it likely different cellular mechanisms drive the pathology in individuals. So far has not been possible to define mechanism underlying life. We generated machine learning-based model can simultaneously predict presence of and its primary mechanistic subtype human neurons. used stem cell technology derive control or patient-derived neurons, subtypes through chemical induction...
This work demonstrates how computational and physical modelling of the positron emission tomography (PET) image acquisition process for a state-of-the-art integrated PET magnetic resonance imaging (PET-MR) system can produce images comparable to manufacturer. The GE SIGNA PET/MR scanner is manufactured by General Electric has time-of-flight (TOF) capabilities about 390 ps. All software development took place in Software Tomographic Image Reconstruction (STIR: http://stir.sf.net) library,...
This work is an extension of our recent on joint activity reconstruction/motion estimation (JRM) from positron emission tomography (PET) data. We performed JRM by maximization the penalized log-likelihood in which probabilistic model assumes that same motion field affects both distribution and attenuation map. Our previous results showed can successfully reconstruct when map misaligned with PET data, but converges slowly due to significant cross-talk likelihood. In this paper, we utilize...
Respiratory motion is a major cause of degradation PET image quality. gating and correction can be performed to reduce the effects respiratory motion; these methods require information, typically obtained from external tracking systems. Various groups have studied data-driven (DD) estimation methods. Recently, DD method was established by calculating centroid distribution (COD) listmode events, which then used with event-by-event (EBE-MC) showed results comparable those an device. The EBE-MC...
Respiratory gating is a powerful tool for tackling motion-related issues in chest PET imaging. On current scanners the respiratory signal obtained from external devices, whereas with Data-Driven methods it can be extracted directly data. The aim of this work to show increased potential application Principal Component Analysis (PCA) on TOF We propose methodology that retains information and compare non-TOF method. tested method 16 FDG oncology patients, monitored an RPM camera. To further...
The prevalence of the coronavirus SARS-CoV-2 disease has resulted in unprecedented collection health data to support research. Historically, coordinating collation such datasets on a national scale been challenging execute for several reasons, including issues with privacy, lack reporting standards, interoperable technologies, and distribution methods. pandemic highlighted importance collaboration between government bodies, healthcare institutions, academic researchers commercial companies...
Positron range is an important spatial resolution limiting factor in PET. When imaging inside a magnetic field the positron non-uniformly affected. A decrease of expected directions perpendicular to direction field, whereas no variation field. Monte Carlo simulations were performed validate these expectations. GATE simulation package [1] (version 5.0.0) was used calculate annihilation distribution positrons water, lung and rib bone. point source placed centre spherical phantom simulated. Six...
The combination of positron emission tomography (PET) with magnetic resonance (MR) imaging opens the way to more accurate diagnosis and improved patient management. At present, data acquired by PET MR scanners are essentially processed separately, search for ways improve accuracy tomographic reconstruction via synergy two techniques is an active area research. aim collaborative computational project on (CCP-PETMR), supported UK engineering physical sciences research council (EPSRC),...
Positron range is one important physical limitation to spatial resolution in PET imaging. We present a method take account of positron blurring iterative reconstruction by including specific kernels approximating the annihilation distribution forward projection operation [1]. The correction implemented within OSMAPOSL algorithm STIR 3.0 [2]. GATE [3] simulation package was used obtain point source 68Ga placed centre spherical water and lung tissue phantoms. simulations were performed without...
Respiratory motion generates lung volume changes during the breathing cycle. These affect tissue density and therefore influence both attenuation effect radiotracer concentration in PET imaging. To detect correct for these effects could improve quantitative accuracy of In this work we propose use Principal Component Analysis (PCA) to respiratory-induced upper lung, where is expected be minimal. The method firstly applied simulation data, specifically generated simulate only no motion....
Software for Tomographic Image Reconstruction (STIR: http://stir.sf.net) is an open source C++ library available reconstruction of emission tomography data. This work aims at the incorporation GE SIGNA PET/MR scanner in STIR and enables PET image with data corrections. The extracted from after acquisition includes a list raw files (emission, normalisation, geometric well counter calibration (wcc) factors), magnetic resonance attenuation correction (MRAC) images scanner-based reconstructions....
PET quantitation depends on the accuracy of CT-derived attenuation correction map. In lung, respiration leads to both positional and density mismatches, causing errors at lung borders but also within whole lung. The aim this work is determine extent associated measured time activity curves (TACs) corresponding kinetic parameter estimates. 5 patients with idiopathic pulmonary fibrosis underwent dynamic <sup xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Abstract The National COVID-19 Chest Imaging Database (NCCID) is a centralised database containing chest X-rays, Computed Tomography (CT) scans and cardiac Magnetic Resonance Images (MRI) from patients across the UK, jointly established by NHSX, British Society of Thoracic (BSTI), Royal Surrey NHS Foundation Trust (RSNFT) Faculty. objective initiative to support better understanding coronavirus SARS-CoV-2 disease (COVID-19) development machine learning (ML) technologies that will improve...
Respiratory gating and motion correction can increase resolution in PET chest imaging, but require a respiratory signal. Data-Driven (DD) methods aim to produce signal from data, avoiding the use of external devices. Principal Component Analysis (PCA) is an easy implement DD algorithm whose signals, however, are determined up arbitrary factor. The direction represented by its has be determined. In this work we present extension TOF data previously presented sign-determination method....
ABSTRACT Parkinson’s disease (PD) is a common, devastating, and incurable neurodegenerative disorder. Several molecular mechanisms have been proposed to drive PD, with genetic pathological evidence pointing towards aberrant protein homeostasis mitochondrial dysfunction. PD clinically highly heterogeneous, it likely that different underlie the pathology in individuals, each requiring specific targeted treatment. Recent advances stem cell technology fluorescent live-cell imaging enabled...
Respiratory motion correction in PET imaging is of crucial importance the thorax. On current scanners, respiratory gating performed based on signal an external device. Recent methods extract a from raw data exploiting driven (DD) methods, avoiding use equipment and having potential increased fidelity to internal motion. However, many these DD determine up arbitrary scale factor: it not known if maxima minima are related end-inspiration or end-expiration states, possibly causing inaccurate...