Publications
1021 results found
Graf R, Schmitt J, Schlaeger S, et al., 2023, Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation., Eur Radiol Exp, Vol: 7
BACKGROUND: Automated segmentation of spinal magnetic resonance imaging (MRI) plays a vital role both scientifically and clinically. However, accurately delineating posterior spine structures is challenging. METHODS: This retrospective study, approved by the ethical committee, involved translating T1-weighted and T2-weighted images into computed tomography (CT) images in a total of 263 pairs of CT/MR series. Landmark-based registration was performed to align image pairs. We compared two-dimensional (2D) paired - Pix2Pix, denoising diffusion implicit models (DDIM) image mode, DDIM noise mode - and unpaired (SynDiff, contrastive unpaired translation) image-to-image translation using "peak signal-to-noise ratio" as quality measure. A publicly available segmentation network segmented the synthesized CT datasets, and Dice similarity coefficients (DSC) were evaluated on in-house test sets and the "MRSpineSeg Challenge" volumes. The 2D findings were extended to three-dimensional (3D) Pix2Pix and DDIM. RESULTS: 2D paired methods and SynDiff exhibited similar translation performance and DCS on paired data. DDIM image mode achieved the highest image quality. SynDiff, Pix2Pix, and DDIM image mode demonstrated similar DSC (0.77). For craniocaudal axis rotations, at least two landmarks per vertebra were required for registration. The 3D translation outperformed the 2D approach, resulting in improved DSC (0.80) and anatomically accurate segmentations with higher spatial resolution than that of the original MRI series. CONCLUSIONS: Two landmarks per vertebra registration enabled paired image-to-image translation from MRI to CT and outperformed all unpaired approaches. The 3D techniques provided anatomically correct segmentations, avoiding underprediction of small structures like the spinous process. RELEVANCE STATEMENT: This study addresses the unresolved issue of translating spinal MRI to CT, making CT-based tools usable for MRI data. It generates whole spine
Leingang O, Riedl S, Mai J, et al., 2023, Automated deep learning-based AMD detection and staging in real-world OCT datasets (PINNACLE study report 5), Scientific Reports, Vol: 13, ISSN: 2045-2322
Real-world retinal optical coherence tomography (OCT) scans are available in abundance in primary and secondary eye care centres. They contain a wealth of information to be analyzed in retrospective studies. The associated electronic health records alone are often not enough to generate a high-quality dataset for clinical, statistical, and machine learning analysis. We have developed a deep learning-based age-related macular degeneration (AMD) stage classifier, to efficiently identify the first onset of early/intermediate (iAMD), atrophic (GA), and neovascular (nAMD) stage of AMD in retrospective data. We trained a two-stage convolutional neural network to classify macula-centered 3D volumes from Topcon OCT images into 4 classes: Normal, iAMD, GA and nAMD. In the first stage, a 2D ResNet50 is trained to identify the disease categories on the individual OCT B-scans while in the second stage, four smaller models (ResNets) use the concatenated B-scan-wise output from the first stage to classify the entire OCT volume. Classification uncertainty estimates are generated with Monte-Carlo dropout at inference time. The model was trained on a real-world OCT dataset, 3765 scans of 1849 eyes, and extensively evaluated, where it reached an average ROC-AUC of 0.94 in a real-world test set.
Buchner JA, Peeken JC, Etzel L, et al., 2023, Identifying core MRI sequences for reliable automatic brain metastasis segmentation., Radiother Oncol, Vol: 188
BACKGROUND: Many automatic approaches to brain tumor segmentation employ multiple magnetic resonance imaging (MRI) sequences. The goal of this project was to compare different combinations of input sequences to determine which MRI sequences are needed for effective automated brain metastasis (BM) segmentation. METHODS: We analyzed preoperative imaging (T1-weighted sequence ± contrast-enhancement (T1/T1-CE), T2-weighted sequence (T2), and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequence) from 339 patients with BMs from seven centers. A baseline 3D U-Net with all four sequences and six U-Nets with plausible sequence combinations (T1-CE, T1, T2-FLAIR, T1-CE + T2-FLAIR, T1-CE + T1 + T2-FLAIR, T1-CE + T1) were trained on 239 patients from two centers and subsequently tested on an external cohort of 100 patients from five centers. RESULTS: The model based on T1-CE alone achieved the best segmentation performance for BM segmentation with a median Dice similarity coefficient (DSC) of 0.96. Models trained without T1-CE performed worse (T1-only: DSC = 0.70 and T2-FLAIR-only: DSC = 0.73). For edema segmentation, models that included both T1-CE and T2-FLAIR performed best (DSC = 0.93), while the remaining four models without simultaneous inclusion of these both sequences reached a median DSC of 0.81-0.89. CONCLUSIONS: A T1-CE-only protocol suffices for the segmentation of BMs. The combination of T1-CE and T2-FLAIR is important for edema segmentation. Missing either T1-CE or T2-FLAIR decreases performance. These findings may improve imaging routines by omitting unnecessary sequences, thus allowing for faster procedures in daily clinical practice while enabling optimal neural network-based target definitions.
