Publications
1021 results found
Kaissis G, Knolle M, Jungmann F, et al., 2022, A UNIFIED INTERPRETATION OF THE GAUSSIAN MECHANISM FOR DIFFERENTIAL PRIVACY THROUGH THE SENSITIVITY INDEX, Journal of Privacy and Confidentiality, Vol: 12
The Gaussian mechanism (GM) represents a universally employed tool for achieving differential privacy (DP), and a large body of work has been devoted to its analysis. We argue that the three prevailing interpretations of the GM, namely (ε, δ)-DP, f-DP and Rényi DP can be expressed by using a single parameter ψ, which we term the sensitivity index. ψ uniquely characterises the GM and its properties by encapsulating its two fundamental quantities: the sensitivity of the query and the magnitude of the noise perturbation. With strong links to the ROC curve and the hypothesis-testing interpretation of DP, ψ offers the practitioner a powerful method for interpreting, comparing and communicating the privacy guarantees of Gaussian mechanisms.
Åkerlund CAI, Holst A, Stocchetti N, et al., 2022, Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study., Crit Care, Vol: 26
BACKGROUND: While the Glasgow coma scale (GCS) is one of the strongest outcome predictors, the current classification of traumatic brain injury (TBI) as 'mild', 'moderate' or 'severe' based on this fails to capture enormous heterogeneity in pathophysiology and treatment response. We hypothesized that data-driven characterization of TBI could identify distinct endotypes and give mechanistic insights. METHODS: We developed an unsupervised statistical clustering model based on a mixture of probabilistic graphs for presentation (< 24 h) demographic, clinical, physiological, laboratory and imaging data to identify subgroups of TBI patients admitted to the intensive care unit in the CENTER-TBI dataset (N = 1,728). A cluster similarity index was used for robust determination of optimal cluster number. Mutual information was used to quantify feature importance and for cluster interpretation. RESULTS: Six stable endotypes were identified with distinct GCS and composite systemic metabolic stress profiles, distinguished by GCS, blood lactate, oxygen saturation, serum creatinine, glucose, base excess, pH, arterial partial pressure of carbon dioxide, and body temperature. Notably, a cluster with 'moderate' TBI (by traditional classification) and deranged metabolic profile, had a worse outcome than a cluster with 'severe' GCS and a normal metabolic profile. Addition of cluster labels significantly improved the prognostic precision of the IMPACT (International Mission for Prognosis and Analysis of Clinical trials in TBI) extended model, for prediction of both unfavourable outcome and mortality (both p < 0.001). CONCLUSIONS: Six stable and clinically distinct TBI endotypes were identified by probabilistic unsupervised clustering. In addition to presenting neurology, a profile of biochemical derangement was found to be an important distinguishing feature that was both biologically plausible and associated with outcome. Our work motivates
Ciarrusta J, Christiaens D, Fitzgibbon SP, et al., 2022, The developing brain structural and functional connectome fingerprint, Developmental Cognitive Neuroscience, Vol: 55, ISSN: 1878-9293
In the mature brain, structural and functional ‘fingerprints’ of brain connectivity can be used to identify the uniqueness of an individual. However, whether the characteristics that make a given brain distinguishable from others already exist at birth remains unknown. Here, we used neuroimaging data from the developing Human Connectome Project (dHCP) of preterm born neonates who were scanned twice during the perinatal period to assess the developing brain fingerprint. We found that 62% of the participants could be identified based on the congruence of the later structural connectome to the initial connectivity matrix derived from the earlier timepoint. In contrast, similarity between functional connectomes of the same subject at different time points was low. Only 10% of the participants showed greater self-similarity in comparison to self-to-other-similarity for the functional connectome. These results suggest that structural connectivity is more stable in early life and can represent a potential connectome fingerprint of the individual: a relatively stable structural connectome appears to support a changing functional connectome at a time when neonates must rapidly acquire new skills to adapt to their new environment.
