Search

Sequential Monte Carlo (SMC), or particle filtering, is widely used in nonlinear state-space systems, but its performance often suffers from poorly approximated proposal and state-transition distributions. This work introduces a differentiable particle filter that leverages the unsupervised variational SMC objective to parameterize the proposal and transition distributions with a neural network, designed to learn from high-dimensional observations. Experimental results demonstrate that our approach outperforms established baselines in tracking the challenging Lorenz attractor from high-dimensional and partial observations. Furthermore, an evidence lower bound based evaluation indicates that our method offers a more accurate representation of the posterior distribution.

Ultrasound images are commonly formed by sequential acquisition of beam-steered scan-lines. Minimizing the number of required scan-lines can significantly enhance frame rate, field of view, energy efficiency, and data transfer speeds. Existing approaches typically use static subsampling schemes in combination with sparsity-based or, more recently, deep-learning-based recovery. In this work, we introduce an adaptive subsampling method that maximizes intrinsic information gain in-situ, employing a Sylvester Normalizing Flow encoder to infer an approximate Bayesian posterior under partial observation in real-time. Using the Bayesian posterior and a deep generative model for future observations, we determine the subsampling scheme that maximizes the mutual information between the subsampled observations, and the next frame of the video. We evaluate our approach using the EchoNet cardiac ultrasound video dataset and demonstrate that our active sampling method outperforms competitive baselines, including uniform and variable-density random sampling, as well as equidistantly spaced scan-lines, improving mean absolute reconstruction error by 15%. Moreover, posterior inference and the sampling scheme generation are performed in just 0.015 seconds (66Hz), making it fast enough for real-time 2D ultrasound imaging applications.

Accurate quantification of metabolites in magnetic resonance spectroscopy (MRS) is challenged by low signal-to-noise ratio (SNR), overlapping metabolites, and various artifacts. Particularly, unknown and unparameterized baseline effects obscure the quantification of low-concentration metabolites, limiting MRS reliability. This paper introduces wavelet analysis-based neural decomposition (WAND), a novel data-driven method designed to decompose MRS signals into their constituent components: metabolite-specific signals, baseline, and artifacts. WAND takes advantage of the enhanced separability of these components within the wavelet domain. The method employs a neural network, specifically a U-Net architecture, trained to predict masks for wavelet coefficients obtained through the continuous wavelet transform. These masks effectively isolate desired signal components in the wavelet domain, which are then inverse-transformed to obtain separated signals. Notably, an artifact mask is created by inverting the sum of all known signal masks, enabling WAND to capture and remove even unpredictable artifacts. The effectiveness of WAND in achieving accurate decomposition is demonstrated through numerical evaluations using simulated spectra. Furthermore, WAND's artifact removal capabilities significantly enhance the quantification accuracy of linear combination model fitting. The method's robustness is further validated using data from the 2016 MRS Fitting Challenge and in-vivo experiments., Comment: Submitted to NMR in Biomedicine

Diffusion models have quickly risen in popularity for their ability to model complex distributions and perform effective posterior sampling. Unfortunately, the iterative nature of these generative models makes them computationally expensive and unsuitable for real-time sequential inverse problems such as ultrasound imaging. Considering the strong temporal structure across sequences of frames, we propose a novel approach that models the transition dynamics to improve the efficiency of sequential diffusion posterior sampling in conditional image synthesis. Through modeling sequence data using a video vision transformer (ViViT) transition model based on previous diffusion outputs, we can initialize the reverse diffusion trajectory at a lower noise scale, greatly reducing the number of iterations required for convergence. We demonstrate the effectiveness of our approach on a real-world dataset of high frame rate cardiac ultrasound images and show that it achieves the same performance as a full diffusion trajectory while accelerating inference 25$\times$, enabling real-time posterior sampling. Furthermore, we show that the addition of a transition model improves the PSNR up to 8\% in cases with severe motion. Our method opens up new possibilities for real-time applications of diffusion models in imaging and other domains requiring real-time inference., Comment: 5 pages, 4 figures, preprint

Gold-standard sleep scoring as performed by human technicians is based on a subset of PSG signals, namely the EEG, EOG, and EMG. The PSG, however, consists of many more signal derivations that could potentially be used to perform sleep staging, including cardiac and respiratory modalities. Leveraging this variety in signals would offer advantages, for example by increasing reliability, resilience to signal loss, and application to long-term non-obtrusive recordings. This paper proposes a deep generative foundation model for fully automatic sleep staging from a plurality of sensors and any combination thereof. We trained a score-based diffusion model with a transformer backbone using a dataset of 1947 expert-labeled overnight sleep recordings with 36 different signals, including neurological, cardiac, and respiratory signals. We achieve zero-shot inference on any sensor set by using a novel Bayesian factorization of the score function across the sensors, i.e., it does not require retraining on specific combinations of signals. On single-channel EEG, our method reaches the performance limit in terms of PSG inter-rater agreement (5-class accuracy 85.6%, kappa 0.791). At the same time, the method offers full flexibility to use any sensor set derived from other modalities, for example, as typically used in home recordings that include finger PPG, nasal cannula and thoracic belt (5-class accuracy 79.0%, kappa of 0.697), or by combining derivations not typically used for sleep staging such as the tibialis and sternocleidomastoid EMG (5-class accuracy 71.0%, kappa of 0.575). Additionally, we propose a novel interpretability metric in terms of information gain per sensor and show that this is linearly correlated with classification performance. Lastly, our foundation model allows for post-hoc addition of entirely new sensor modalities by merely training a score estimator on the novel input.