Raab R, Küderle A, Zakreuskaya A, et al., 2023, Federated electronic health records for the European Health Data Space., Lancet Digit Health, Vol: 5, Pages: e840-e847
The European Commission's draft for the European Health Data Space (EHDS) aims to empower citizens to access their personal health data and share it with physicians and other health-care providers. It further defines procedures for the secondary use of electronic health data for research and development. Although this planned legislation is undoubtedly a step in the right direction, implementation approaches could potentially result in centralised data silos that pose data privacy and security risks for individuals. To address this concern, we propose federated personal health data spaces, a novel architecture for storing, managing, and sharing personal electronic health records that puts citizens at the centre-both conceptually and technologically. The proposed architecture puts citizens in control by storing personal health data on a combination of personal devices rather than in centralised data silos. We describe how this federated architecture fits within the EHDS and can enable the same features as centralised systems while protecting the privacy of citizens. We further argue that increased privacy and control do not contradict the use of electronic health data for research and development. Instead, data sovereignty and transparency encourage active participation in studies and data sharing. This combination of privacy-by-design and transparent, privacy-preserving data sharing can enable health-care leaders to break the privacy-exploitation barrier, which currently limits the secondary use of health data in many cases.
Marcus A, Bentley P, Rueckert D, 2023, Stroke Outcome and Evolution Prediction from CT Brain Using a Spatiotemporal Diffusion Autoencoder, Machine Learning in Clinical Neuroimaging. MLCN 2023. Lecture Notes in Computer Science, vol 14312.
Wright R, Gomez A, Zimmer VA, et al., 2023, Fast fetal head compounding from multi-view 3D ultrasound, MEDICAL IMAGE ANALYSIS, Vol: 89, ISSN: 1361-8415
Taylor TRP, Menten MJ, Rueckert D, et al., 2023, The role of the retinal vasculature in age-related macular degeneration: a spotlight on OCTA, EYE, ISSN: 0950-222X
Cruz G, Hammernik K, Kuestner T, et al., 2023, Single-heartbeat cardiac cine imaging via jointly regularized non-rigid motion corrected reconstruction, NMR in Biomedicine, Vol: 36, Pages: 1-16, ISSN: 0952-3480
PURPOSE: Develop a novel approach for 2D breath-hold cardiac cine from a single heartbeat, by combining cardiac motion corrected reconstructions and non-rigidly aligned patch-based regularization. METHODS: Conventional cardiac cine imaging is obtained via motion resolved reconstructions of data acquired over multiple heartbeats. Here, we achieve single-heartbeat cine imaging by incorporating non-rigid cardiac motion correction into the reconstruction of each cardiac phase, in conjunction with a motion-aligned patch-based regularization. The proposed Motion Corrected CINE (MC-CINE) incorporates all acquired data into the reconstruction of each (motion corrected) cardiac phase, resulting in a better posed problem than motion resolved approaches. MC-CINE was compared to iterative SENSE and XD-GRASP in fourteen healthy subjects in terms of image sharpness, reader scoring (1-5 range) and reader ranking (1-9 range) of image quality, and single-slice left ventricular assessment. RESULTS: MC-CINE was significantly superior to both iterative SENSE and XD-GRASP using 20, 2 and 1 heartbeat(s). Iterative SENSE, XD-GRASP and MC-CINE achieved sharpness of 74%, 74% and 82% using 20 heartbeats, and 53%, 66% and 82% with 1 heartbeat, respectively. Corresponding results for reader scores were 4.0, 4.7 and 4.9, with 20 heartbeats, and 1.1, 3.0 and 3.9 with 1 heartbeat. Corresponding results for reader rankings were 5.3, 7.3 and 8.6 with 20 heartbeats, and 1.0, 3.2 and 5.4 with 1 heartbeat. MC-CINE using a single heartbeat presented non-significant differences in image quality to iterative SENSE with 20 heartbeats. MC-CINE and XD-GRASP at one heartbeat both presented a non-significant negative bias of <2% in ejection fraction relative to the reference iterative SENSE. CONCLUSION: The proposed MC-CINE significantly improves image quality relative to iterative SENSE and XD-GRASP, enabling 2D cine from a single heartbeat.
