Accurate structure prediction of biomolecular interactions with AlphaFold 3.

The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2-6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein-ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein-nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody-antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

Prediction of mechanistic subtypes of Parkinson's using patient-derived stem cell models.

Parkinson's disease is a common, incurable neurodegenerative disorder that is clinically heterogeneous: it is likely that different cellular mechanisms drive the pathology in different individuals. So far it has not been possible to define the cellular mechanism underlying the neurodegenerative disease in life. We generated a machine learning-based model that can simultaneously predict the presence of disease and its primary mechanistic subtype in human neurons. We used stem cell technology to derive control or patient-derived neurons, and generated different disease subtypes through chemical induction or the presence of mutation. Multidimensional fluorescent labelling of organelles was performed in healthy control neurons and in four different disease subtypes, and both the quantitative single-cell fluorescence features and the images were used to independently train a series of classifiers to build deep neural networks. Quantitative cellular profile-based classifiers achieve an accuracy of 82%, whereas image-based deep neural networks predict control and four distinct disease subtypes with an accuracy of 95%. The machine learning-trained classifiers achieve their accuracy across all subtypes, using the organellar features of the mitochondria with the additional contribution of the lysosomes, confirming the biological importance of these pathways in Parkinson's. Altogether, we show that machine learning approaches applied to patient-derived cells are highly accurate at predicting disease subtypes, providing proof of concept that this approach may enable mechanistic stratification and precision medicine approaches in the future.

Towards nationally curated data archives for clinical radiology image analysis at scale: Learnings from national data collection in response to a pandemic.

The prevalence of the coronavirus SARS-CoV-2 disease has resulted in the unprecedented collection of health data to support research. Historically, coordinating the collation of such datasets on a national scale has been challenging to execute for several reasons, including issues with data privacy, the lack of data reporting standards, interoperable technologies, and distribution methods. The coronavirus SARS-CoV-2 disease pandemic has highlighted the importance of collaboration between government bodies, healthcare institutions, academic researchers and commercial companies in overcoming these issues during times of urgency. The National COVID-19 Chest Imaging Database, led by NHSX, British Society of Thoracic Imaging, Royal Surrey NHS Foundation Trust and Faculty, is an example of such a national initiative. Here, we summarise the experiences and challenges of setting up the National COVID-19 Chest Imaging Database, and the implications for future ambitions of national data curation in medical imaging to advance the safe adoption of artificial intelligence in healthcare.

An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis.

BACKGROUND: The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better understanding of the coronavirus SARS-CoV-2 disease (COVID-19) and the development of machine learning technologies that will improve care for patients hospitalized with a severe COVID-19 infection. This article introduces the training dataset, including a snapshot analysis covering the completeness of clinical data, and availability of image data for the various use-cases (diagnosis, prognosis, longitudinal risk). An additional cohort analysis measures how well the NCCID represents the wider COVID-19-affected UK population in terms of geographic, demographic, and temporal coverage. FINDINGS: The NCCID offers high-quality DICOM images acquired across a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage. CONCLUSION: The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.

PET image reconstruction using physical and mathematical modelling for time of flight PET-MR scanners in the STIR library.

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 and magnetic resonance imaging (PET-MR) system can produce images comparable to the manufacturer. The GE SIGNA PET/MR scanner is manufactured by General Electric and has time-of-flight (TOF) capabilities of about 390 ps. All software development took place in the Software for Tomographic Image Reconstruction (STIR: http://stir.sf.net) library, which is a widely used open source software to reconstruct data as exported from emission tomography scanners. The new software developments will be integrated into STIR, providing the opportunity for researchers worldwide to establish and expand their image reconstruction methods. Furthermore, this work is of particular significance as it provides the first validation of TOF PET image reconstruction for real scanner datasets using the STIR library. This paper presents the methodology, analysis, and critical issues encountered in implementing an independent reconstruction software package. Acquired PET data were processed via several appropriate algorithms which are necessary to produce an accurate and precise quantitative image. This included mathematical, physical and anatomical modelling of the patient and simulation of various aspects of the acquisition. These included modelling of random coincidences using 'singles' rates per crystals, detector efficiencies and geometric effects. Attenuation effects were calculated by using the STIR's attenuation correction model. Modelling all these effects within the system matrix allowed the reconstruction of PET images which demonstrates the metabolic uptake of the administered radiopharmaceutical. These implementations were validated using measured phantom and clinical datasets. The developments are tested using the ordered subset expectation maximisation (OSEM) and the more recently proposed kernelised expectation maximisation (KEM) algorithm which incorporates anatomical information from MR images into PET reconstruction.