Ultrasound images formed by delay-and-sum beamforming are plagued by artifacts that only clear up after compounding many transmissions. Some prior works pose imaging as an inverse problem. This approach can yield high image quality with few transmits, but requires a very fine image grid and is not robust to changes in measurement model parameters. We present INverse grid-Free Estimation of Reflectivities (INFER), an off-grid and stochastic algorithm that solves the inverse scattering problem in ultrasound imaging. Our method jointly optimizes for the locations of the gridpoints, their reflectivities, and the measurement model parameters such as the speed of sound. This approach allows us to use significantly fewer gridpoints, while obtaining better contrast and resolution and being more robust to changes in the imaging target and the hardware. The use of stochastic optimization enables solving for multiple transmissions simultaneously without increasing the required memory or computational load per iteration. We show that our method works across different imaging targets and across different transmit schemes and compares favorably against other beamforming and inverse solvers. The source code and the dataset to reproduce the results in this paper are available at www.github.com/vincentvdschaft/off-grid-ultrasound.

Diffusion models, widely used in image generation, rely on iterative refinement to generate images from noise. Understanding this data evolution is important for model development and interpretability, yet challenging due to its high-dimensional, iterative nature. Prior works often focus on static or instance-level analyses, missing the iterative and holistic aspects of the generative path. While dimensionality reduction can visualize image evolution for few instances, it does preserve the iterative structure. To address these gaps, we introduce EvolvED, a method that presents a holistic view of the iterative generative process in diffusion models. EvolvED goes beyond instance exploration by leveraging predefined research questions to streamline generative space exploration. Tailored prompts aligned with these questions are used to extract intermediate images, preserving iterative context. Targeted feature extractors trace the evolution of key image attribute evolution, addressing the complexity of high-dimensional outputs. Central to EvolvED is a novel evolutionary embedding algorithm that encodes iterative steps while maintaining semantic relations. It enhances the visualization of data evolution by clustering semantically similar elements within each iteration with t-SNE, grouping elements by iteration, and aligning an instance's elements across iterations. We present rectilinear and radial layouts to represent iterations and support exploration. We apply EvolvED to diffusion models like GLIDE and Stable Diffusion, demonstrating its ability to provide valuable insights into the generative process.

Subsampling is commonly used to mitigate costs associated with data acquisition, such as time or energy requirements, motivating the development of algorithms for estimating the fully-sampled signal of interest $x$ from partially observed measurements $y$. In maximum-entropy sampling, one selects measurement locations that are expected to have the highest entropy, so as to minimize uncertainty about $x$. This approach relies on an accurate model of the posterior distribution over future measurements, given the measurements observed so far. Recently, diffusion models have been shown to produce high-quality posterior samples of high-dimensional signals using guided diffusion. In this work, we propose Active Diffusion Subsampling (ADS), a method for performing active subsampling using guided diffusion in which the model tracks a distribution of beliefs over the true state of $x$ throughout the reverse diffusion process, progressively decreasing its uncertainty by choosing to acquire measurements with maximum expected entropy, and ultimately generating the posterior distribution $p(x | y)$. ADS can be applied using pre-trained diffusion models for any subsampling rate, and does not require task-specific retraining - just the specification of a measurement model. Furthermore, the maximum entropy sampling policy employed by ADS is interpretable, enhancing transparency relative to existing methods using black-box policies. Experimentally, we show that ADS outperforms fixed sampling strategies, and study an application of ADS in Magnetic Resonance Imaging acceleration using the fastMRI dataset, finding that ADS performs competitively with supervised methods. Code available at https://active-diffusion-subsampling.github.io/., Comment: 17 pages, 12 figures, preprint

Change point detection (CPD) and anomaly detection (AD) are essential techniques in various fields to identify abrupt changes or abnormal data instances. However, existing methods are often constrained to univariate data, face scalability challenges with large datasets due to computational demands, and experience reduced performance with high-dimensional or intricate data, as well as hidden anomalies. Furthermore, they often lack interpretability and adaptability to domain-specific knowledge, which limits their versatility across different fields. In this work, we propose a deep learning-based CPD/AD method called Probabilistic Predictive Coding (PPC) that jointly learns to encode sequential data to low dimensional latent space representations and to predict the subsequent data representations as well as the corresponding prediction uncertainties. The model parameters are optimized with maximum likelihood estimation by comparing these predictions with the true encodings. At the time of application, the true and predicted encodings are used to determine the probability of conformity, an interpretable and meaningful anomaly score. Furthermore, our approach has linear time complexity, scalability issues are prevented, and the method can easily be adjusted to a wide range of data types and intricate applications. We demonstrate the effectiveness and adaptability of our proposed method across synthetic time series experiments, image data, and real-world magnetic resonance spectroscopic imaging data., Comment: Submitted to Machine Learning

