179 results found
Lino M, Fotiadis S, Bharath AA, et al., 2022, Towards fast simulation of environmental fluid mechanics with multi-scale graph neural networks, AI for Earth and Space Science, Publisher: ICLR, Pages: 1-11
Numerical simulators are essential tools in the study of naturalfluid-systems, but their performance often limits application in practice.Recent machine-learning approaches have demonstrated their ability toaccelerate spatio-temporal predictions, although, with only moderate accuracyin comparison. Here we introduce MultiScaleGNN, a novel multi-scale graphneural network model for learning to infer unsteady continuum mechanics inproblems encompassing a range of length scales and complex boundary geometries.We demonstrate this method on advection problems and incompressible fluiddynamics, both fundamental phenomena in oceanic and atmospheric processes. Ourresults show good extrapolation to new domain geometries and parameters forlong-term temporal simulations. Simulations obtained with MultiScaleGNN arebetween two and four orders of magnitude faster than those on which it wastrained.
Wong N, Meshkinfamfard S, Turbé V, et al., 2022, Machine learning to support visual auditing of home-based lateral flow immunoassay self-test results for SARS-CoV-2 antibodies, Communications Medicine, ISSN: 2730-664X
Lateral flow immunoassays (LFIAs) are being used worldwide for COVID-19 mass testing and antibody prevalence studies. Relatively simple to use and low cost, these tests can be self-administered at home but rely on subjective interpretation of a test line by eye, risking false positives and negatives. Here we report the development of ALFA (Automated Lateral Flow Analysis) to improve reported sensitivity and specificity. Our computational pipeline uses machine learning, computer vision techniques and signal processing algorithms to analyse images of the Fortress LFIA SARS-CoV-2 antibody self-test, and subsequently classify results as invalid, IgG negative and IgG positive. A large image library of 595,339 participant-submitted test photographs was created as part of the REACT-2 community SARS-CoV-2 antibody prevalence study in England, UK. Automated analysis showed substantial agreement with human experts (Kappa 0.90-0.97) and performed consistently better than study participants, particularly for weak positive IgG results. Specificity (98.7-99.4%) and sensitivity (90.1-97.1%) were high compared with visual interpretation by human experts (ranges due to the varying prevalence of weak positive IgG tests in datasets). Alongside ALFA, we developed an analysis toolkit which could also detect device blood leakage issues. Given the potential for LFIAs to be used at scale in the COVID-19 response (for both antibody and antigen testing), even a small improvement in the accuracy of the algorithms could impact the lives of millions of people by reducing the risk of false positive and false negative result read-outs by members of the public. Our findings support the use of machine learning-enabled automated reading of at-home antibody lateral flow tests, to be a tool for improved accuracy for population-level community surveillance.
Bharath A, Uslu F, Varela Anjari M, et al., 2022, LA-Net: A multi-task deep network for the segmentation of the left atrium, IEEE Transactions on Medical Imaging, Vol: 41, Pages: 456-464, ISSN: 0278-0062
Although atrial fibrillation (AF) is the most common sustained atrial arrhythmia, treatment success for this condition remains suboptimal. Information from magnetic resonance imaging (MRI) has the potential to improve treatment efficacy, but there are currently few automatic tools for the segmentation of the atria in MR images. In the study, we propose a LA-Net, a multi-task network optimised to simultaneously generate left atrial segmentation and edge masks from MRI. LA-Net includes cross attention modules (CAMs) and enhanced decoder modules (EDMs) to purposefully select the most meaningful edge information for segmentation and smoothly incorporate it into segmentation masks at multiple-scales. We evaluate the performance of LA-Net on two MR sequences: late gadolinium enhanced (LGE) atrial MRI and atrial short axis balanced steady state free precession (bSSFP) MRI. LA-Net gives Hausdorff distances of 12.43 mm and Dice scores of 0.92 on the LGE (STACOM 2018) dataset and Hausdorff distances of 17.41 mm and Dice scores of 0.90 on the bSSFP (in-house) dataset without any post-processing, surpassing previously proposed segmentation networks, including U-Net and SEGANet. Our method allows automatic extraction of information about the LA from MR images, which can play an important role in the management of AF patients.