Anders P, Traber GL, Hagag AM, et al., 2022, Investigation of intermediate AMD with MAIA microperimetry metrics by the PINNACLE Consortium, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Lotery AJ, Hagag AM, Kaye R, et al., 2022, Risk factors for progression of intermediate age-related macular degeneration: A systematic review and meta-analysis, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Riedl S, Vogl W-D, Leingang O, et al., 2022, Automated detection of morphologic changes on SD-OCT leading toward outer retinal atrophy in intermediate age-related macular degeneration in the prospective PINNACLE trial, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Hagag AM, Riedl S, Prevost T, et al., 2022, Adaptive optics phenotypes of intermediate age-related macular degeneration, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Böhm JK, Schaeben V, Schäfer N, et al., 2022, Extended Coagulation Profiling in Isolated Traumatic Brain Injury: A CENTER-TBI Analysis., Neurocrit Care, Vol: 36, Pages: 927-941
BACKGROUND: Trauma-induced coagulopathy in traumatic brain injury (TBI) remains associated with high rates of complications, unfavorable outcomes, and mortality. The underlying mechanisms are largely unknown. Embedded in the prospective multinational Collaborative European Neurotrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study, coagulation profiles beyond standard conventional coagulation assays were assessed in patients with isolated TBI within the very early hours of injury. METHODS: Results from blood samples (citrate/EDTA) obtained on hospital admission were matched with clinical and routine laboratory data of patients with TBI captured in the CENTER-TBI central database. To minimize confounding factors, patients with strictly isolated TBI (iTBI) (n = 88) were selected and stratified for coagulopathy by routine international normalized ratio (INR): (1) INR < 1.2 and (2) INR ≥ 1.2. An INR > 1.2 has been well adopted over time as a threshold to define trauma-related coagulopathy in general trauma populations. The following parameters were evaluated: quick's value, activated partial thromboplastin time, fibrinogen, thrombin time, antithrombin, coagulation factor activity of factors V, VIII, IX, and XIII, protein C and S, plasminogen, D-dimer, fibrinolysis-regulating parameters (thrombin activatable fibrinolysis inhibitor, plasminogen activator inhibitor 1, antiplasmin), thrombin generation, and fibrin monomers. RESULTS: Patients with iTBI with INR ≥ 1.2 (n = 16) had a high incidence of progressive intracranial hemorrhage associated with increased mortality and unfavorable outcome compared with patients with INR < 1.2 (n = 72). Activity of coagulation factors V, VIII, IX, and XIII dropped on average by 15-20% between the groups whereas protein C and S levels dropped by 20%. With an elevated INR, thromb
Ceyisakar IE, Huijben JA, Maas AIR, et al., 2022, Can We Cluster ICU Treatment Strategies for Traumatic Brain Injury by Hospital Treatment Preferences?, Neurocrit Care, Vol: 36, Pages: 846-856
BACKGROUND: In traumatic brain injury (TBI), large between-center differences in treatment and outcome for patients managed in the intensive care unit (ICU) have been shown. The aim of this study is to explore if European neurotrauma centers can be clustered, based on their treatment preference in different domains of TBI care in the ICU. METHODS: Provider profiles of centers participating in the Collaborative European Neurotrauma Effectiveness Research in TBI study were used to assess correlations within and between the predefined domains: intracranial pressure monitoring, coagulation and transfusion, surgery, prophylactic antibiotics, and more general ICU treatment policies. Hierarchical clustering using Ward's minimum variance method was applied to group data with the highest similarity. Heat maps were used to visualize whether hospitals could be grouped to uncover types of hospitals adhering to certain treatment strategies. RESULTS: Provider profiles were available from 66 centers in 20 different countries in Europe and Israel. Correlations within most of the predefined domains varied from low to high correlations (mean correlation coefficients 0.2-0.7). Correlations between domains were lower, with mean correlation coefficients of 0.2. Cluster analysis showed that policies could be grouped, but hospitals could not be grouped based on their preference. CONCLUSIONS: Although correlations between treatment policies within domains were found, the failure to cluster hospitals indicates that a specific treatment choice within a domain is not a proxy for other treatment choices within or outside the domain. These results imply that studying the effects of specific TBI interventions on outcome can be based on between-center variation without being substantially confounded by other treatments. TRIAL REGISTRATION: We do not report the results of a health care intervention.
