Tolga Cukur

Bilkent University · Department of Electrical & Electronics Engineering

Medical image reconstruction from undersampled acquisitions is an ill-posed problem that involves inversion of the imaging operator linking measurement and image domains. In recent years, physics-driven (PD) models have gained prominence in learning-based reconstruction given their enhanced balance between efficiency and performance. For reconstruc...

Learning-based methods offer performance leaps over traditional methods in classification analysis of high-dimensional functional MRI (fMRI) data. In this domain, deep-learning models that analyze functional connectivity (FC) features among brain regions have been particularly promising. However, many existing models receive as input temporally sta...

Diffusion models have recently been shown to excel in many image reconstruction tasks that involve inverse problems based on a forward measurement operator. A common framework uses task-agnostic unconditional models that are later post-conditioned for reconstruction, an approach that typically suffers from suboptimal task performance. While task-sp...

In recent years, deep learning models comprising transformer components have pushed the performance envelope in medical image synthesis tasks. Contrary to convolutional neural networks (CNNs) that use static, local filters, transformers use self-attention mechanisms to permit adaptive, non-local filtering to sensitively capture long-range context....

Compressive focal plane arrays (FPA) enable costeffective high-resolution (HR) imaging by acquisition of several multiplexed measurements on a low-resolution (LR) sensor. Multiplexed encoding of the visual scene is often attained via electronically controllable spatial light modulators (SLM). To capture system non-idealities such as optical aberrat...

Deep learning analyses have offered sensitivity leaps in detection of cognition-related variables from functional MRI (fMRI) measurements of brain responses. Yet, as deep models perform hierarchical nonlinear transformations on fMRI data, interpreting the association between individual brain regions and the detected variables is challenging. Among...

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...

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 fie...

Magnetic Resonance Imaging (MRI) produces excellent soft tissue contrast, albeit it is an inherently slow imaging modality. Promising deep learning methods have recently been proposed to reconstruct accelerated MRI scans. However, existing methods still suffer from various limitations regarding image fidelity, contextual sensitivity, and reliance o...

Discover the power of deep neural networks for image reconstruction with this state-of-the-art review of modern theories and applications. The background theory of deep learning is introduced step-by-step, and by incorporating modeling fundamentals this book explains how to implement deep learning in a variety of modalities, including X-ray, CT, MR...

Recent years have witnessed a surge in deep generative models for accelerated MRI reconstruction. Diffusion priors in particular have gained traction with their superior representational fidelity and diversity. Instead of the target transformation from undersampled to fully-sampled data, common diffusion priors are trained to learn a multi-step tra...

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 regular...

Deep learning analyses have offered sensitivity leaps in detection of cognitive states from functional MRI (fMRI) measurements across the brain. Yet, as deep models perform hierarchical nonlinear transformations on their input, interpreting the association between brain responses and cognitive states is challenging. Among common explanation approac...

Imputation of missing images via source-to-target modality translation can improve diversity in medical imaging protocols. A pervasive approach for synthesizing target images involves one-shot mapping through generative adversarial networks (GAN). Yet, GAN models that implicitly characterize the image distribution can suffer from limited sample fid...

Magnetic Resonance Imaging (MRI) produces excellent soft tissue contrast, albeit it is an inherently slow imaging modality. Promising deep learning methods have recently been proposed to reconstruct accelerated MRI scans. However, existing methods still suffer from various limitations regarding image fidelity, contextual sensitivity, and reliance o...

Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator, they can show poor generalization across variable operators. Unconditional models instead learn generative im...

Deep-learning models have enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) data. Yet, many previous methods are suboptimally sensitive for contextual representations across diverse time scales. Here, we present BolT, a blood-oxygen-level-dependent transformer model, for analyzing multi-variate fMRI time series. BolT l...

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 dir...

Purpose: To develop a deep learning model that predicts active inflammation from sacroiliac joint radiographs and to compare the success with radiologists. Materials and Methods: A total of 1,537 (augmented 1752) grade 0 SIJs of 768 patients were retrospectively analyzed. Gold-standard MRI exams showed active inflammation in 330 joints according to...

Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan times. Reconstruction methods can alleviate this limitation by recovering clinically usable images from accelerated acquisitions. In particular, learning-based methods promise performance leaps by employing deep neural networks as data-driven priors. A...

