Emine Ulku Saritas

Medical image reconstruction from undersampled acquisitions is an ill-posed inverse problem requiring accurate recovery of anatomical structures from incomplete measurements. Physics-driven (PD) network models have gained prominence for this task by integrating data-consistency mechanisms with learned priors, enabling improved performance over purely data-driven approaches. However, reconstruction quality still hinges on the network's ability to disentangle artifacts from true anatomical signals-both of which exhibit complex, multi-scale contextual structure. Convolutional neural networks (CNNs) capture local correlations but often struggle with non-local dependencies. While transformers aim to alleviate this limitation, practical implementations involve design compromises to reduce computational cost by balancing local and non-local sensitivity, occasionally resulting in performance comparable to CNNs. To address these challenges, we propose MambaRoll, a novel physics-driven autoregressive state space model (SSM) for high-fidelity and efficient image reconstruction. MambaRoll employs an unrolled architecture where each cascade autoregressively predicts finer-scale feature maps conditioned on coarser-scale representations, enabling consistent multi-scale context propagation. Each stage is built on a hierarchy of scale-specific PD-SSM modules that capture spatial dependencies while enforcing data consistency through residual correction. To further improve scale-aware learning, we introduce a Deep Multi-Scale Decoding (DMSD) loss, which provides supervision at intermediate spatial scales in alignment with the autoregressive design. Demonstrations on accelerated MRI and sparse-view CT reconstructions show that MambaRoll provides improved performance relative to state-of-the-art CNN-, transformer-, and SSM-based methods.

The bending dynamics of microscopic filaments play a crucial role in various mechanical and biological processes. While thermal fluctuations typically have a minor effect, active fluctuations can provide sufficient mechanical energy to alter bending deformations in these systems. In this work, we investigate how active noise influences the bending dynamics of a self-assembled chain of magnetic particles at a curved liquid-air interface in the presence of swimming E. coli bacteria. We analyze the bending behavior of semiflexible chains under a lateral gravitational force and compare their response in passive and active baths. In a passive bath, the chain remains bent, fluctuating slightly around its deformed configuration due to thermal noise. However, in an active bath, strong bacterial activity suppresses the average bending deformation, causing the chain to fluctuate around a nearly straight configuration. These findings highlight the impact of active fluctuations on self-assembled microstructures and demonstrate a simple yet effective approach to studying the mechanical dynamics of microscopic filaments.

Transformers have gained prominence in natural language processing due to their representational capabilities and performances. Transformers process natural language as a sequence on finite context windows; however, global relationships among words beyond these windows cannot be completely modeled via sequence processing only. Graph neural network (GNN) based models have been proposed to alleviate this problem, as they provide geometric extensions to neural networks, enabling models to learn associations within a text. However, regular graph-based methods ignore the sequential nature of underlying texts. In this paper, we propose EmoVis, the first generic graph-based neural network that utilizes visibility graphs, which converts classical time-series information to graph representations. We cast the problem as an emotion classification task, enabling the proposed model to learn associations between the labels and words in a sentence. Moreover, EmoVis can be used as a highly modular graph-based extension to any transformer-based model, significantly improving their performance and learning capabilities in various languages. We experimentally show that EmoVis enables transformer-based models to outperform the state-of-the-art baselines across three diverse datasets in different languages in the SemEval2018 competition datasets and the GoEmotions dataset.

In magnetic particle imaging (MPI), selection field (SF) gradients are utilized to form a field-free point (FFP) in space, such that only the magnetic nanoparticles (MNPs) in the vicinity of the FFP respond to the applied drive field (DF) and contribute to the received signal. While the relaxation behavior of MNPs adversely affects image quality by reducing signal intensity and causing blurring, it also provides MPI with functional imaging capabilities, such as viscosity and temperature mapping. This work investigates the effects of SF gradients on the relaxation behavior of the MNPs using an in-house magnetic particle spectrometer (MPS) setup equipped with an additional DC electromagnet SF coil, which switches the MPS setup into an MPI system. The results reveal that the presence of SF gradients boosts the viscosity sensitivity of MPI, and that the MPI signal can be sensitized to viscosity even at high DF frequencies and amplitudes if sufficiently large SF gradients are applied.

In magnetic particle imaging (MPI), simultaneous excitation and signal acquisition leads to direct feedthrough interference. While this interference can be mitigated up to some extent with passive compensation, its time-varying nature necessitates active compensation methods to achieve the sensitivity levels needed for applications such as stem cell tracking. We have recently proposed an active compensation technique for MRI, which uses a vector modulator and a lookup-table-based algorithm for reducing the direct feedthrough in the analog domain. Here, we adapt this technique to MPI, demonstrating a successful recovery of the fundamental frequency and a significant increase in detection sensitivity.

Monitoring of prevalent airborne diseases such as COVID-19 characteristically involves respiratory assessments. While auscultation is a mainstream method for preliminary screening of disease symptoms, its utility is hampered by the need for dedicated hospital visits. Remote monitoring based on recordings of respiratory sounds on portable devices is a promising alternative, which can assist in early assessment of COVID-19 that primarily affects the lower respiratory tract. In this study, we introduce a novel deep learning approach to distinguish patients with COVID-19 from healthy controls given audio recordings of cough or breathing sounds. The proposed approach leverages a novel hierarchical spectrogram transformer (HST) on spectrogram representations of respiratory sounds. HST embodies self-attention mechanisms over local windows in spectrograms, and window size is progressively grown over model stages to capture local to global context. HST is compared against state-of-the-art conventional and deep-learning baselines. Demonstrations on crowd-sourced multi-national datasets indicate that HST outperforms competing methods, achieving over 90% area under the receiver operating characteristic curve (AUC) in detecting COVID-19 cases.