Holland R, Menten MJ, Leingang O, et al., 2022, Self-supervised pretraining enables deep learning-based classification of AMD with fewer annotations, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
- Author Web Link
- Cite
- Citations: 1
Menten MJ, Leingang O, Bogunovic H, et al., 2022, Discovery of imaging biomarkers for healthy aging and age-related macular degeneration using counterfactual generative adversarial networks, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Lachmann M, Rippen E, Rueckert D, et al., 2022, Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis., Eur Heart J Digit Health, Vol: 3, Pages: 153-168
AIMS: Hypothesizing that aortic outflow velocity profiles contain more valuable information about aortic valve obstruction and left ventricular contractility than can be captured by the human eye, features of the complex geometry of Doppler tracings from patients with severe aortic stenosis (AS) were extracted by a convolutional neural network (CNN). METHODS AND RESULTS: After pre-training a CNN (VGG-16) on a large data set (ImageNet data set; 14 million images belonging to 1000 classes), the convolutional part was employed to transform Doppler tracings to 1D arrays. Among 366 eligible patients [age: 79.8 ± 6.77 years; 146 (39.9%) women] with pre-procedural echocardiography and right heart catheterization prior to transcatheter aortic valve replacement (TAVR), good quality Doppler tracings from 101 patients were analysed. The convolutional part of the pre-trained VGG-16 model in conjunction with principal component analysis and k-means clustering distinguished two shapes of aortic outflow velocity profiles. Kaplan-Meier analysis revealed that mortality in patients from Cluster 2 (n = 40, 39.6%) was significantly increased [hazard ratio (HR) for 2-year mortality: 3; 95% confidence interval (CI): 1-8.9]. Apart from reduced cardiac output and mean aortic valve gradient, patients from Cluster 2 were also characterized by signs of pulmonary hypertension, impaired right ventricular function, and right atrial enlargement. After training an extreme gradient boosting algorithm on these 101 patients, validation on the remaining 265 patients confirmed that patients assigned to Cluster 2 show increased mortality (HR for 2-year mortality: 2.6; 95% CI: 1.4-5.1, P-value: 0.004). CONCLUSION: Transfer learning enables sophisticated pattern recognition even in clinical data sets of limited size. Importantly, it is the left ventricular compensation capacity in the face of increased afterload, and not so much the actual obstruction of the aortic valve, that determines fate after
Leingang O, Bogunovic H, Riedl S, et al., 2022, Automated deep learning-based AMD stage detection in real-world OCT datasets, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Edwards AD, Rueckert D, Smith SM, et al., 2022, The Developing Human Connectome Project Neonatal Data Release, FRONTIERS IN NEUROSCIENCE, Vol: 16
- Author Web Link
- Open Access Link
- Cite
- Citations: 12
Thomas I, Dickens AM, Posti JP, et al., 2022, Serum metabolome associated with severity of acute traumatic brain injury., Nat Commun, Vol: 13
Complex metabolic disruption is a crucial aspect of the pathophysiology of traumatic brain injury (TBI). Associations between this and systemic metabolism and their potential prognostic value are poorly understood. Here, we aimed to describe the serum metabolome (including lipidome) associated with acute TBI within 24 h post-injury, and its relationship to severity of injury and patient outcome. We performed a comprehensive metabolomics study in a cohort of 716 patients with TBI and non-TBI reference patients (orthopedic, internal medicine, and other neurological patients) from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) cohort. We identified panels of metabolites specifically associated with TBI severity and patient outcomes. Choline phospholipids (lysophosphatidylcholines, ether phosphatidylcholines and sphingomyelins) were inversely associated with TBI severity and were among the strongest predictors of TBI patient outcomes, which was further confirmed in a separate validation dataset of 558 patients. The observed metabolic patterns may reflect different pathophysiological mechanisms, including protective changes of systemic lipid metabolism aiming to maintain lipid homeostasis in the brain.