Dai T, Du Y, Fang M, et al., 2022, Diversity-augmented intrinsic motivation for deep reinforcement learning, Neurocomputing, Vol: 468, Pages: 396-406, ISSN: 0925-2312
In many real-world problems, reward signals received by agents are delayed or sparse, which makes it challenging to train a reinforcement learning (RL) agent. An intrinsic reward signal can help an agent to explore such environments in the quest for novel states. In this work, we propose a general end-to-end diversity-augmented intrinsic motivation for deep reinforcement learning which encourages the agent to explore new states and automatically provides denser rewards. Specifically, we measure the diversity of adjacent states under a model of state sequences based on determinantal point process (DPP); this is coupled with a straight-through gradient estimator to enable end-to-end differentiability. The proposed approach is comprehensively evaluated on the MuJoCo and the Arcade Learning Environments (Atari and SuperMarioBros). The experiments show that an intrinsic reward based on the diversity measure derived from the DPP model accelerates the early stages of training in Atari games and SuperMarioBros. In MuJoCo, the approach improves on prior techniques for tasks using the standard reward setting, and achieves the state-of-the-art performance on 12 out of 15 tasks containing delayed rewards.
Galazis C, Wu H, Li Z, et al., 2022, Tempera: Spatial Transformer Feature Pyramid Network for Cardiac MRI Segmentation, Pages: 268-276, ISSN: 0302-9743
Assessing the structure and function of the right ventricle (RV) is important in the diagnosis of several cardiac pathologies. However, it remains more challenging to segment the RV than the left ventricle (LV). In this paper, we focus on segmenting the RV in both short (SA) and long-axis (LA) cardiac MR images simultaneously. For this task, we propose a new multi-input/output architecture, hybrid 2D/3D geometric spatial TransformEr Multi-Pass fEature pyRAmid (Tempera). Our feature pyramid extends current designs by allowing not only a multi-scale feature output but multi-scale SA and LA input images as well. Tempera transfers learned features between SA and LA images via layer weight sharing and incorporates a geometric target transformer to map the predicted SA segmentation to LA space. Our model achieves an average Dice score of 0.836 and 0.798 for the SA and LA, respectively, and 26.31 mm and 31.19 mm Hausdorff distances. This opens up the potential for the incorporation of RV segmentation models into clinical workflows.
Zaman S, Petri C, Vimalesvaran K, et al., 2022, Automatic diagnosis labeling of cardiovascular MRI by using semisupervised natural language processing of text reports, Radiology: Artificial Intelligence, Vol: 4, ISSN: 2638-6100
A semisupervised natural language processing (NLP) algorithm, based on bidirectional transformers, accurately categorized diagnoses from cardiac MRI text of radiology reports for the labeling of MR images; the model had a higher accuracy than traditional NLP models and performed faster labeling than clinicians.
Herrero Martin C, Oved A, Chowdhury R, et al., 2021, EP-PINNs: cardiac electrophysiology characterisation using physics-informed neural networks, Frontiers in Cardiovascular Medicine, ISSN: 2297-055X
Accurately inferring underlying electrophysiological (EP) tissue properties from action potential recordings is expected to be clinically useful in the diagnosis and treatment of arrhythmias such as atrial fibrillation, but it is notoriously difficult to perform. We present EP-PINNs (Physics-Informed Neural Networks), a novel tool for accurate action potential simulation and EP parameter estimation, from sparse amounts of EP data. We demonstrate, using 1D and 2D in silico data, how EP-PINNs are able to reconstruct the spatio-temporal evolution of action potentials, whilst predicting parameters related to action potential duration (APD), excitability and diffusion coefficients. EP-PINNs are additionally able to identify heterogeneities in EP properties, making them potentially useful for the detection of fibrosis and other localised pathology linked to arrhythmias. Finally, we show EP-PINNs effectiveness on biological in vitro preparations, by characterising the effect of anti-arrhythmic drugs on APD using optical mapping data. EP-PINNs are a promising clinical tool for the characterisation and potential treatment guidance of arrhythmias.
