Publications
242 results found
Huang J-J, Dragotti PL, 2022, WINNet: wavelet-inspired invertible network for image denoising, IEEE Transactions on Image Processing, Vol: 31, Pages: 4377-4392, ISSN: 1057-7149
Image denoising aims to restore a clean image from an observed noisy one. Model-based image denoising approaches can achieve good generalization ability over different noise levels and are with high interpretability. Learning-based approaches are able to achieve better results, but usually with weaker generalization ability and interpretability. In this paper, we propose a wavelet-inspired invertible network (WINNet) to combine the merits of the wavelet-based approaches and learning-based approaches. The proposed WINNet consists of K -scale of lifting inspired invertible neural networks (LINNs) and sparsity-driven denoising networks together with a noise estimation network. The network architecture of LINNs is inspired by the lifting scheme in wavelets. LINNs are used to learn a non-linear redundant transform with perfect reconstruction property to facilitate noise removal. The denoising network implements a sparse coding process for denoising. The noise estimation network estimates the noise level from the input image which will be used to adaptively adjust the soft-thresholds in LINNs. The forward transform of LINNs produces a redundant multi-scale representation for denoising. The denoised image is reconstructed using the inverse transform of LINNs with the denoised detail channels and the original coarse channel. The simulation results show that the proposed WINNet method is highly interpretable and has strong generalization ability to unseen noise levels. It also achieves competitive results in the non-blind/blind image denoising and in image deblurring.
Verinaz-Jadan H, Song P, Howe CL, et al., 2022, Shift-invariant-subspace discretization and volume reconstruction for light field microscopy, IEEE Transactions on Computational Imaging, Vol: 8, Pages: 286-301, ISSN: 2573-0436
Light Field Microscopy (LFM) is an imaging technique that captures 3D spatial information with a single 2D image. LFM is attractive because of its relatively simple implementation and fast volume acquisition rate. Capturing volume time series at a camera frame rate can enable the study of the behaviour of many biological systems. For instance, it could provide insights into the communication dynamics of living 3D neural networks. However, conventional 3D reconstruction algorithms for LFM typically suffer from high computational cost, low lateral resolution, and reconstruction artifacts. In this work, we study the origin of these issues and propose novel techniques to improve the performance of the reconstruction process. First, we propose a discretization approach that uses shift-invariant subspaces to generalize the typical discretization framework used in LFM. Then, we study the shift-invariant-subspace assumption as a prior for volume reconstruction under ideal conditions. Furthermore, we present a method to reduce the computational time of the forward model by using singular value decomposition (SVD). Finally, we propose to use iterative approaches that incorporate additional priors to perform artifact-free 3D reconstruction from real light field images. We experimentally show that our approach performs better than Richardson-Lucy-based strategies in computational time, image quality, and artifact reduction.
Howe C, Song P, Verinaz Jadan HI, et al., 2022, Comparing synthetic refocusing to deconvolution for the extraction of neuronal calcium transients from light fields, Neurophotonics, Vol: 9, Pages: 1-17, ISSN: 2329-4248
Significance: Light-field microscopy (LFM) enables fast, light-efficient, volumetric imaging of neuronal activity with calcium indicators. Calcium transients differ in temporal signal-to-noise ratio (tSNR) and spatial confinement when extracted from volumes reconstructed by different algorithms.Aim: We evaluated the capabilities and limitations of two light-field reconstruction algorithms for calcium fluorescence imaging.Approach: We acquired light-field image series from neurons either bulk-labeled or filled intracellularly with the red-emitting calcium dye CaSiR-1 in acute mouse brain slices. We compared the tSNR and spatial onfinement of calcium signals extracted from volumes reconstructed with synthetic refocusing and Richardson-Lucy 3D deconvolution with and without total variation regularization.Results: Both synthetic refocusing and Richardson-Lucy deconvolution resolved calcium signals from single cells and neuronal dendrites in three dimensions. Increasing deconvolution iteration number improved spatial confinement but reduced tSNR compared to synthetic refocusing. Volumetric light-field imaging did not decrease calcium signal tSNR compared to interleaved, widefield image series acquired in matched planes.Conclusions: LFM enables high-volume rate, volumetric imaging of calcium transients in single cells (bulk-labeled), somata and dendrites (intracellular loaded). The trade-offs identified for tSNR, spatial confinement, and computational cost indicate which of synthetic refocusing or deconvolution can better realize the scientific requirements of future LFM calcium imaging applications.
