Deep Unfolded Robust PCA With Application to Clutter Suppression in Ultrasound

Abstract

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.

Learned SPARCOM: Unfolded Deep Super-Resolution Microscopy

“…In the original paper suggesting algorithm unfolding [17], the authors unfold the iterative algorithm with minimal modifications, leaving the multiplication operators used in the original algorithm intact. Recent publications [24,26] suggest convolutional extensions to the original approach, allowing a dual benefit: exploiting the shared spatial information between neighboring image pixels, and significantly reducing the number of trainable parameters, leading to more effective training.…”

“…In their seminal work, Gregor and LeCun unfolded the Iterative Shrinkage-Thresholding Algorithm (ISTA) for sparse coding [20,21] into a learned ISTA (LISTA) network, and demonstrated that propagating the data through only 10 blocks is equivalent to running the iterative algorithm for 200 iterations, without requiring fine-tuning of any parameters. In recent years, the concept of algorithm unfolding has been applied to many different problems, including, among others, single-image-superresolution (deblurring) [22,23], image denoising and image inpainting [24], ultrasound localization microscopy [25], ultrasound clutter suppression [26], and multi-channel source separation [27].…”

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

“…Our design is inspired by deep unfolding, which is a common method for obtaining ML architectures from model-based iterative algorithms [5], [20]. Unfolding was shown to yield efficient and reliable DNNs for applications such as sparse recovery [5], recovery from one-bit measurements [6], matrix factorization [21], image deblurring [22], and robust principal component analysis [23]. However, there is a fundamental difference between our approach and conventional unfolding: The main rationale of unfolding is to convert each iteration of the algorithm into a layer, namely, to design a DNN in light of a modelbased algorithm, or alternatively, to integrate the algorithm into the DNN.…”

Deep Learning in Ultrasound Imaging

“…To overcome these limitations, in [81], [82], [83], the task of clutter removal was formulated as a convex optimization problem by leveraging a low-rank-and-sparse decomposition. The authors of [81] then proposed an efficient deep learning solution to this convex optimization problem through an algorithmunfolding strategy [84]. To enable explicit embedding of signal structure in the resulting network architecture, the following model for the signal after beamforming was proposed.…”