Martin CH, Oved A, Chowdhury RA, et al., 2021, EP-PINNs: cardiac electrophysiology characterisation using physics-informed neural networks, Publisher: arXiv
Accurately inferring underlying electrophysiological (EP) tissue propertiesfrom action potential recordings is expected to be clinically useful in thediagnosis and treatment of arrhythmias such as atrial fibrillation, but it isnotoriously difficult to perform. We present EP-PINNs (Physics-Informed NeuralNetworks), a novel tool for accurate action potential simulation and EPparameter estimation, from sparse amounts of EP data. We demonstrate, using 1Dand 2D in silico data, how EP-PINNs are able to reconstruct the spatio-temporalevolution of action potentials, whilst predicting parameters related to actionpotential duration (APD), excitability and diffusion coefficients. EP-PINNs areadditionally able to identify heterogeneities in EP properties, making thempotentially useful for the detection of fibrosis and other localised pathologylinked to arrhythmias. Finally, we show EP-PINNs effectiveness on biological invitro preparations, by characterising the effect of anti-arrhythmic drugs onAPD using optical mapping data. EP-PINNs are a promising clinical tool for thecharacterisation and potential treatment guidance of arrhythmias.
Dai T, Liu H, Arulkumaran K, et al., 2021, Diversity-based trajectory and goal selection with hindsight experience replay, 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI)
Hindsight experience replay (HER) is a goal relabelling technique typicallyused with off-policy deep reinforcement learning algorithms to solvegoal-oriented tasks; it is well suited to robotic manipulation tasks thatdeliver only sparse rewards. In HER, both trajectories and transitions aresampled uniformly for training. However, not all of the agent's experiencescontribute equally to training, and so naive uniform sampling may lead toinefficient learning. In this paper, we propose diversity-based trajectory andgoal selection with HER (DTGSH). Firstly, trajectories are sampled according tothe diversity of the goal states as modelled by determinantal point processes(DPPs). Secondly, transitions with diverse goal states are selected from thetrajectories by using k-DPPs. We evaluate DTGSH on five challenging roboticmanipulation tasks in simulated robot environments, where we show that ourmethod can learn more quickly and reach higher performance than otherstate-of-the-art approaches on all tasks.
Liu Y, Zou Z, Yang Y, et al., 2021, Efficient Source Camera Identification with Diversity-Enhanced Patch Selection and Deep Residual Prediction, SENSORS, Vol: 21
Patel R, Thong EHE, Batta V, et al., 2021, Automated Identification of Orthopedic Implants on Radiographs Using Deep Learning., Radiol Artif Intell, Vol: 3
Accurate identification of metallic orthopedic implant design is important for preoperative planning of revision arthroplasty. Surgical records of implant models are frequently unavailable. The aim of this study was to develop and evaluate a convolutional neural network for identifying orthopedic implant models using radiographs. In this retrospective study, 427 knee and 922 hip unilateral anteroposterior radiographs, including 12 implant models from 650 patients, were collated from an orthopedic center between March 2015 and November 2019 to develop classification networks. A total of 198 images paired with autogenerated image masks were used to develop a U-Net segmentation network to automatically zero-mask around the implants on the radiographs. Classification networks processing original radiographs, and two-channel conjoined original and zero-masked radiographs, were ensembled to provide a consensus prediction. Accuracies of five senior orthopedic specialists assisted by a reference radiographic gallery were compared with network accuracy using McNemar exact test. When evaluated on a balanced unseen dataset of 180 radiographs, the final network achieved a 98.9% accuracy (178 of 180) and 100% top-three accuracy (180 of 180). The network performed superiorly to all five specialists (76.1% [137 of 180] median accuracy and 85.6% [154 of 180] best accuracy; both P < .001), with robustness to scan quality variation and difficult to distinguish implants. A neural network model was developed that outperformed senior orthopedic specialists at identifying implant models on radiographs; real-world application can now be readily realized through training on a broader range of implants and joints, supported by all code and radiographs being made freely available. Supplemental material is available for this article. Keywords: Neural Networks, Skeletal-Appendicular, Knee, Hip, Computer Applications-General (Informatics), Prostheses, Technology Assess-ment, Observer Perform
Rodrigues J, Bharath A, Overby D, 2021, Automated machine learning detection of transcellular pores in Schlemm's canal endothelial cells exposed to stretch, Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