Ziller A, Mueller TT, Braren R, et al., 2022, Privacy: An Axiomatic Approach, ENTROPY, Vol: 24
Dou Q, So TY, Jiang M, et al., 2022, Author Correction: Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study, npj Digital Medicine, Vol: 5, ISSN: 2398-6352
Correction to: npj Digital Medicine https://doi.org/10.1038/s41746-021-00431-6, published online 29 March 2021
Thanaj M, Mielke J, McGurk K, et al., 2022, Genetic and environmental determinants of diastolic heart function, Nature Cardiovascular Research, Vol: 1, Pages: 361-371, ISSN: 2731-0590
Diastole is the sequence of physiological events that occur in the heart during ventricular filling and principally depends onmyocardial relaxation and chamber stiffness. Abnormal diastolic function is related to many cardiovascular disease processesand is predictive of health outcomes, but its genetic architecture is largely unknown. Here, we use machine learning cardiacmotion analysis to measure diastolic functional traits in 39,559 participants of the UK Biobank and perform a genome-wideassociation study. We identified 9 significant, independent loci near genes that are associated with maintaining sarcomericfunction under biomechanical stress and genes implicated in the development of cardiomyopathy. Age, sex and diabetes wereindependent predictors of diastolic function and we found a causal relationship between genetically-determined ventricularstiffness and incident heart failure. Our results provide insights into the genetic and environmental factors influencing diastolicfunction that are relevant for identifying causal relationships and potential tractable targets.
Gale-Grant O, Fenn-Moltu S, França LGS, et al., 2022, Effects of gestational age at birth on perinatal structural brain development in healthy term-born babies, Human Brain Mapping, Vol: 43, Pages: 1577-1589, ISSN: 1065-9471
Infants born in early term (37-38 weeks gestation) experience slower neurodevelopment than those born at full term (40-41 weeks gestation). While this could be due to higher perinatal morbidity, gestational age at birth may also have a direct effect on the brain. Here we characterise brain volume and white matter correlates of gestational age at birth in healthy term-born neonates and their relationship to later neurodevelopmental outcome using T2 and diffusion weighted MRI acquired in the neonatal period from a cohort (n = 454) of healthy babies born at term age (>37 weeks gestation) and scanned between 1 and 41 days after birth. Images were analysed using tensor-based morphometry and tract-based spatial statistics. Neurodevelopment was assessed at age 18 months using the Bayley Scales of Infant and Toddler Development, Third Edition (Bayley-III). Infants born earlier had higher relative ventricular volume and lower relative brain volume in the deep grey matter, cerebellum and brainstem. Earlier birth was also associated with lower fractional anisotropy, higher mean, axial, and radial diffusivity in major white matter tracts. Gestational age at birth was positively associated with all Bayley-III subscales at age 18 months. Regression models predicting outcome from gestational age at birth were significantly improved after adding neuroimaging features associated with gestational age at birth. This work adds to the body of evidence of the impact of early term birth and highlights the importance of considering the effect of gestational age at birth in future neuroimaging studies including term-born babies.