Vector quantization is a fundamental operation for data compression and vector search. To obtain high accuracy, multi-codebook methods represent each vector using codewords across several codebooks. Residual quantization (RQ) is one such method, which iteratively quantizes the error of the previous step. While the error distribution is dependent on previously-selected codewords, this dependency is not accounted for in conventional RQ as it uses a fixed codebook per quantization step. In this paper, we propose QINCo, a neural RQ variant that constructs specialized codebooks per step that depend on the approximation of the vector from previous steps. Experiments show that QINCo outperforms state-of-the-art methods by a large margin on several datasets and code sizes. For example, QINCo achieves better nearest-neighbor search accuracy using 12-byte codes than the state-of-the-art UNQ using 16 bytes on the BigANN1M and Deep1M datasets., Comment: To appear at ICML 2024

Data uncertainties, such as sensor noise, occlusions or limitations in the acquisition method can introduce irreducible ambiguities in images, which result in varying, yet plausible, semantic hypotheses. In Machine Learning, this ambiguity is commonly referred to as aleatoric uncertainty. In image segmentation, latent density models can be utilized to address this problem. The most popular approach is the Probabilistic U-Net (PU-Net), which uses latent Normal densities to optimize the conditional data log-likelihood Evidence Lower Bound. In this work, we demonstrate that the PU-Net latent space is severely sparse and heavily under-utilized. To address this, we introduce mutual information maximization and entropy-regularized Sinkhorn Divergence in the latent space to promote homogeneity across all latent dimensions, effectively improving gradient-descent updates and latent space informativeness. Our results show that by applying this on public datasets of various clinical segmentation problems, our proposed methodology receives up to 11% performance gains compared against preceding latent variable models for probabilistic segmentation on the Hungarian-Matched Intersection over Union. The results indicate that encouraging a homogeneous latent space significantly improves latent density modeling for medical image segmentation.

Echocardiography has been a prominent tool for the diagnosis of cardiac disease. However, these diagnoses can be heavily impeded by poor image quality. Acoustic clutter emerges due to multipath reflections imposed by layers of skin, subcutaneous fat, and intercostal muscle between the transducer and heart. As a result, haze and other noise artifacts pose a real challenge to cardiac ultrasound imaging. In many cases, especially with difficult-to-image patients such as patients with obesity, a diagnosis from B-Mode ultrasound imaging is effectively rendered unusable, forcing sonographers to resort to contrast-enhanced ultrasound examinations or refer patients to other imaging modalities. Tissue harmonic imaging has been a popular approach to combat haze, but in severe cases is still heavily impacted by haze. Alternatively, denoising algorithms are typically unable to remove highly structured and correlated noise, such as haze. It remains a challenge to accurately describe the statistical properties of structured haze, and develop an inference method to subsequently remove it. Diffusion models have emerged as powerful generative models and have shown their effectiveness in a variety of inverse problems. In this work, we present a joint posterior sampling framework that combines two separate diffusion models to model the distribution of both clean ultrasound and haze in an unsupervised manner. Furthermore, we demonstrate techniques for effectively training diffusion models on radio-frequency ultrasound data and highlight the advantages over image data. Experiments on both \emph{in-vitro} and \emph{in-vivo} cardiac datasets show that the proposed dehazing method effectively removes haze while preserving signals from weakly reflected tissue., Comment: 12pages, 15 figures, preprint IEEE submission

This work proposes a method to accelerate the acquisition of high-quality edited magnetic resonance spectroscopy (MRS) scans using machine learning models taking the sample covariance matrix as input. The method is invariant to the number of transients and robust to noisy input data for both synthetic as well as in-vivo scenarios.

Direction of arrival (DoA) estimation is a fundamental task in array processing. A popular family of DoA estimation algorithms are subspace methods, which operate by dividing the measurements into distinct signal and noise subspaces. Subspace methods, such as Multiple Signal Classification (MUSIC) and Root-MUSIC, rely on several restrictive assumptions, including narrowband non-coherent sources and fully calibrated arrays, and their performance is considerably degraded when these do not hold. In this work we propose SubspaceNet; a data-driven DoA estimator which learns how to divide the observations into distinguishable subspaces. This is achieved by utilizing a dedicated deep neural network to learn the empirical autocorrelation of the input, by training it as part of the Root-MUSIC method, leveraging the inherent differentiability of this specific DoA estimator, while removing the need to provide a ground-truth decomposable autocorrelation matrix. Once trained, the resulting SubspaceNet serves as a universal surrogate covariance estimator that can be applied in combination with any subspace-based DoA estimation method, allowing its successful application in challenging setups. SubspaceNet is shown to enable various DoA estimation algorithms to cope with coherent sources, wideband signals, low SNR, array mismatches, and limited snapshots, while preserving the interpretability and the suitability of classic subspace methods., Comment: Under review for publication in the IEEE

This literature review presents a comprehensive overview of machine learning (ML) applications in proton magnetic resonance spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state-of-the-art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the magnetic resonance field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in-vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.