Davis BM, Guo L, Ravindran N, et al., 2020, Dynamic changes in cell size and corresponding cell fate after optic nerve injury, Scientific Reports, Vol: 10, ISSN: 2045-2322
Identifying disease-specific patterns of retinal cell loss in pathological conditions has been highlighted by the emergence of techniques such as Detection of Apoptotic Retinal Cells and Adaptive Optics confocal Scanning Laser Ophthalmoscopy which have enabled single-cell visualisation in vivo. Cell size has previously been used to stratify Retinal Ganglion Cell (RGC) populations in histological samples of optic neuropathies, and early work in this field suggested that larger RGCs are more susceptible to early loss than smaller RGCs. More recently, however, it has been proposed that RGC soma and axon size may be dynamic and change in response to injury. To address this unresolved controversy, we applied recent advances in maximising information extraction from RGC populations in retinal whole mounts to evaluate the changes in RGC size distribution over time, using three well-established rodent models of optic nerve injury. In contrast to previous studies based on sampling approaches, we examined the whole Brn3a-positive RGC population at multiple time points over the natural history of these models. The morphology of over 4 million RGCs was thus assessed to glean novel insights from this dataset. RGC subpopulations were found to both increase and decrease in size over time, supporting the notion that RGC cell size is dynamic in response to injury. However, this study presents compelling evidence that smaller RGCs are lost more rapidly than larger RGCs despite the dynamism. Finally, using a bootstrap approach, the data strongly suggests that disease-associated changes in RGC spatial distribution and morphology could have potential as novel diagnostic indicators.
Lino M, Cantwell C, Fotiadis S, et al., 2020, Simulating surface wave dynamics with convolutional networks, Publisher: arXiv
We investigate the performance of fully convolutional networks to simulatethe motion and interaction of surface waves in open and closed complexgeometries. We focus on a U-Net architecture and analyse how well itgeneralises to geometric configurations not seen during training. Wedemonstrate that a modified U-Net architecture is capable of accuratelypredicting the height distribution of waves on a liquid surface within curvedand multi-faceted open and closed geometries, when only simple box andright-angled corner geometries were seen during training. We also consider aseparate and independent 3D CNN for performing time-interpolation on thepredictions produced by our U-Net. This allows generating simulations with asmaller time-step size than the one the U-Net has been trained for.
Lourenco A, Kerfoot E, Dibblin C, et al., 2020, Automatic estimation of left atrial function from short axis CINE-MRI using machine learning, European-Society-of-Cardiology (ESC) Congress, Publisher: OXFORD UNIV PRESS, Pages: 229-229, ISSN: 0195-668X
Howard JP, Zaman S, Ragavan A, et al., 2020, Automated analysis and detection of abnormalities in transaxial anatomical cardiovascular magnetic resonance images: a proof of concept study with potential to optimize image acquisition, International Journal of Cardiovascular Imaging, Vol: 37, Pages: 1033-1042, ISSN: 1569-5794
The large number of available MRI sequences means patients cannot realistically undergo them all, so the range of sequences to be acquired during a scan are protocolled based on clinical details. Adapting this to unexpected findings identified early on in the scan requires experience and vigilance. We investigated whether deep learning of the images acquired in the first few minutes of a scan could provide an automated early alert of abnormal features. Anatomy sequences from 375 CMR scans were used as a training set. From these, we annotated 1500 individual slices and used these to train a convolutional neural network to perform automatic segmentation of the cardiac chambers, great vessels and any pleural effusions. 200 scans were used as a testing set. The system then assembled a 3D model of the thorax from which it made clinical measurements to identify important abnormalities. The system was successful in segmenting the anatomy slices (Dice 0.910) and identified multiple features which may guide further image acquisition. Diagnostic accuracy was 90.5% and 85.5% for left and right ventricular dilatation, 85% for left ventricular hypertrophy and 94.4% for ascending aorta dilatation. The area under ROC curve for diagnosing pleural effusions was 0.91. We present proof-of-concept that a neural network can segment and derive accurate clinical measurements from a 3D model of the thorax made from transaxial anatomy images acquired in the first few minutes of a scan. This early information could lead to dynamic adaptive scanning protocols, and by focusing scanner time appropriately and prioritizing cases for supervision and early reporting, improve patient experience and efficiency.