Fenchel D, Dimitrova R, Robinson EC, et al., 2022, Neonatal multi-modal cortical profiles predict 18-month developmental outcomes, DEVELOPMENTAL COGNITIVE NEUROSCIENCE, Vol: 54, ISSN: 1878-9293
- Author Web Link
- Cite
- Citations: 7
Davies RH, Augusto JB, Bhuva A, et al., 2022, Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning, Journal of Cardiovascular Magnetic Resonance, Vol: 24, ISSN: 1097-6647
BackgroundMeasurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions. This is best assessed using cardiovascular magnetic resonance (CMR), but image analysis is currently performed by individual clinicians, which introduces error. We sought to develop a machine learning algorithm for volumetric analysis of CMR images with demonstrably better precision than human analysis.MethodsA fully automated machine learning algorithm was trained on 1923 scans (10 scanner models, 13 institutions, 9 clinical conditions, 60,000 contours) and used to segment the LV blood volume and myocardium. Performance was quantified by measuring precision on an independent multi-site validation dataset with multiple pathologies with n = 109 patients, scanned twice. This dataset was augmented with a further 1277 patients scanned as part of routine clinical care to allow qualitative assessment of generalization ability by identifying mis-segmentations. Machine learning algorithm (‘machine’) performance was compared to three clinicians (‘human’) and a commercial tool (cvi42, Circle Cardiovascular Imaging).FindingsMachine analysis was quicker (20 s per patient) than human (13 min). Overall machine mis-segmentation rate was 1 in 479 images for the combined dataset, occurring mostly in rare pathologies not encountered in training. Without correcting these mis-segmentations, machine analysis had superior precision to three clinicians (e.g. scan-rescan coefficients of variation of human vs machine: LVEF 6.0% vs 4.2%, LV mass 4.8% vs. 3.6%; both P < 0.05), translating to a 46% reduction in required trial sample size using an LVEF endpoint.ConclusionWe present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.
Falkai P, Koutsouleris N, Bertsch K, et al., 2022, Concept of the Munich/Augsburg Consortium Precision in Mental Health for the German Center of Mental Health, Frontiers in Psychiatry, Vol: 13
The Federal Ministry of Education and Research (BMBF) issued a call for a new nationwide research network on mental disorders, the German Center of Mental Health (DZPG). The Munich/Augsburg consortium was selected to participate as one of six partner sites with its concept “Precision in Mental Health (PriMe): Understanding, predicting, and preventing chronicity.” PriMe bundles interdisciplinary research from the Ludwig-Maximilians-University (LMU), Technical University of Munich (TUM), University of Augsburg (UniA), Helmholtz Center Munich (HMGU), and Max Planck Institute of Psychiatry (MPIP) and has a focus on schizophrenia (SZ), bipolar disorder (BPD), and major depressive disorder (MDD). PriMe takes a longitudinal perspective on these three disorders from the at-risk stage to the first-episode, relapsing, and chronic stages. These disorders pose a major health burden because in up to 50% of patients they cause untreatable residual symptoms, which lead to early social and vocational disability, comorbidities, and excess mortality. PriMe aims at reducing mortality on different levels, e.g., reducing death by psychiatric and somatic comorbidities, and will approach this goal by addressing interdisciplinary and cross-sector approaches across the lifespan. PriMe aims to add a precision medicine framework to the DZPG that will propel deeper understanding, more accurate prediction, and personalized prevention to prevent disease chronicity and mortality across mental illnesses. This framework is structured along the translational chain and will be used by PriMe to innovate the preventive and therapeutic management of SZ, BPD, and MDD from rural to urban areas and from patients in early disease stages to patients with long-term disease courses. Research will build on platforms that include one on model systems, one on the identification and validation of predictive markers, one on the development of novel multimodal treatments, one on the regulation and streng
Meng Q, Bai W, Liu T, et al., 2022, Multiview Motion Estimation for 3D cardiac motion tracking
Code for paper ''MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRI''
Ouyang C, Biffi C, Chen C, et al., 2022, Self-supervised learning for few-shot medical image segmentation, IEEE Transactions on Medical Imaging, Vol: 41, Pages: 1837-1848, ISSN: 0278-0062
Fully-supervised deep learning segmentation models are inflexible when encountering new unseen semantic classes and their fine-tuning often requires significant amounts of annotated data. Few-shot semantic segmentation (FSS) aims to solve this inflexibility by learning to segment an arbitrary unseen semantically meaningful class by referring to only a few labeled examples, without involving fine-tuning. State-of-the-art FSS methods are typically designed for segmenting natural images and rely on abundant annotated data of training classes to learn image representations that generalize well to unseen testing classes. However, such a training mechanism is impractical in annotation-scarce medical imaging scenarios. To address this challenge, in this work, we propose a novel self-supervised FSS framework for medical images, named SSL-ALPNet, in order to bypass the requirement for annotations during training. The proposed method exploits superpixel-based pseudo-labels to provide supervision signals. In addition, we propose a simple yet effective adaptive local prototype pooling module which is plugged into the prototype networks to further boost segmentation accuracy. We demonstrate the general applicability of the proposed approach using three different tasks: organ segmentation of abdominal CT and MRI images respectively, and cardiac segmentation of MRI images. The proposed method yields higher Dice scores than conventional FSS methods which require manual annotations for training in our experiments.