Natural History, Quality of Life, and Outcome in Cardiac Transthyretin Amyloidosis.

BACKGROUND: Transthyretin amyloidosis cardiomyopathy (ATTR-CM) is an increasingly recognized cause of heart failure in older individuals. We sought to characterize the natural history of ATTR-CM and compare outcomes and quality of life among patients with acquired and hereditary forms of the disease. METHODS: We studied 711 patients with wild-type ATTR-CM, 205 with hereditary ATTR-CM associated with the V1221 variant (V122I-hATTR-CM), and 118 with non-V122I-hATTR-CM at the UK National Amyloidosis Center between 2000 and 2017. Patients underwent prospective protocolized evaluations comprising assessment of cardiac parameters, functional status by 6-minute walk test, quality of life according to the Kansas City Cardiomyopathy Questionnaire, and survival. Hospital service usage pre- and postdiagnosis was established using English central health records in a subset of patients. RESULTS: There was substantial diagnostic delay, with patients using hospital services a median (interquartile range) of 17 (9-27) times during the 3 years before diagnosis, by which time quality of life was poor; diagnosis of wild-type ATTR-CM was delayed >4 years after presentation with cardiac symptoms in 42% of cases. Patients with V122I-hATTR-CM were more impaired functionally ( P<0.001) and had worse measures of cardiac disease ( P<0.001) at the time of diagnosis, a greater decline in quality of life, and poorer survival ( P<0.001) in comparison with the other subgroups. CONCLUSIONS: ATTR-CM is an inexorably progressive and eventually fatal cardiomyopathy associated with poor quality of life. Diagnosis is often delayed for many years after symptoms develop. Improved awareness and wider use of recently validated diagnostic imaging methods are urgently required for patients to benefit from recent therapeutic developments.

Event-by-event non-rigid data-driven PET respiratory motion correction methods: comparison of principal component analysis and centroid of distribution.

Respiratory motion is a major cause of degradation of PET image quality. Respiratory gating and motion correction can be performed to reduce the effects of respiratory motion; these methods require motion information, typically obtained from external tracking systems. Various groups have studied data-driven (DD) motion estimation methods. Recently, a DD respiratory motion estimation method was established by calculating the centroid of distribution (COD) of listmode events, which was then used with event-by-event respiratory motion correction (EBE-MC) and showed results comparable to those with an external motion tracking device. The EBE-MC method only corrected for rigid motion, so that non-rigid components still contributed to motion-induced blurring. A non-rigid respiratory motion correction (NRMC) was later developed to overcome this problem, but was only evaluated using signals from an external monitor. Thus, it is desirable to further develop DD motion estimation to achieve the best respiratory motion correction results. We evaluated two DD respiratory motion detection methods, COD and principal component analysis (PCA), by comparing the extracted motion trace to that acquired by the Anzai system in dynamic studies with two tracers. PCA was chosen as a preliminary study indicated that it produced stable results than other DD methods. We then developed and performed DD-EBE-NRMC using either COD- or PCA-derived respiratory motion information. DD correction results were compared with Anzai-based results. For all tested studies, both COD and PCA showed a good-to-excellent match with Anzai signals, with PCA showing a higher correlation with Anzai signals. The DD-EBE-NRMC results showed that both COD and PCA provide comparable image quality improvement to the Anzai-based correction. Although COD showed a lower correlation with Anzai than PCA, COD-based NRMC results are comparable to those of PCA, both of which showed great reduction in motion-induced blurring.

Sign determination methods for the respiratory signal in data-driven PET gating.