Dai T, Liu H, Bharath A, 2020, Episodic self-imitation learning with hindsight, Electronics (Basel), Vol: 9, ISSN: 2079-9292
Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm, which samples good state–action pairs from the experience replay buffer, our agent leverages entire episodes with hindsight to aid self-imitation learning. A selection module is introduced to filter uninformative samples from each episode of the update. The proposed method overcomes the limitations of the standard self-imitation learning algorithm, a transitions-based method which performs poorly in handling continuous control environments with sparse rewards. From the experiments, episodic self-imitation learning is shown to perform better than baseline on-policy algorithms, achieving comparable performance to state-of-the-art off-policy algorithms in several simulated robot control tasks. The trajectory selection module is shown to prevent the agent learning undesirable hindsight experiences. With the capability of solving sparse reward problems in continuous control settings, episodic self-imitation learning has the potential to be applied to real-world problems that have continuous action spaces, such as robot guidance and manipulation.
Brook J, Kim M-Y, Koutsoftidis S, et al., 2020, Development of a pro-arrhythmic ex vivo intact human and porcine model: cardiac electrophysiological changes associated with cellular uncoupling, Pflügers Archiv European Journal of Physiology, Vol: 472, Pages: 1435-1446, ISSN: 0031-6768
We describe a human and large animal Langendorff experimental apparatus for live electrophysiological studies and measure the electrophysiological changes due to gap-junction uncoupling in human and porcine hearts. The resultant ex vivo intact human and porcine model can bridge the translational gap between smaller simple laboratory models and clinical research. In particular, electrophysiological models would benefit from the greater myocardial mass of a large heart due to its effects on far field signal, electrode contact issues and motion artefacts, consequently more closely mimicking the clinical setting Porcine (n=9) and human (n=4) donor hearts were perfused on a custom-designed Langendorff apparatus. Epicardial electrograms were collected at 16 sites across the left atrium and left ventricle. 1mM of carbenoxolone was administered at 5ml/min to induce cellular uncoupling, and then recordings were repeated at the same sites. Changes in electrogram characteristics were analysed.We demonstrate the viability of a controlled ex vivo model of intact porcine and human hearts for electrophysiology with pharmacological modulation. Carbenoxolone reduces cellular coupling and changes contact electrogram features. The time from stimulus artefact to (-dV/dt)max increased between baseline and carbenoxolone (47.9±4.1ms to 67.2±2.7ms) indicating conduction slowing. The features with the largest percentage change between baseline to Carbenoxolone were Fractionation +185.3%, Endpoint amplitude -106.9%, S-Endpoint Gradient +54.9%, S Point, -39.4%, RS Ratio +38.6% and (-dV/dt)max -20.9%.The physiological relevance of this methodological tool is that it provides a model to further investigate pharmacologically-induced proarrhythmic substrates.
Lourenço A, Kerfoot E, Dibblin C, et al., 2020, Left atrial ejection fraction estimation using SEGANet for fully automated segmentation of CINE MRI, Publisher: arXiv
Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia,characterised by a rapid and irregular electrical activation of the atria.Treatments for AF are often ineffective and few atrial biomarkers exist toautomatically characterise atrial function and aid in treatment selection forAF. Clinical metrics of left atrial (LA) function, such as ejection fraction(EF) and active atrial contraction ejection fraction (aEF), are promising, buthave until now typically relied on volume estimations extrapolated fromsingle-slice images. In this work, we study volumetric functional biomarkers ofthe LA using a fully automatic SEGmentation of the left Atrium based on aconvolutional neural Network (SEGANet). SEGANet was trained using a dedicateddata augmentation scheme to segment the LA, across all cardiac phases, in shortaxis dynamic (CINE) Magnetic Resonance Images (MRI) acquired with full cardiaccoverage. Using the automatic segmentations, we plotted volumetric time curvesfor the LA and estimated LA EF and aEF automatically. The proposed methodyields high quality segmentations that compare well with manual segmentations(Dice scores [$0.93 \pm 0.04$], median contour [$0.75 \pm 0.31$] mm andHausdorff distances [$4.59 \pm 2.06$] mm). LA EF and aEF are also in agreementwith literature values and are significantly higher in AF patients than inhealthy volunteers. Our work opens up the possibility of automaticallyestimating LA volumes and functional biomarkers from multi-slice CINE MRI,bypassing the limitations of current single-slice methods and improving thecharacterisation of atrial function in AF patients.