Al-Jibury E, King JWD, Guo Y, et al., 2023, A deep learning method for replicate-based analysis of chromosome conformation contacts using Siamese neural networks, Nature Communications, Vol: 14, ISSN: 2041-1723
The organisation of the genome in nuclear space is an important frontier of biology. Chromosome conformation capture methods such as Hi-C and Micro-C produce genome-wide chromatin contact maps that provide rich data containing quantitative and qualitative information about genome architecture. Most conventional approaches to genome-wide chromosome conformation capture data are limited to the analysis of pre-defined features, and may therefore miss important biological information. One constraint is that biologically important features can be masked by high levels of technical noise in the data. Here we introduce a replicate-based method for deep learning from chromatin conformation contact maps. Using a Siamese network configuration our approach learns to distinguish technical noise from biological variation and outperforms image similarity metrics across a range of biological systems. The features extracted from Hi-C maps after perturbation of cohesin and CTCF reflect the distinct biological functions of cohesin and CTCF in the formation of domains and boundaries, respectively. The learnt distance metrics are biologically meaningful, as they mirror the density of cohesin and CTCF binding. These properties make our method a powerful tool for the exploration of chromosome conformation capture data, such as Hi-C capture Hi-C, and Micro-C.
Meiser P, Knolle MA, Hirschberger A, et al., 2023, A distinct stimulatory cDC1 subpopulation amplifies CD8+T cell responses in tumors for protective anti-cancer immunity, CANCER CELL, Vol: 41, Pages: 1498-+, ISSN: 1535-6108
- Author Web Link
- Cite
- Citations: 1
Anders P, Traber GL, Pfau M, et al., 2023, Comparison of Novel Volumetric Microperimetry Metrics in Intermediate Age-Related Macular Degeneration: PINNACLE Study Report 3., Transl Vis Sci Technol, Vol: 12
PURPOSE: To investigate and compare novel volumetric microperimetry (MP)-derived metrics in intermediate age-related macular degeneration (iAMD), as current MP metrics show high variability and low sensitivity. METHODS: This is a cross-sectional analysis of microperimetry baseline data from the multicenter, prospective PINNACLE study (ClinicalTrials.gov NCT04269304). The Visual Field Modeling and Analysis (VFMA) software and an open-source implementation (OSI) were applied to calculate MP-derived hill-of-vison (HOV) surface plots and the total volume (VTOT) beneath the plots. Bland-Altman plots were used for methodologic comparison, and the association of retinal sensitivity metrics with explanatory variables was tested with mixed-effects models. RESULTS: In total, 247 eyes of 189 participants (75 ± 7.3 years) were included in the analysis. The VTOT output of VFMA and OSI exhibited a significant difference (P < 0.0001). VFMA yielded slightly higher coefficients of determination than OSI and mean sensitivity (MS) in univariable and multivariable modeling, for example, in association with low-luminance visual acuity (LLVA) (marginal R2/conditional R2: VFMA 0.171/0.771, OSI 0.162/0.765, MS 0.133/0.755). In the multivariable analysis, LLVA was the only demonstrable predictor of VFMA VTOT (t-value, P-value: -7.5, <0.001) and MS (-6.5, <0.001). CONCLUSIONS: The HOV-derived metric of VTOT exhibits favorable characteristics compared to MS in evaluating retinal sensitivity. The output of VFMA and OSI is not exactly interchangeable in this cross-sectional analysis. Longitudinal analysis is necessary to assess their performance in ability-to-detect change. TRANSLATIONAL RELEVANCE: This study explores new volumetric MP endpoints for future application in therapeutic trials in iAMD and reports specific characteristics of the available HOV software applications.