Magnetic nanoparticles have been extensively explored as theranostic agents both in academic and clinical settings. Their self-assembly into nanohybrids using block copolymers can lead to new nanostructures with high functionalities and performances. Herein, we demonstrate a high-throughput and scalable method to elaborate magnetic micelles by the assembly of iron oxide magnetite nanoflowers, an efficient nanoheater, and the block copolymer Poly(styrene)-block-poly(acrylic acid) via a microfluidic-assisted nanoprecipitation method. We show that the size and shape of the magnetomicelles can be easily tuned by modulating the residence time in the microfluidic channel. In addition to their biocompatibility, we demonstrate the potential of these magnetic nanohybrids as multimodal theranostic platforms capable of generating heat by photothermia and functioning as negative contrast agents in magnetic resonance imaging and as imaging tracers in magnetic particle imaging. Notably, they outperform currently commercially available particles in terms of imaging functionalities.

Purpose: To introduce an unsupervised deep‐learning method for fast and effective correction of susceptibility artifacts in reversed phase‐encode (PE) image pairs acquired with echo planar imaging (EPI).Methods: Recent learning‐based correction approaches in EPI estimate a displacement field, unwarp the reversed‐PE image pair with the estimated field, and average the unwarped pair to yield a corrected image. Unsupervised learning in these unwarping‐based methods is commonly attained via a similarity constraint between the unwarped images in reversed‐PE directions, neglecting consistency to the acquired EPI images. This work introduces a novel unsupervised deep Forward‐Distortion Network (FD‐Net) that predicts both the susceptibility‐induced displacement field and the underlying anatomically correct image. Unlike previous methods, FD‐Net enforces the forward‐distortions of the correct image in both PE directions to be consistent with the acquired reversed‐PE image pair. FD‐Net further leverages a multiresolution architecture to maintain high local and global performance.Results: FD‐Net performs competitively with a gold‐standard reference method (TOPUP) in image quality, while enabling a leap in computational efficiency. Furthermore, FD‐Net outperforms recent unwarping‐based methods for unsupervised correction in terms of both image and field quality.Conclusion: The unsupervised FD‐Net method introduces a deep forward‐distortion approach to enable fast, high‐fidelity correction of susceptibility artifacts in EPI by maintaining consistency to measured data. Therefore, it holds great promise for improving the anatomical accuracy of EPI imaging.

Magnetic particle imaging (MPI) offers unparalleled contrast and resolution for tracing magnetic nanoparticles. A common imaging procedure calibrates a system matrix (SM) that is used to reconstruct data from subsequent scans. The ill-posed reconstruction problem can be solved by simultaneously enforcing data consistency based on the SM and regularizing the solution based on an image prior. Traditional hand-crafted priors cannot capture the complex attributes of MPI images, whereas recent MPI methods based on learned priors can suffer from extensive inference times or limited generalization performance. Here, we introduce a novel physics-driven method for MPI reconstruction based on a deep equilibrium model with learned data consistency (DEQ-MPI). DEQ-MPI reconstructs images by augmenting neural networks into an iterative optimization, as inspired by unrolling methods in deep learning. Yet, conventional unrolling methods are computationally restricted to few iterations resulting in non-convergent solutions, and they use hand-crafted consistency measures that can yield suboptimal capture of the data distribution. DEQ-MPI instead trains an implicit mapping to maximize the quality of a convergent solution, and it incorporates a learned consistency measure to better account for the data distribution. Demonstrations on simulated and experimental data indicate that DEQ-MPI achieves superior image quality and competitive inference time to state-of-the-art MPI reconstruction methods.

In this research, a multi‐step microfluidic reactor was used to fabricate chitosan – superparamagnetic iron oxide composite nanoparticles (Ch – SPIONs), where composite formation using chitosan was aimed to provide antibacterial property and nanoparticle stability for magnetic resonance imaging (MRI). Monodispersed Ch – SPIONs had an average particle size of 8.8 ± 1.2 nm with a magnetization value of 32.0 emu/g. Ch – SPIONs could be used as an MRI contrast agent by shortening T₂ relaxation parameter of the surrounding environment, as measured on a 3 T MRI scanner. In addition, Ch – SPIONs with concentrations less than 1 g/L promoted bone cell (osteoblast) viability up to 7 days of culture in vitro in the presence of 0.4 T external static magnetic field. These nanoparticles were also tested against Staphylococcus aureus (S. aureus) and Pseudomonas aeruginosa (P. aeruginosa), which are dangerous pathogens that cause infection in tissues and biomedical devices. Upon interaction of Ch – SPIONs with S. aureus and P. aeruginosa at 0.01 g/L concentration, nearly a 2‐fold reduction in the number of colonies was observed for both bacteria strains at 48 h of culture. Results cumulatively showed that Ch – SPIONs were potential candidates as a cytocompatible and antibacterial agent that can be targeted to biofilm and imaged using an MRI.