Uslu F, Varela M, Bharath AA, 2020, A semi-automatic method to segment the left atrium in MR volumes with varying slice numbers., 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Publisher: IEEE, Pages: 1198-1202
Atrial fibrillation (AF) is the most common sustained arrhythmia and is associated with dramatic increases in mortality and morbidity. Atrial cine MR images are increasingly used in the management of this condition, but there are few specific tools to aid in the segmentation of such data. Some characteristics of atrial cine MR (thick slices, variable number of slices in a volume) preclude the direct use of traditional segmentation tools. When combined with scarcity of labelled data and similarity of the intensity and texture of the left atrium (LA) to other cardiac structures, the segmentation of the LA in CINE MRI becomes a difficult task. To deal with these challenges, we propose a semi-automatic method to segment the left atrium (LA) in MR images, which requires an initial user click per volume. The manually given location information is used to generate a chamber location map to roughly locate the LA, which is then used as an input to a deep network with slightly over 0.5 million parameters. A tracking method is introduced to pass the location information across a volume and to remove unwanted structures in segmentation maps. According to the results of our experiments conducted in an in-house MRI dataset, the proposed method outperforms the U-Net  with a margin of 20 mm on Hausdorff distance and 0.17 on Dice score, with limited manual interaction.
Varela Anjari M, Queiros S, Anjari M, et al., 2020, Strain maps of the left atrium imagedwith a novel high-resolutionCINEMRI protocol*, 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology, Publisher: IEEE, Pages: 1178-1181, ISSN: 1557-170X
To date, regional atrial strains have not been imaged in vivo, despite their potential to provide useful clinical information. To address this gap, we present a novel CINE MRI protocol capable of imaging the entire left atrium at an isotropic 2-mm resolution in one single breath-hold.As proof of principle, we acquired data in 10 healthy volunteers and 2 cardiovascular patients using this technique.We also demonstrated how regional atrial strains can be estimated from this data following a manual segmentation of the left atrium using automatic image tracking techniques.The estimated principal strains vary smoothly across the left atrium and have a similar magnitude to estimates reported in the literature.
Fotiadis S, Pignatelli E, Valencia ML, et al., 2020, Comparing recurrent and convolutional neural networks for predicting wave propagation, Publisher: arXiv
Dynamical systems can be modelled by partial differential equations andnumerical computations are used everywhere in science and engineering. In thiswork, we investigate the performance of recurrent and convolutional deep neuralnetwork architectures to predict the surface waves. The system is governed bythe Saint-Venant equations. We improve on the long-term prediction overprevious methods while keeping the inference time at a fraction of numericalsimulations. We also show that convolutional networks perform at least as wellas recurrent networks in this task. Finally, we assess the generalisationcapability of each network by extrapolating in longer time-frames and indifferent physical settings.
Dai T, Arulkumaran K, Gerbert T, et al., 2020, Analysing deep reinforcement learning agents trained with domain randomisation, Publisher: arXiv
Deep reinforcement learning has the potential to train robots to performcomplex tasks in the real world without requiring accurate models of the robotor its environment. A practical approach is to train agents in simulation, andthen transfer them to the real world. One popular method for achievingtransferability is to use domain randomisation, which involves randomlyperturbing various aspects of a simulated environment in order to make trainedagents robust to the reality gap. However, less work has gone intounderstanding such agents - which are deployed in the real world - beyond taskperformance. In this work we examine such agents, through qualitative andquantitative comparisons between agents trained with and without visual domainrandomisation. We train agents for Fetch and Jaco robots on a visuomotorcontrol task and evaluate how well they generalise using different testingconditions. Finally, we investigate the internals of the trained agents byusing a suite of interpretability techniques. Our results show that the primaryoutcome of domain randomisation is more robust, entangled representations,accompanied with larger weights with greater spatial structure; moreover, thetypes of changes are heavily influenced by the task setup and presence ofadditional proprioceptive inputs. Additionally, we demonstrate that our domainrandomised agents require higher sample complexity, can overfit and moreheavily rely on recurrent processing. Furthermore, even with an improvedsaliency method introduced in this work, we show that qualitative studies maynot always correspond with quantitative measures, necessitating the combinationof inspection tools in order to provide sufficient insights into the behaviourof trained agents.