Woodrow RE, Winzeck S, Luppi A, et al., 2023, Acute thalamic connectivity precedes chronic post-concussive symptoms in mild traumatic brain injury, BRAIN, Vol: 146, Pages: 3484-3499, ISSN: 0006-8950
- Author Web Link
- Cite
- Citations: 2
Usynin D, Rueckert D, Kaissis G, 2023, Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks, ACM TRANSACTIONS ON PRIVACY AND SECURITY, Vol: 26, ISSN: 2471-2566
Sitaru S, Oueslati T, Schielein MC, et al., 2023, [Automatische Körperteil-Identifikation in dermatologischen klinischen Bildern durch maschinelles Lernen]., J Dtsch Dermatol Ges, Vol: 21, Pages: 863-871
Sitaru S, Oueslati T, Schielein MC, et al., 2023, Automatic body part identification in real-world clinical dermatological images using machine learning, JOURNAL DER DEUTSCHEN DERMATOLOGISCHEN GESELLSCHAFT, Vol: 21, Pages: 863-869, ISSN: 1610-0379
Mikolić A, Steyerberg EW, Polinder S, et al., 2023, Prognostic Models for Global Functional Outcome and Post-Concussion Symptoms Following Mild Traumatic Brain Injury: A Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) Study., J Neurotrauma, Vol: 40, Pages: 1651-1670
After mild traumatic brain injury (mTBI), a substantial proportion of individuals do not fully recover on the Glasgow Outcome Scale Extended (GOSE) or experience persistent post-concussion symptoms (PPCS). We aimed to develop prognostic models for the GOSE and PPCS at 6 months after mTBI and to assess the prognostic value of different categories of predictors (clinical variables; questionnaires; computed tomography [CT]; blood biomarkers). From the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study, we included participants aged 16 or older with Glasgow Coma Score (GCS) 13-15. We used ordinal logistic regression to model the relationship between predictors and the GOSE, and linear regression to model the relationship between predictors and the Rivermead Post-concussion Symptoms Questionnaire (RPQ) total score. First, we studied a pre-specified Core model. Next, we extended the Core model with other clinical and sociodemographic variables available at presentation (Clinical model). The Clinical model was then extended with variables assessed before discharge from hospital: early post-concussion symptoms, CT variables, biomarkers, or all three categories (extended models). In a subset of patients mostly discharged home from the emergency department, the Clinical model was extended with 2-3-week post-concussion and mental health symptoms. Predictors were selected based on Akaike's Information Criterion. Performance of ordinal models was expressed as a concordance index (C) and performance of linear models as proportion of variance explained (R2). Bootstrap validation was used to correct for optimism. We included 2376 mTBI patients with 6-month GOSE and 1605 patients with 6-month RPQ. The Core and Clinical models for GOSE showed moderate discrimination (C = 0.68 95% confidence interval 0.68 to 0.70 and C = 0.70[0.69 to 0.71], respectively) and injury severity was the strongest predictor. The
Foellmer B, Williams MCC, Dey D, et al., 2023, Roadmap on the use of artificial intelligence for imaging of vulnerable atherosclerotic plaque in coronary arteries, NATURE REVIEWS CARDIOLOGY, ISSN: 1759-5002
Karolis VR, Fitzgibbon SP, Cordero-Grande L, et al., 2023, Maturational networks of human fetal brain activity reveal emerging connectivity patterns prior to ex-utero exposure, COMMUNICATIONS BIOLOGY, Vol: 6
Mueller TT, Paetzold JC, Prabhakar C, et al., 2023, Differentially Private Graph Neural Networks for Whole-Graph Classification, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vol: 45, Pages: 7308-7318, ISSN: 0162-8828
Sutton J, Menten MJ, Riedl S, et al., 2023, Correction: Developing and validating a multivariable prediction model which predicts progression of intermediate to late age-related macular degeneration-the PINNACLE trial protocol, Eye, Vol: 37, Pages: 1-1, ISSN: 0950-222X
Anders P, Traber G, Pfau M, et al., 2023, Regional Variation of Retinal Sensitivity in Intermediate AMD in the PINNACLE study, Annual Meeting of the Association-for-Research-in-Vision-and-Ophthalmology (ARVO), Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Menten M, Kreitner L, Paetzold J, et al., 2023, Synthetic data facilitates deep-learning-based segmentation of OCT angiography images without human annotations, Annual Meeting of the Association-for-Research-in-Vision-and-Ophthalmology (ARVO), Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Chakravarty A, Emre T, Leingang O, et al., 2023, Self-supervised machine learning for individual prediction of conversion to neovascular AMD in PINNACLE study, Annual Meeting of the Association-for-Research-in-Vision-and-Ophthalmology (ARVO), Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Paetzold JCC, Lux L, Kreitner L, et al., 2023, Geometric deep learning for disease classification in OCTA images, Annual Meeting of the Association-for-Research-in-Vision-and-Ophthalmology (ARVO), Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Holland R, Leingang O, Hagag