The Kalman filter (KF) is a widely-used algorithm for tracking dynamic systems that are captured by state space (SS) models. The need to fully describe a SS model limits its applicability under complex settings, e.g., when tracking based on visual data, and the processing of high-dimensional signals often induces notable latency. These challenges can be treated by mapping the measurements into latent features obeying some postulated closed-form SS model, and applying the KF in the latent space. However, the validity of this approximated SS model may constitute a limiting factor. In this work, we study tracking from high-dimensional measurements under complex settings using a hybrid model-based/data-driven approach. By gradually tackling the challenges in handling the observations model and the task, we develop Latent-KalmanNet, which implements tracking from high-dimensional measurements by leveraging data to jointly learn the KF along with the latent space mapping. Latent-KalmanNet combines a learned encoder with data-driven tracking in the latent space using the recently proposed-KalmanNet, while identifying the ability of each of these trainable modules to assist its counterpart via providing a suitable prior (by KalmanNet) and by learning a latent representation that facilitates data-aided tracking (by the encoder). Our empirical results demonstrate that the proposed Latent-KalmanNet achieves improved accuracy and run-time performance over both model-based and data-driven techniques by learning a surrogate latent representation that most facilitates tracking, while operating with limited complexity and latency., Comment: Under review for publication in the IEEE

Solving ill-posed inverse problems requires careful formulation of prior beliefs over the signals of interest and an accurate description of their manifestation into noisy measurements. Handcrafted signal priors based on e.g. sparsity are increasingly replaced by data-driven deep generative models, and several groups have recently shown that state-of-the-art score-based diffusion models yield particularly strong performance and flexibility. In this paper, we show that the powerful paradigm of posterior sampling with diffusion models can be extended to include rich, structured, noise models. To that end, we propose a joint conditional reverse diffusion process with learned scores for the noise and signal-generating distribution. We demonstrate strong performance gains across various inverse problems with structured noise, outperforming competitive baselines that use normalizing flows and adversarial networks. This opens up new opportunities and relevant practical applications of diffusion modeling for inverse problems in the context of non-Gaussian measurement models., Comment: 11 pages, 7 figures, preprint

Electrocardiography (ECG) signals play a pivotal role in many healthcare applications, especially in at-home monitoring of vital signs. Wearable technologies, which these applications often depend upon, frequently produce low-quality ECG signals. While several methods exist for ECG denoising to enhance signal quality and aid clinical interpretation, they often underperform with ECG data from wearable technology due to limited noise tolerance or inadequate flexibility in capturing ECG dynamics. This paper introduces HKF, a hierarchical and adaptive Kalman filter, which uses a proprietary state space model to effectively capture both intra- and inter-heartbeat dynamics for ECG signal denoising. HKF learns a patient-specific structured prior for the ECG signal's intra-heartbeat dynamics in an online manner, resulting in a filter that adapts to the specific ECG signal characteristics of each patient. In an empirical study, HKF demonstrated superior denoising performance (reduced mean-squared error) while preserving the unique properties of the waveform. In a comparative analysis, HKF outperformed previously proposed methods for ECG denoising, such as the model-based Kalman filter and data-driven autoencoders. This makes it a suitable candidate for applications in extramural healthcare settings., Comment: Submitted to Transactions on Signal Processing

Melanoma is a serious form of skin cancer with high mortality rate at later stages. Fortunately, when detected early, the prognosis of melanoma is promising and malignant melanoma incidence rates are relatively low. As a result, datasets are heavily imbalanced which complicates training current state-of-the-art supervised classification AI models. We propose to use generative models to learn the benign data distribution and detect Out-of-Distribution (OOD) malignant images through density estimation. Normalizing Flows (NFs) are ideal candidates for OOD detection due to their ability to compute exact likelihoods. Nevertheless, their inductive biases towards apparent graphical features rather than semantic context hamper accurate OOD detection. In this work, we aim at using these biases with domain-level knowledge of melanoma, to improve likelihood-based OOD detection of malignant images. Our encouraging results demonstrate potential for OOD detection of melanoma using NFs. We achieve a 9% increase in Area Under Curve of the Receiver Operating Characteristics by using wavelet-based NFs. This model requires significantly less parameters for inference making it more applicable on edge devices. The proposed methodology can aid medical experts with diagnosis of skin-cancer patients and continuously increase survival rates. Furthermore, this research paves the way for other areas in oncology with similar data imbalance issues., Comment: Published at 1st Workshop on Cancer Prevention through early detecTion (MICCAI 2022)

Continuous monitoring with an ever-increasing number of sensors has become ubiquitous across many application domains. However, acquired time series are typically high-dimensional and difficult to interpret. Expressive deep learning (DL) models have gained popularity for dimensionality reduction, but the resulting latent space often remains difficult to interpret. In this work we propose SOM-CPC, a model that visualizes data in an organized 2D manifold, while preserving higher-dimensional information. We address a largely unexplored and challenging set of scenarios comprising high-rate time series, and show on both synthetic and real-life data (physiological data and audio recordings) that SOM-CPC outperforms strong baselines like DL-based feature extraction, followed by conventional dimensionality reduction techniques, and models that jointly optimize a DL model and a Self-Organizing Map (SOM). SOM-CPC has great potential to acquire a better understanding of latent patterns in high-rate data streams.