Foust A, Song P, Verinaz Jadan HI, et al., 2022, Light-field microscopy for optical imaging of neuronal activity: when model-based methods meet data-driven approaches, IEEE: Signal Processing Magazine, Vol: 39, ISSN: 1053-5888
Understanding how networks of neurons process information is one of the key challenges in modern neuroscience.A necessary step to achieve this goal is to be able to observe the dynamics of large populations of neurons overa large area of the brain. Light-field microscopy (LFM), a type of scanless microscope, is a particularly attractivecandidate for high-speed three-dimensional (3D) imaging. It captures volumetric information in a single snapshot,allowing volumetric imaging at video frame-rates. Specific features of imaging neuronal activity using LFM callfor the development of novel machine learning approaches that fully exploit priors embedded in physics and opticsmodels. Signal processing theory and wave-optics theory could play a key role in filling this gap, and contributeto novel computational methods with enhanced interpretability and generalization by integrating model-driven anddata-driven approaches. This paper is devoted to a comprehensive survey to state-of-the-art of computational methods for LFM, with a focus on model-based and data-driven approaches
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.
Erdemir E, Dragotti PL, Gunduz D, 2022, PRIVACY-AWARE COMMUNICATION OVER A WIRETAP CHANNEL WITH GENERATIVE NETWORKS, 47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 2989-2993, ISSN: 1520-6149
Pu W, Huang J-J, Sober B, et al., 2022, Mixed X-Ray Image Separation for Artworks With Concealed Designs, IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol: 31, Pages: 4458-4473, ISSN: 1057-7149
Gao F, Deng X, Xu M, et al., 2022, Multi-Modal Convolutional Dictionary Learning, IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol: 31, Pages: 1325-1339, ISSN: 1057-7149
- Author Web Link
- Cite
- Citations: 1
Wang R, Alexandru R, Dragotti PL, 2022, PERFECT RECONSTRUCTION OF CLASSES OF NON-BANDLIMITED SIGNALS FROM PROJECTIONS WITH UNKNOWN ANGLES, 47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 5877-5881, ISSN: 1520-6149
Liu S, Alexandru R, Dragotti PL, 2022, CONVOLUTIONAL ISTA NETWORK WITH TEMPORAL CONSISTENCY CONSTRAINTS FOR VIDEO RECONSTRUCTION FROM EVENT CAMERAS, 47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 1935-1939, ISSN: 1520-6149
Sober B, Bucklow S, Daly N, et al., 2022, Revealing and Reconstructing Hidden or Lost Features in Art Investigation, IEEE BITS the Information Theory Magazine, Pages: 1-16, ISSN: 2692-4080
Perez-Nieves N, Leung VCH, Dragotti PL, et al., 2021, Neural heterogeneity promotes robust learning, Nature Communications, Vol: 12, ISSN: 2041-1723
The brain has a hugely diverse, heterogeneous structure. Whether or not heterogeneity at the neural level plays a functional role remains unclear, and has been relatively little explored in models which are often highly homogeneous. We compared the performance of spiking neural networks trained to carry out tasks of real-world difficulty, with varying degrees of heterogeneity, and found that it substantially improved task performance. Learning was more stable and robust, particularly for tasks with a rich temporal structure. In addition, the distribution of neuronal parameters in the trained networks closely matches those observed experimentally. We suggest that the heterogeneity observed in the brain may be more than just the byproduct of noisy processes, but rather may serve an active and important role in allowing animals to learn in changing environments.Summary Neural heterogeneity is metabolically efficient for learning, and optimal parameter distribution matches experimental data.