Chen Y, Schönlieb C-B, Liò P, et al., 2022, AI-based reconstruction for fast MRI – a systematic review and meta-analysis, Proceedings of the Institute of Electrical and Electronics Engineers (IEEE), Vol: 110, Pages: 224-245, ISSN: 0018-9219
Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process. With the resurgence of artificial intelligence, deep neural networks and CS algorithms are being integrated to redefine the state of the art of fast MRI. The past several years have witnessed substantial growth in the complexity, diversity, and performance of deep learning-based CS techniques that are dedicated to fastMRI. In this meta-analysis, we systematically review the deep learning-based CS techniques for fast MRI, describe key model designs, highlight breakthroughs, and discuss promising directions. We have also introduced a comprehensive analysis framework and a classification system to assess the pivotal role of deep learning in CS-based accelerationfor MRI.
Galimberti S, Graziano F, Maas AIR, et al., 2022, Effect of frailty on 6-month outcome after traumatic brain injury: a multicentre cohort study with external validation., Lancet Neurol, Vol: 21, Pages: 153-162
BACKGROUND: Frailty is known to be associated with poorer outcomes in individuals admitted to hospital for medical conditions requiring intensive care. However, little evidence is available for the effect of frailty on patients' outcomes after traumatic brain injury. Many frailty indices have been validated for clinical practice and show good performance to predict clinical outcomes. However, each is specific to a particular clinical context. We aimed to develop a frailty index to predict 6-month outcomes in patients after a traumatic brain injury. METHODS: A cumulative deficit approach was used to create a novel frailty index based on 30 items dealing with disease states, current medications, and laboratory values derived from data available from CENTER-TBI, a prospective, longitudinal observational study of patients with traumatic brain injury presenting within 24 h of injury and admitted to a ward or an intensive care unit at 65 centres in Europe between Dec 19, 2014, and Dec 17, 2017. From the individual cumulative CENTER-TBI frailty index (range 0-30), we obtained a standardised value (range 0-1), with high scores indicating higher levels of frailty. The effect of frailty on 6-month outcome evaluated with the extended Glasgow Outcome Scale (GOSE) was assessed through a proportional odds logistic model adjusted for known outcome predictors. An unfavourable outcome was defined as death or severe disability (GOSE score ≤4). External validation was performed on data from TRACK-TBI, a prospective observational study co-designed with CENTER-TBI, which enrolled patients with traumatic brain injury at 18 level I trauma centres in the USA from Feb 26, 2014, to July 27, 2018. CENTER-TBI is registered with ClinicalTrials.gov, NCT02210221; TRACK-TBI is registered at ClinicalTrials.gov, NCT02119182. FINDINGS: 2993 participants (median age was 51 years [IQR 30-67], 2058 [69%] were men) were included in this analysis. The overall median CENTER-TBI frailty index score was 0
Hinterwimmer F, Lazic I, Suren C, et al., 2022, Machine learning in knee arthroplasty: specific data are key-a systematic review., Knee Surg Sports Traumatol Arthrosc, Vol: 30, Pages: 376-388
PURPOSE: Artificial intelligence (AI) in healthcare is rapidly growing and offers novel options of data analysis. Machine learning (ML) represents a distinct application of AI, which is capable of generating predictions and has already been tested in different medical specialties with various approaches such as diagnostic applications, cost predictions or identification of risk factors. In orthopaedics, this technology has only recently been introduced and the literature on ML in knee arthroplasty is scarce. In this review, we aim to investigate which predictions are already feasible using ML models in knee arthroplasty to identify prerequisites for the effective use of this novel approach. For this reason, we conducted a systematic review of ML algorithms for outcome prediction in knee arthroplasty. METHODS: A comprehensive search of PubMed, Medline