Medical ultrasound imaging relies heavily on high-quality signal processing to provide reliable and interpretable image reconstructions. Conventionally, reconstruction algorithms where derived from physical principles. These algorithms rely on assumptions and approximations of the underlying measurement model, limiting image quality in settings were these assumptions break down. Conversely, more sophisticated solutions based on statistical modelling, careful parameter tuning, or through increased model complexity, can be sensitive to different environments. Recently, deep learning based methods, which are optimized in a data-driven fashion, have gained popularity. These model-agnostic techniques often rely on generic model structures, and require vast training data to converge to a robust solution. A relatively new paradigm combines the power of the two: leveraging data-driven deep learning, as well as exploiting domain knowledge. These model-based solutions yield high robustness, and require less parameters and training data than conventional neural networks. In this work we provide an overview of these techniques from recent literature, and discuss a wide variety of ultrasound applications. We aim to inspire the reader to further research in this area, and to address the opportunities within the field of ultrasound signal processing. We conclude with a future perspective on model-based deep learning techniques for medical ultrasound.

Analog-to-digital converters (ADCs) allow physical signals to be processed using digital hardware. Their conversion consists of two stages: Sampling, which maps a continuous-time signal into discrete-time, and quantization, i.e., representing the continuous-amplitude quantities using a finite number of bits. ADCs typically implement generic uniform conversion mappings that are ignorant of the task for which the signal is acquired, and can be costly when operating in high rates and fine resolutions. In this work we design task-oriented ADCs which learn from data how to map an analog signal into a digital representation such that the system task can be efficiently carried out. We propose a model for sampling and quantization that facilitates the learning of non-uniform mappings from data. Based on this learnable ADC mapping, we present a mechanism for optimizing a hybrid acquisition system comprised of analog combining, tunable ADCs with fixed rates, and digital processing, by jointly learning its components end-to-end. Then, we show how one can exploit the representation of hybrid acquisition systems as deep network to optimize the sampling rate and quantization rate given the task by utilizing Bayesian meta-learning techniques. We evaluate the proposed deep task-based ADC in two case studies: the first considers symbol detection in multi-antenna digital receivers, where multiple analog signals are simultaneously acquired in order to recover a set of discrete information symbols. The second application is the beamforming of analog channel data acquired in ultrasound imaging. Our numerical results demonstrate that the proposed approach achieves performance which is comparable to operating with high sampling rates and fine resolution quantization, while operating with reduced overall bit rate.

Intravascular ultrasound (IVUS) offers a unique perspective in the treatment of vascular diseases by creating a sequence of ultrasound-slices acquired from within the vessel. However, unlike conventional hand-held ultrasound, the thin catheter only provides room for a small number of physical channels for signal transfer from a transducer-array at the tip. For continued improvement of image quality and frame rate, we present the use of deep reinforcement learning to deal with the current physical information bottleneck. Valuable inspiration has come from the field of magnetic resonance imaging (MRI), where learned acquisition schemes have brought significant acceleration in image acquisition at competing image quality. To efficiently accelerate IVUS imaging, we propose a framework that utilizes deep reinforcement learning for an optimal adaptive acquisition policy on a per-frame basis enabled by actor-critic methods and Gumbel top-$K$ sampling., Comment: 5 pages, 3 figures, conference

Ultrasonography offers an inexpensive, widely-accessible and compact medical imaging solution. However, compared to other imaging modalities such as CT and MRI, ultrasound images notoriously suffer from strong speckle noise, which originates from the random interference of sub-wavelength scattering. This deteriorates ultrasound image quality and makes interpretation challenging. We here propose a new unsupervised ultrasound speckle reduction and image denoising method based on maximum-a-posteriori estimation with deep generative priors that are learned from high-quality MRI images. To model the generative tissue reflectivity prior, we exploit normalizing flows, which in recent years have shown to be very powerful in modeling signal priors across a variety of applications. To facilitate generaliation, we factorize the prior and train our flow model on patches from the NYU fastMRI (fully-sampled) dataset. This prior is then used for inference in an iterative denoising scheme. We first validate the utility of our learned priors on noisy MRI data (no prior domain shift), and then turn to evaluating performance on both simulated and in-vivo ultrasound images from the PICMUS and CUBDL datasets. The results show that the method outperforms other (unsupervised) ultrasound denoising methods (NLM and OBNLM) both quantitatively and qualitatively., Comment: 10 pages, 8 figures

Plane Wave imaging enables many applications that require high frame rates, including localisation microscopy, shear wave elastography, and ultra-sensitive Doppler. To alleviate the degradation of image quality with respect to conventional focused acquisition, typically, multiple acquisitions from distinctly steered plane waves are coherently (i.e. after time-of-flight correction) compounded into a single image. This poses a trade-off between image quality and achievable frame-rate. To that end, we propose a new deep learning approach, derived by formulating plane wave compounding as a linear inverse problem, that attains high resolution, high-contrast images from just 3 plane wave transmissions. Our solution unfolds the iterations of a proximal gradient descent algorithm as a deep network, thereby directly exploiting the physics-based generative acquisition model into the neural network design. We train our network in a greedy manner, i.e. layer-by-layer, using a combination of pixel, temporal, and distribution (adversarial) losses to achieve both perceptual fidelity and data consistency. Through the strong model-based inductive bias, the proposed architecture outperforms several standard benchmark architectures in terms of image quality, with a low computational and memory footprint.