Wang X, Jiang L, Li L, et al., 2021, Joint Learning of 3D Lesion Segmentation and Classification for Explainable COVID-19 Diagnosis, IEEE TRANSACTIONS ON MEDICAL IMAGING, Vol: 40, Pages: 2463-2476, ISSN: 0278-0062
- Author Web Link
- Cite
- Citations: 15
Yan S, Huang J-J, Daly N, et al., 2021, When de prony met Leonardo: an automatic algorithm for chemical element extraction from macro X-ray fluorescence data, IEEE Transactions on Computational Imaging, Vol: 7, Pages: 908-924, ISSN: 2333-9403
Macro X-ray Fluorescence (MA-XRF) scanning is an increasingly widely used technique for analytical imaging of paintings and other artworks. The datasets acquired must be processed to produce maps showing the distribution of the chemical elements that are present in the painting. Existing approaches require varying degrees of expert user intervention, in particular to select a list of target elements against which to fit the data. In this paper, we propose a novel approach that can automatically extract and identify chemical elements and their distributions from MA-XRF datasets. The proposed approach consists of three parts: 1) pre-processing steps, 2) pulse detection and model order selection based on Finite Rate of Innovation theory, and 3) chemical element estimation based on Cramér-Rao bounding techniques. The performance of our approach is assessed using MA-XRF datasets acquired from paintings in the collection of the National Gallery, London. The results presented show the ability of our approach to detect elements with weak X-ray fluorescence intensity and from noisy XRF spectra, to separate overlapping elemental signals and, excitingly, to aid visualisation of hidden underdrawing in a masterpiece by Leonardo da Vinci.
Leung VCH, Huang J-J, Eldar Y, et al., 2021, Reconstruction Of FRI Signals Using Autoencoders With Fixed Decoders, 2021 29th European Signal Processing Conference (EUSIPCO), Pages: 1496-1500
Yu Q, Huang J-J, Zhu J, et al., 2021, Deep phase retrieval: Analyzing over-parameterization in phase retrieval, SIGNAL PROCESSING, Vol: 180, ISSN: 0165-1684
Hilton M, Alexandru R, Dragotti PL, 2021, GUARANTEED RECONSTRUCTION FROM INTEGRATE-AND-FIRE NEURONS WITH ALPHA SYNAPTIC ACTIVATION, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 5474-5478
- Author Web Link
- Cite
- Citations: 1
Huang J-J, Dragotti PL, 2021, LINN: Lifting Inspired Invertible Neural Network for Image Denoising, 29th European Signal Processing Conference (EUSIPCO), Publisher: EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP, Pages: 636-640, ISSN: 2076-1465
Alexandru R, Blu T, Dragotti PL, 2021, LOCALISING DIFFUSION SOURCES FROM SAMPLES TAKEN ALONG UNKNOWN PARAMETRIC TRAJECTORIES, 29th European Signal Processing Conference (EUSIPCO), Publisher: EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP, Pages: 2199-2203, ISSN: 2076-1465
Pu W, Huang J, Sober B, et al., 2021, A Learning Based Approach to Separate Mixed X-Ray Images Associated with Artwork with Concealed Designs, 29th European Signal Processing Conference (EUSIPCO), Publisher: EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP, Pages: 1491-1495, ISSN: 2076-1465
- Author Web Link
- Cite
- Citations: 1
Alexandru R, Blu T, Dragotti PL, 2021, Diffusion SLAM: Localizing Diffusion Sources From Samples Taken by Location-Unaware Mobile Sensors, IEEE TRANSACTIONS ON SIGNAL PROCESSING, Vol: 69, Pages: 5539-5554, ISSN: 1053-587X
Song P, Jadan HV, Howe CL, et al., 2021, MODEL-INSPIRED DEEP LEARNING FOR LIGHT-FIELD MICROSCOPY WITH APPLICATION TO NEURON LOCALIZATION, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 8087-8091
- Author Web Link
- Cite
- Citations: 3
Xu J, Deng X, Xu M, et al., 2021, CU-NET plus : DEEP FULLY INTERPRETABLE NETWORK FOR MULTI-MODAL IMAGE RESTORATION, IEEE International Conference on Image Processing (ICIP), Publisher: IEEE, Pages: 1674-1678, ISSN: 1522-4880
Verinaz-Jadan H, Song P, Howe CL, et al., 2021, DEEP LEARNING FOR LIGHT FIELD MICROSCOPY USING PHYSICS-BASED MODELS, 18th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 1091-1094, ISSN: 1945-7928
- Author Web Link
- Cite
- Citations: 2
Hilton M, Alexandru R, Dragotti PL, 2021, Time Encoding Using the Hyperbolic Secant Kernel, 28th European Signal Processing Conference (EUSIPCO), Publisher: IEEE, Pages: 2304-2308, ISSN: 2076-1465
- Author Web Link
- Cite
- Citations: 2
Erdemir E, Dragotti PL, Gunduz D, 2021, ACTIVE PRIVACY-UTILITY TRADE-OFF AGAINST A HYPOTHESIS TESTING ADVERSARY, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Publisher: IEEE, Pages: 2660-2664
- Author Web Link
- Cite
- Citations: 4
Perez-Nieves N, Leung V, Dragotti PL, et al., 2020, Neural heterogeneity promotes robust learning
The brain has a hugely diverse, heterogeneous structure. Whether or not heterogeneity at the neural level plays a functional role remains unclear, and has been relatively little explored in models which are often highly homogeneous. We compared the performance of spiking neural networks trained to carry out tasks of real-world difficulty, with varying degrees of heterogeneity, and found that it substantially improved task performance. Learning was more stable and robust, particularly for tasks with a rich temporal structure. In addition, the distribution of neuronal parameters in the trained networks closely matches those observed experimentally. We suggest that the heterogeneity observed in the brain may be more than just the byproduct of noisy processes, but rather may serve an active and important role in allowing animals to learn in changing environments. <h4>Summary</h4> Neural heterogeneity is metabolically efficient for learning, and optimal parameter distribution matches experimental data.