AM, et al., 2023, Deep-learning-based clustering of OCT images for automated biomarker discovery in age-related macular degeneration, Annual Meeting of the Association-for-Research-in-Vision-and-Ophthalmology (ARVO), Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Fayed AE, Menten MJ, Kreitner L, et al., 2023, Retinal Vasculature of Different Diameters and Plexuses Exhibit Distinct Vulnerability to Varying Stages of Diabetic Retinopathy, Annual Meeting of the Association-for-Research-in-Vision-and-Ophthalmology (ARVO), Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Williams LZJ, Fitzgibbon SP, Bozek J, et al., 2023, Structural and functional asymmetry of the neonatal cerebral cortex, NATURE HUMAN BEHAVIOUR, Vol: 7, Pages: 942-955, ISSN: 2397-3374
- Author Web Link
- Cite
- Citations: 3
Cullen H, Dimitrakopoulou K, Patel H, et al., 2023, Common genetic variability associated with years of education and cognitive performance predicts language outcomes at two, 55th European-Society-of-Human-Genetics (ESHG) Conference, Publisher: SPRINGERNATURE, Pages: 339-339, ISSN: 1018-4813
Fenn-Moltu S, Fitzgibbon SP, Ciarrusta J, et al., 2023, Development of neonatal brain functional centrality and alterations associated with preterm birth, Cerebral Cortex, Vol: 33, Pages: 5585-5596, ISSN: 1047-3211
Formation of the functional connectome in early life underpins future learning and behavior. However, our understanding of how the functional organization of brain regions into interconnected hubs (centrality) matures in the early postnatal period is limited, especially in response to factors associated with adverse neurodevelopmental outcomes such as preterm birth. We characterized voxel-wise functional centrality (weighted degree) in 366 neonates from the Developing Human Connectome Project. We tested the hypothesis that functional centrality matures with age at scan in term-born babies and is disrupted by preterm birth. Finally, we asked whether neonatal functional centrality predicts general neurodevelopmental outcomes at 18 months. We report an age-related increase in functional centrality predominantly within visual regions and a decrease within the motor and auditory regions in term-born infants. Preterm-born infants scanned at term equivalent age had higher functional centrality predominantly within visual regions and lower measures in motor regions. Functional centrality was not related to outcome at 18 months old. Thus, preterm birth appears to affect functional centrality in regions undergoing substantial development during the perinatal period. Our work raises the question of whether these alterations are adaptive or disruptive and whether they predict neurodevelopmental characteristics that are more subtle or emerge later in life.
Sutton J, Menten MJ, Riedl S, et al., 2023, Developing and validating a multivariable prediction model which predicts progression of intermediate to late age-related macular degeneration-the PINNACLE trial protocol, Eye, Vol: 37, Pages: 1275-1283, ISSN: 0950-222X
AimsAge-related macular degeneration (AMD) is characterised by a progressive loss of central vision. Intermediate AMD is a risk factor for progression to advanced stages categorised as geographic atrophy (GA) and neovascular AMD. However, rates of progression to advanced stages vary between individuals. Recent advances in imaging and computing technologies have enabled deep phenotyping of intermediate AMD. The aim of this project is to utilise machine learning (ML) and advanced statistical modelling as an innovative approach to discover novel features and accurately quantify markers of pathological retinal ageing that can individualise progression to advanced AMD.MethodsThe PINNACLE study consists of both retrospective and prospective parts. In the retrospective part, more than 400,000 optical coherent tomography (OCT) images collected from four University Teaching Hospitals and the UK Biobank Population Study are being pooled, centrally stored and pre-processed. With this large dataset featuring eyes with AMD at various stages and healthy controls, we aim to identify imaging biomarkers for disease progression for intermediate AMD via supervised and unsupervised ML. The prospective study part will firstly characterise the progression of intermediate AMD in patients followed between one and three years; secondly, it will validate the utility of biomarkers identified in the retrospective cohort as predictors of progression towards late AMD. Patients aged 55–90 years old with intermediate AMD in at least one eye will be recruited across multiple sites in UK, Austria and Switzerland for visual function tests, multimodal retinal imaging and genotyping. Imaging will be repeated every four months to identify early focal signs of deterioration on spectral-domain optical coherence tomography (OCT) by human graders. A focal event triggers more frequent follow-up with visual function and imaging tests. The primary outcome is the sensitivity and specificity of the OCT ima
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.