In this paper we adapt KalmanNet, which is a recently pro-posed deep neural network (DNN)-aided system whose architecture follows the operation of the model-based Kalman filter (KF), to learn its mapping in an unsupervised manner, i.e., without requiring ground-truth states. The unsupervised adaptation is achieved by exploiting the hybrid model-based/data-driven architecture of KalmanNet, which internally predicts the next observation as the KF does. These internal features are then used to compute the loss rather than the state estimate at the output of the system. With the capability of unsupervised learning, one can use KalmanNet not only to track the hidden state, but also to adapt to variations in the state space (SS) model. We numerically demonstrate that when the noise statistics are unknown, unsupervised KalmanNet achieves a similar performance to KalmanNet with supervised learning. We also show that we can adapt a pre-trained KalmanNet to changing SS models without providing additional data thanks to the unsupervised capabilities., Comment: 5 Pages, 5 Figures, Submitted to ICASSP 2022

Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking systems struggle to reliably characterize uncertainty. In this paper, we investigate the ability of KalmanNet, a recently proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. By exploiting the interpretable nature of KalmanNet, we show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure. We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the KF; and while in the presence of evolution model-mismatch, KalmanNet pro-vides a more accurate error estimation., Comment: Accepted to ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing

The smoothing task is core to many signal processing applications. A widely popular smoother is the Rauch-Tung-Striebel (RTS) algorithm, which achieves minimal mean-squared error recovery with low complexity for linear Gaussian state space (SS) models, yet is limited in systems that are only partially known, as well as non-linear and non-Gaussian. In this work we propose RTSNet, a highly efficient model-based and data-driven smoothing algorithm suitable for partially known SS models. RTSNet integrates dedicated trainable models into the flow of the classical RTS smoother, while iteratively refining its sequence estimate via deep unfolding methodology. As a result, RTSNet learns from data to reliably smooth when operating under model mismatch and non-linearities while retaining the efficiency and interpretability of the traditional RTS smoothing algorithm. Our empirical study demonstrates that RTSNet overcomes non-linearities and model mismatch, outperforming classic smoothers operating with both mismatched and accurate domain knowledge. Moreover, while RTSNet is based on compact neural networks, which leads to faster training and inference times, it demonstrates improved performance over previously proposed deep smoothers in non-linear settings., Comment: This manuscript is a preprint. It is partially based on work presented at IEEE ICASSP, Singapore, 2022. RTSNet: Deep Learning Aided Kalman Smoothing, doi:10.1109/ICASSP43922.2022.9746487. The extended version has been accepted for publication in IEEE Transactions on Signal Processing, 2023 RTSNet: Learning to Smooth in Partially Known State-Space Models, doi:10.1109/TSP.2023.3329964

The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to facilitate, e.g., drawing multiple samples, sampling from structured domains, or gradient estimation for error backpropagation in neural network optimization. The goal of this survey article is to present background about the Gumbel-max trick, and to provide a structured overview of its extensions to ease algorithm selection. Moreover, it presents a comprehensive outline of (machine learning) literature in which Gumbel-based algorithms have been leveraged, reviews commonly-made design choices, and sketches a future perspective., Comment: Accepted as a survey article in IEEE TPAMI

Direction of arrival (DoA) estimation of multiple signals is pivotal in sensor array signal processing. A popular multi-signal DoA estimation method is the multiple signal classification (MUSIC) algorithm, which enables high-performance super-resolution DoA recovery while being highly applicable in practice. MUSIC is a model-based algorithm, relying on an accurate mathematical description of the relationship between the signals and the measurements and assumptions on the signals themselves (non-coherent, narrowband sources). As such, it is sensitive to model imperfections. In this work we propose to overcome these limitations of MUSIC by augmenting the algorithm with specifically designed neural architectures. Our proposed deep augmented MUSIC (DA-MUSIC) algorithm is thus a hybrid model-based/data-driven DoA estimator, which leverages data to improve performance and robustness while preserving the interpretable flow of the classic method. DA-MUSIC is shown to learn to overcome limitations of the purely model-based method, such as its inability to successfully localize coherent sources as well as estimate the number of coherent signal sources present. We further demonstrate the superior resolution of the DA-MUSIC algorithm in synthetic narrowband and broadband scenarios as well as with real-world data of DoA estimation from seismic signals., Comment: Submitted to TVT