Huang J-J, Dragotti PL, 2020, Learning deep analysis dictionaries for image super-resolution, IEEE Transactions on Signal Processing, Vol: 68, Pages: 6633-6648, ISSN: 1053-587X
Inspired by the recent success of deep neural networks and the recent efforts to develop multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) which is optimized to address a specific regression task known as single image super-resolution. Contrary to other multi-layer dictionary models, our architecture contains L layers of analysis dictionary and soft-thresholding operators to gradually extract high-level features and a layer of synthesis dictionary which is designed to optimize the regression task at hand. In our approach, each analysis dictionary is partitioned into two sub-dictionaries: an Information Preserving Analysis Dictionary (IPAD) and a Clustering Analysis Dictionary (CAD). The IPAD together with the corresponding soft-thresholds is designed to pass the key information from the previous layer to the next layer, while the CAD together with the corresponding soft-thresholding operator is designed to produce a sparse feature representation of its input data that facilitates discrimination of key features. DeepAM uses both supervised and unsupervised setup. Simulation results show that the proposed deep analysis dictionary model achieves better performance compared to a deep neural network that has the same structure and is optimized using back-propagation when training datasets are small. On noisy image super-resolution, DeepAM can be well adapted to unseen testing noise levels by rescaling the IPAD and CAD thresholds of the first layer.
Howe CL, Quicke P, Song P, et al., 2020, Comparing synthetic refocusing to deconvolution for the extraction of neuronal calcium transients from light-fields, Publisher: Cold Spring Harbor Laboratory
<jats:title>Abstract</jats:title><jats:sec><jats:title>Significance</jats:title><jats:p>Light-field microscopy (LFM) enables fast, light-efficient, volumetric imaging of neuronal activity with calcium indicators. Calcium transients differ in temporal signal-to-noise ratio (tSNR) and spatial confinement when extracted from volumes reconstructed by different algorithms.</jats:p></jats:sec><jats:sec><jats:title>Aim</jats:title><jats:p>We evaluated the capabilities and limitations of two light-field reconstruction algorithms for calcium fluorescence imaging.</jats:p></jats:sec><jats:sec><jats:title>Approach</jats:title><jats:p>We acquired light-field image series from neurons either bulk-labeled or filled intracellularly with the red-emitting calcium dye CaSiR-1 in acute mouse brain slices. We compared the tSNR and spatial confinement of calcium signals extracted from volumes reconstructed with synthetic refocusing and Richardson-Lucy 3D deconvolution with and without total variation regularization.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Both synthetic refocusing and Richardson-Lucy deconvolution resolved calcium signals from single cells and neuronal dendrites in three dimensions. Increasing deconvolution iteration number improved spatial confinement but reduced tSNR compared to synthetic refocusing. Volumetric light-field imaging did not decrease calcium signal tSNR compared to interleaved, widefield image series acquired in matched planes.</jats:p></jats:sec><jats:sec><jats:title>Conclusions</jats:title><jats:p>LFM enables high-volume rate, volumetric imaging of calcium transients in single cells (bulk-labeled), somata and dendrites (intracellular loaded). The trade-offs identified for tSNR, spatial confinement, and computational cost indicate which of syntheti
Parsi M, Crossley P, Dragotti PL, et al., 2020, Wavelet based fault location on power transmission lines using real-world travelling wave data, ELECTRIC POWER SYSTEMS RESEARCH, Vol: 186, ISSN: 0378-7796
- Author Web Link
- Cite
- Citations: 14
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.