Uslu F, Bass C, Bharath AA, 2020, PERI-Net: a parameter efficient residual inception network for medical image segmentation, TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, Vol: 28, Pages: 2261-2277, ISSN: 1300-0632
Sorteberg WE, Garasto S, Cantwell CC, et al., 2020, Approximating the Solution of Surface Wave Propagation Using Deep Neural Networks
Sarrico M, Arulkumaran K, Agostinelli A, et al., 2019, Sample-efficient reinforcement learning with maximum entropy mellowmax episodic control, Publisher: arXiv
Deep networks have enabled reinforcement learning to scale to more complexand challenging domains, but these methods typically require large quantitiesof training data. An alternative is to use sample-efficient episodic controlmethods: neuro-inspired algorithms which use non-/semi-parametric models thatpredict values based on storing and retrieving previously experiencedtransitions. One way to further improve the sample efficiency of theseapproaches is to use more principled exploration strategies. In this work, wetherefore propose maximum entropy mellowmax episodic control (MEMEC), whichsamples actions according to a Boltzmann policy with a state-dependenttemperature. We demonstrate that MEMEC outperforms other uncertainty- andsoftmax-based exploration methods on classic reinforcement learningenvironments and Atari games, achieving both more rapid learning and higherfinal rewards.
Agostinelli A, Arulkumaran K, Sarrico M, et al., 2019, Memory-efficient episodic control reinforcement learning with dynamic online k-means
Recently, neuro-inspired episodic control (EC) methods have been developed toovercome the data-inefficiency of standard deep reinforcement learningapproaches. Using non-/semi-parametric models to estimate the value function,they learn rapidly, retrieving cached values from similar past states. Inrealistic scenarios, with limited resources and noisy data, maintainingmeaningful representations in memory is essential to speed up the learning andavoid catastrophic forgetting. Unfortunately, EC methods have a large space andtime complexity. We investigate different solutions to these problems based onprioritising and ranking stored states, as well as online clusteringtechniques. We also propose a new dynamic online k-means algorithm that is bothcomputationally-efficient and yields significantly better performance atsmaller memory sizes; we validate this approach on classic reinforcementlearning environments and Atari games.
Kothari S, Gionfrida L, Bharath AA, et al., 2019, Artificial Intelligence (AI) and rheumatology: a potential partnership, RHEUMATOLOGY, Vol: 58, Pages: 1894-1895, ISSN: 1462-0324
Balaram S, Arulkumaran K, Dai T, et al., 2019, A maximum entropy deep reinforcement learning neural tracker, 10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 400-408, ISSN: 0302-9743
Tracking of anatomical structures has multiple applications in the field of biomedical imaging, including screening, diagnosing and monitoring the evolution of pathologies. Semi-automated tracking of elongated structures has been previously formulated as a problem suitable for deep reinforcement learning (DRL), but it remains a challenge. We introduce a maximum entropy continuous-action DRL neural tracker capable of training from scratch in a complex environment in the presence of high noise levels, Gaussian blurring and detractors. The trained model is evaluated on two-photon microscopy images of mouse cortex. At the expense of slightly worse robustness compared to a previously applied DRL tracker, we reach significantly higher accuracy, approaching the performance of the standard hand-engineered algorithm used for neuron tracing. The higher sample efficiency of our maximum entropy DRL tracker indicates its potential of being applied directly to small biomedical datasets.
Bharath A, 2019, AI to assess mechanisms of glaucoma and other diseases, Annual Meeting of the Association-for-Research-in-Vision-and-Ophthalmology (ARVO), Publisher: ASSOC RESEARCH VISION OPHTHALMOLOGY INC, ISSN: 0146-0404
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.