State estimation of dynamical systems in real-time is a fundamental task in signal processing. For systems that are well-represented by a fully known linear Gaussian state space (SS) model, the celebrated Kalman filter (KF) is a low complexity optimal solution. However, both linearity of the underlying SS model and accurate knowledge of it are often not encountered in practice. Here, we present KalmanNet, a real-time state estimator that learns from data to carry out Kalman filtering under non-linear dynamics with partial information. By incorporating the structural SS model with a dedicated recurrent neural network module in the flow of the KF, we retain data efficiency and interpretability of the classic algorithm while implicitly learning complex dynamics from data. We demonstrate numerically that KalmanNet overcomes non-linearities and model mismatch, outperforming classic filtering methods operating with both mismatched and accurate domain knowledge., Comment: Accepted for publication in IEEE Transactions on Signal Processing - TSP

Cognitive radars are systems that rely on learning through interactions of the radar with the surrounding environment. To realize this, radar transmit parameters can be adapted such that they facilitate some downstream task. This paper proposes the use of deep reinforcement learning (RL) to learn policies for gain control under the object detection task. The YOLOv3 single-shot object detector is used for the downstream task and will be concurrently used alongside the RL agent. Furthermore, a synthetic dataset is introduced which models the radar environment with use of the Grand Theft Auto V game engine. This approach allows for simulation of vast amounts of data with flexible assignment of the radar parameters to aid in the active learning process., Comment: 5 pages, 5 figures, conference

Many application domains, spanning from computational photography to medical imaging, require recovery of high-fidelity images from noisy, incomplete or partial/compressed measurements. State of the art methods for solving these inverse problems combine deep learning with iterative model-based solvers, a concept known as deep algorithm unfolding. By combining a-priori knowledge of the forward measurement model with learned (proximal) mappings based on deep networks, these methods yield solutions that are both physically feasible (data-consistent) and perceptually plausible. However, current proximal mappings only implicitly learn such image priors. In this paper, we propose to make these image priors fully explicit by embedding deep generative models in the form of normalizing flows within the unfolded proximal gradient algorithm. We demonstrate that the proposed method outperforms competitive baselines on various image recovery tasks, spanning from image denoising to inpainting and deblurring.

Unstructured neural network pruning algorithms have achieved impressive compression rates. However, the resulting - typically irregular - sparse matrices hamper efficient hardware implementations, leading to additional memory usage and complex control logic that diminishes the benefits of unstructured pruning. This has spurred structured coarse-grained pruning solutions that prune entire filters or even layers, enabling efficient implementation at the expense of reduced flexibility. Here we propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, kernels, filters/feature maps), while retaining efficient memory organization (e.g. pruning exactly k-out-of-n weights for every output neuron, or pruning exactly k-out-of-n kernels for every feature map). We refer to this algorithm as Dynamic Probabilistic Pruning (DPP). DPP leverages the Gumbel-softmax relaxation for differentiable k-out-of-n sampling, facilitating end-to-end optimization. We show that DPP achieves competitive compression rates and classification accuracy when pruning common deep learning models trained on different benchmark datasets for image classification. Relevantly, the non-magnitude-based nature of DPP allows for joint optimization of pruning and weight quantization in order to even further compress the network, which we show as well. Finally, we propose novel information theoretic metrics that show the confidence and pruning diversity of pruning masks within a layer.

Compressed sensing (CS) MRI relies on adequate undersampling of the k-space to accelerate the acquisition without compromising image quality. Consequently, the design of optimal sampling patterns for these k-space coefficients has received significant attention, with many CS MRI methods exploiting variable-density probability distributions. Realizing that an optimal sampling pattern may depend on the downstream task (e.g. image reconstruction, segmentation, or classification), we here propose joint learning of both task-adaptive k-space sampling and a subsequent model-based proximal-gradient recovery network. The former is enabled through a probabilistic generative model that leverages the Gumbel-softmax relaxation to sample across trainable beliefs while maintaining differentiability. The proposed combination of a highly flexible sampling model and a model-based (sampling-adaptive) image reconstruction network facilitates exploration and efficient training, yielding improved MR image quality compared to other sampling baselines.

Biomedical imaging is unequivocally dependent on the ability to reconstruct interpretable and high-quality images from acquired sensor data. This reconstruction process is pivotal across many applications, spanning from magnetic resonance imaging to ultrasound imaging. While advanced data-adaptive reconstruction methods can recover much higher image quality than traditional approaches, their implementation often poses a high computational burden. In ultrasound imaging, this burden is significant, especially when striving for low-cost systems, and has motivated the development of high-resolution and high-contrast adaptive beamforming methods. Here we show that deep neural networks that adopt the algorithmic structure and constraints of adaptive signal processing techniques can efficiently learn to perform fast high-quality ultrasound beamforming using very little training data. We apply our technique to two distinct ultrasound acquisition strategies (plane wave, and synthetic aperture), and demonstrate that high image quality can be maintained when measuring at low data-rates, using undersampled array designs. Beyond biomedical imaging, we expect that the proposed deep~learning based adaptive processing framework can benefit a variety of array and signal processing applications, in particular when data-efficiency and robustness are of importance.