database and the Cochrane Library was conducted to find ML applications for knee arthroplasty. All relevant articles were systematically retrieved and evaluated by an orthopaedic surgeon and a data scientist on the basis of the PRISMA statement. The search strategy yielded 225 articles of which 19 were finally assessed as eligible. A modified Coleman Methodology Score (mCMS) was applied to account for a methodological evaluation. RESULTS: The studies presented in this review demonstrated fair to good results (AUC median 0.76/range 0.57-0.98), while heterogeneous prediction models were analysed: complications (6), costs (4), functional outcome (3), revision (2), postoperative satisfaction (2), surgical technique (1) and biomechanical properties (1) were investigated. The median mCMS was 65 (range 40-80) points. CONCLUSION: The prediction of distinct outcomes with ML models applying specific data is already feasible; however, the prediction of more complex outcomes is still inaccurate. Registry data on knee arthroplasty have not been fully analysed yet so that specific parameters have not been sufficiently evaluated. The
Nasirigerdeh R, Torkzadehmahani R, Matschinske J, et al., 2022, sPLINK: a hybrid federated tool as a robust alternative to meta-analysis in genome-wide association studies, GENOME BIOLOGY, Vol: 23, ISSN: 1474-760X
- Author Web Link
- Cite
- Citations: 7
Liu T, Meng Q, Huang J-J, et al., 2022, Video summarization through reinforcement learning with a 3D spatio-temporal U-Net, IEEE Transactions on Image Processing, Vol: 31, Pages: 1573-1586, ISSN: 1057-7149
Intelligent video summarization algorithms allow to quickly convey the most relevant information in videos through the identification of the most essential and explanatory content while removing redundant video frames. In this paper, we introduce the 3DST-UNet-RL framework for video summarization. A 3D spatio-temporal U-Net is used to efficiently encode spatio-temporal information of the input videos for downstream reinforcement learning (RL). An RL agent learns from spatio-temporal latent scores and predicts actions for keeping or rejecting a video frame in a video summary. We investigate if real/inflated 3D spatio-temporal CNN features are better suited to learn representations from videos than commonly used 2D image features. Our framework can operate in both, a fully unsupervised mode and a supervised training mode. We analyse the impact of prescribed summary lengths and show experimental evidence for the effectiveness of 3DST-UNet-RL on two commonly used general video summarization benchmarks. We also applied our method on a medical video summarization task. The proposed video summarization method has the potential to save storage costs of ultrasound screening videos as well as to increase efficiency when browsing patient video data during retrospective analysis or audit without loosing essential information.
Dahan S, Fawaz A, Williams LZJ, et al., 2022, Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis, Pages: 282-303
The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range associations, as the generalisation of convolutions to irregular surfaces is non-trivial. Motivated by the success of attention-modelling in computer vision, we translate convolution-free vision transformer approaches to surface data, to introduce a domain-agnostic architecture to study any surface data projected onto a spherical manifold. Here, surface patching is achieved by representing spherical data as a sequence of triangular patches, extracted from a subdivided icosphere. A transformer model encodes the sequence of patches via successive multi-head self-attention layers while preserving the sequence resolution. We validate the performance of the proposed Surface Vision Transformer (SiT) on the task of phenotype regression from cortical surface metrics derived from the Developing Human Connectome Project (dHCP). Experiments show that the SiT generally outperforms surface CNNs, while performing comparably on registered and unregistered data. Analysis of transformer attention maps offers strong potential to characterise subtle cognitive developmental patterns.
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.