Patient respiratory motion during PET image acquisition leads to blurring in the reconstructed images and may cause significant artifacts, resulting in decreased lesion detectability, inaccurate standard uptake value calculation and incorrect treatment planning in radiation therapy. To reduce these effects data can be regrouped into (nearly) 'motion-free' gates prior to reconstruction by selecting the events with respect to the breathing phase. This gating procedure therefore needs a respiratory signal: on current scanners it is obtained from an external device, whereas with data driven (DD) methods it can be directly obtained from the raw PET data. DD methods thus eliminate the use of external equipment, which is often expensive, needs prior setup and can cause patient discomfort, and they could also potentially provide increased fidelity to the internal movement. DD methods have been recently applied on PET data showing promising results. However, many methods provide signals whose direction with respect to the physical motion is uncertain (i.e. their sign is arbitrary), therefore a maximum in the signal could refer either to the end-inspiration or end-expiration phase, possibly causing inaccurate motion correction. In this work we propose two novel methods, CorrWeights and CorrSino, to detect the correct direction of the motion represented by the DD signal, that is obtained by applying principal component analysis (PCA) on the acquired data. They only require the PET raw data, and they rely on the assumption that one of the major causes of change in the acquired data related to the chest is respiratory motion in the axial direction, that generates a cranio-caudal motion of the internal organs. We also implemented two versions of a published registration-based method, that require image reconstruction. The methods were first applied on XCAT simulations, and later evaluated on cancer patient datasets monitored by the Varian Real-time Position ManagementTM (RPM) device, selecting the lower chest bed positions. For each patient different time intervals were evaluated ranging from 50 to 300 s in duration. The novel methods proved to be generally more accurate than the registration-based ones in detecting the correct sign of the respiratory signal, and their failure rates are lower than 3% when the DD signal is highly correlated with the RPM. They also have the advantage of faster computation time, avoiding reconstruction. Moreover, CorrWeights is not specifically related to PCA and considering its simple implementation, it could easily be applied together with any DD method in clinical practice.

PET iterative reconstruction incorporating an efficient positron range correction method.

Positron range is one of the main physical effects limiting the spatial resolution of positron emission tomography (PET) images. If positrons travel inside a magnetic field, for instance inside a nuclear magnetic resonance (MR) tomograph, the mean range will be smaller but still significant. In this investigation we examined a method to correct for the positron range effect in iterative image reconstruction by including tissue-specific kernels in the forward projection operation. The correction method was implemented within STIR library (Software for Tomographic Image Reconstruction). In order to obtain the positron annihilation distribution of various radioactive isotopes in water and lung tissue, simulations were performed with the Monte Carlo package GATE [Jan et al. 2004 [1]] simulating different magnetic field intensities (0 T, 3 T, 9.5 T and 11 T) along the axial scanner direction. The positron range kernels were obtained for (68)Ga in water and lung tissue for 0 T and 3 T magnetic field voxellizing the annihilation coordinates into a three-dimensional matrix. The proposed method was evaluated using simulations of material-variant and material-invariant positron range corrections for the HYPERImage preclinical PET-MR scanner. The use of the correction resulted in sharper active region boundary definition, albeit with noise enhancement, and in the recovery of the true activity mean value of the hot regions. Moreover, in the case where a magnetic field is present, the correction accounts for the non-isotropy of the positron range effect, resulting in the recovery of resolution along the axial plane.

Maximum-likelihood joint image reconstruction and motion estimation with misaligned attenuation in TOF-PET/CT.

This work is an extension of our recent work on joint activity reconstruction/motion estimation (JRM) from positron emission tomography (PET) data. We performed JRM by maximization of the penalized log-likelihood in which the probabilistic model assumes that the same motion field affects both the activity distribution and the attenuation map. Our previous results showed that JRM can successfully reconstruct the activity distribution when the attenuation map is misaligned with the PET data, but converges slowly due to the significant cross-talk in the likelihood. In this paper, we utilize time-of-flight PET for JRM and demonstrate that the convergence speed is significantly improved compared to JRM with conventional PET data.

Maximum-Likelihood Joint Image Reconstruction/Motion Estimation in Attenuation-Corrected Respiratory Gated PET/CT Using a Single Attenuation Map.

This work provides an insight into positron emission tomography (PET) joint image reconstruction/motion estimation (JRM) by maximization of the likelihood, where the probabilistic model accounts for warped attenuation. Our analysis shows that maximum-likelihood (ML) JRM returns the same reconstructed gates for any attenuation map (µ-map) that is a deformation of a given µ-map, regardless of its alignment with the PET gates. We derived a joint optimization algorithm accordingly, and applied it to simulated and patient gated PET data. We first evaluated the proposed algorithm on simulations of respiratory gated PET/CT data based on the XCAT phantom. Our results show that independently of which µ-map is used as input to JRM: (i) the warped µ-maps correspond to the gated µ-maps, (ii) JRM outperforms the traditional post-registration reconstruction and consolidation (PRRC) for hot lesion quantification and (iii) reconstructed gated PET images are similar to those obtained with gated µ-maps. This suggests that a breath-held µ-map can be used. We then applied JRM on patient data with a µ-map derived from a breath-held high resolution CT (HRCT), and compared the results with PRRC, where each reconstructed PET image was obtained with a corresponding cine-CT gated µ-map. Results show that JRM with breath-held HRCT achieves similar reconstruction to that using PRRC with cine-CT. This suggests a practical low-dose solution for implementation of motion-corrected respiratory gated PET/CT.