Limitations on bandwidth and power consumption impose strict bounds on data rates of diagnostic imaging systems. Consequently, the design of suitable (i.e. task- and data-aware) compression and reconstruction techniques has attracted considerable attention in recent years. Compressed sensing emerged as a popular framework for sparse signal reconstruction from a small set of compressed measurements. However, typical compressed sensing designs measure a (non)linearly weighted combination of all input signal elements, which poses practical challenges. These designs are also not necessarily task-optimal. In addition, real-time recovery is hampered by the iterative and time-consuming nature of sparse recovery algorithms. Recently, deep learning methods have shown promise for fast recovery from compressed measurements, but the design of adequate and practical sensing strategies remains a challenge. Here, we propose a deep learning solution termed Deep Probabilistic Sub-sampling (DPS), that learns a task-driven sub-sampling pattern, while jointly training a subsequent task model. Once learned, the task-based sub-sampling patterns are fixed and straightforwardly implementable, e.g. by non-uniform analog-to-digital conversion, sparse array design, or slow-time ultrasound pulsing schemes. The effectiveness of our framework is demonstrated in-silico for sparse signal recovery from partial Fourier measurements, and in-vivo for both anatomical image and tissue-motion (Doppler) reconstruction from sub-sampled medical ultrasound imaging data.

Contrast enhanced ultrasound is a radiation-free imaging modality which uses encapsulated gas microbubbles for improved visualization of the vascular bed deep within the tissue. It has recently been used to enable imaging with unprecedented subwavelength spatial resolution by relying on super-resolution techniques. A typical preprocessing step in super-resolution ultrasound is to separate the microbubble signal from the cluttering tissue signal. This step has a crucial impact on the final image quality. Here, we propose a new approach to clutter removal based on robust principle component analysis (PCA) and deep learning. We begin by modeling the acquired contrast enhanced ultrasound signal as a combination of a low rank and sparse components. This model is used in robust PCA and was previously suggested in the context of ultrasound Doppler processing and dynamic magnetic resonance imaging. We then illustrate that an iterative algorithm based on this model exhibits improved separation of microbubble signal from the tissue signal over commonly practiced methods. Next, we apply the concept of deep unfolding to suggest a deep network architecture tailored to our clutter filtering problem which exhibits improved convergence speed and accuracy with respect to its iterative counterpart. We compare the performance of the suggested deep network on both simulations and in-vivo rat brain scans, with a commonly practiced deep-network architecture and the fast iterative shrinkage algorithm, and show that our architecture exhibits better image quality and contrast.

Ultrasound localization microscopy has enabled super-resolution vascular imaging through precise localization of individual ultrasound contrast agents (microbubbles) across numerous imaging frames. However, analysis of high-density regions with significant overlaps among the microbubble point spread responses yields high localization errors, constraining the technique to low-concentration conditions. As such, long acquisition times are required to sufficiently cover the vascular bed. In this work, we present a fast and precise method for obtaining super-resolution vascular images from high-density contrast-enhanced ultrasound imaging data. This method, which we term Deep Ultrasound Localization Microscopy (Deep-ULM), exploits modern deep learning strategies and employs a convolutional neural network to perform localization microscopy in dense scenarios. This end-to-end fully convolutional neural network architecture is trained effectively using on-line synthesized data, enabling robust inference in-vivo under a wide variety of imaging conditions. We show that deep learning attains super-resolution with challenging contrast-agent densities, both in-silico as well as in-vivo. Deep-ULM is suitable for real-time applications, resolving about 70 high-resolution patches (128x128 pixels) per second on a standard PC. Exploiting GPU computation, this number increases to 1250 patches per second.

Ultrasound localization microscopy offers new radiation-free diagnostic tools for vascular imaging deep within the tissue. Sequential localization of echoes returned from inert microbubbles with low-concentration within the bloodstream reveal the vasculature with capillary resolution. Despite its high spatial resolution, low microbubble concentrations dictate the acquisition of tens of thousands of images, over the course of several seconds to tens of seconds, to produce a single super-resolved image. %since each echo is required to be well separated from adjacent microbubbles. Such long acquisition times and stringent constraints on microbubble concentration are undesirable in many clinical scenarios. To address these restrictions, sparsity-based approaches have recently been developed. These methods reduce the total acquisition time dramatically, while maintaining good spatial resolution in settings with considerable microbubble overlap. %Yet, non of the reported methods exploit the fact that microbubbles actually flow within the bloodstream. % to improve recovery. Here, we further improve sparsity-based super-resolution ultrasound imaging by exploiting the inherent flow of microbubbles and utilize their motion kinematics. While doing so, we also provide quantitative measurements of microbubble velocities. Our method relies on simultaneous tracking and super-localization of individual microbubbles in a frame-by-frame manner, and as such, may be suitable for real-time implementation. We demonstrate the effectiveness of the proposed approach on both simulations and {\it in-vivo} contrast enhanced human prostate scans, acquired with a clinically approved scanner., Comment: 11 pages, 9 figures