Learning-based methods have recently enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) time series. Deep learning models that receive as input functional connectivity (FC) features among brain regions have been commonly adopted in the literature. However, many models focus on temporally static FC features across a scan...

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 regular...

Broadspread use of medical imaging devices with digital storage has paved the way for curation of substantial data repositories. Fast access to image samples with similar appearance to suspected cases can help establish a consulting system for healthcare professionals, and improve diagnostic procedures while minimizing processing delays. However, m...

Multi-institutional efforts can facilitate training of deep MRI reconstruction models, albeit privacy risks arise during cross-site sharing of imaging data. Federated learning (FL) has recently been introduced to address privacy concerns by enabling distributed training without transfer of imaging data. Existing FL methods employ conditional recons...

MRI translation models learn a mapping from an acquired source contrast to an unavailable target contrast. Collaboration between institutes is essential to train translation models that can generalize across diverse datasets. That said, aggregating all imaging data and training a centralized model poses privacy problems. Recently, federated learnin...

Deep learning models have been broadly adopted for accelerating MRI acquisitions in recent years. A common approach is to train deep models based on loss functions that place equal emphasis on reconstruction errors across the field-of-view. This homogeneous weighting of loss contributions might be undesirable in cases where the diagnostic focus is...

Deep learning has been successfully adopted for accelerated MRI reconstruction given its exceptional performance in inverse problems. Deep reconstruction models are commonly based on convolutional neural network (CNN) architectures that use compact input-invariant filters to capture static local features in data. While this inductive bias allows ef...

Magnetic particle imaging (MPI) is a recent modality that enables high contrast and frame-rate imaging of the magnetic nanoparticle (MNP) distribution. Based on a measured system matrix, MPI reconstruction can be cast as an inverse problem that is commonly solved via regularized iterative optimization. Yet, hand-crafted regularization terms can eli...

The processing of legal texts has been developing as an emerging field in natural language processing (NLP). Legal texts contain unique jargon and complex linguistic attributes in vocabulary, semantics, syntax, and morphology. Therefore, the development of text simplification (TS) methods specific to the legal domain is of paramount importance for...

Learning-based translation between MRI contrasts involves supervised deep models trained using high-quality source- and target-contrast images derived from fully-sampled acquisitions, which might be difficult to collect under limitations on scan costs or time. To facilitate curation of training sets, here we introduce the first semi-supervised mode...

Object and action perception in cluttered dynamic natural scenes relies on efficient allocation of limited brain resources to prioritize the attended targets over distractors. It has been suggested that during visual search for objects, distributed semantic representation of hundreds of object categories is warped to expand the representation of ta...

Monitoring of prevalent airborne diseases such as COVID-19 characteristically involve respiratory assessments. While auscultation is a mainstream method for symptomatic monitoring, its diagnostic utility is hampered by the need for dedicated hospital visits. Continual remote monitoring based on recordings of respiratory sounds on portable devices i...

Imputation of missing images via source-to-target modality translation can facilitate downstream tasks in medical imaging. A pervasive approach for synthesizing target images involves one-shot mapping through generative adversarial networks (GAN). Yet, GAN models that implicitly characterize the image distribution can suffer from limited sample fid...

Learning-based MRI translation involves a synthesis model that maps a source-contrast onto a target-contrast image. Multi-institutional collaborations are key to training synthesis models across broad datasets, yet centralized training involves privacy risks. Federated learning (FL) is a collaboration framework that instead adopts decentralized tra...

Deep MRI reconstruction is commonly performed with conditional models that map undersampled data as input onto fully-sampled data as output. Conditional models perform de-aliasing under knowledge of the accelerated imaging operator, so they poorly generalize under domain shifts in the operator. Unconditional models are a powerful alternative that i...

Magnetic particle imaging (MPI) offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used to set up an inverse problem to reconstruct images of the MNP distribution during subsequent scans. This calib...

Functional magnetic resonance imaging (fMRI) enables examination of inter-regional interactions in the brain via functional connectivity (FC) analyses that measure the synchrony between the temporal activations of separate regions. Given their exceptional sensitivity, deep-learning methods have received growing interest for FC analyses of high-dime...

We propose bidirectional imparting or BiImp, a generalized method for aligning embedding dimensions with concepts during the embedding learning phase. While preserving the semantic structure of the embedding space, BiImp makes dimensions interpretable, which has a critical role in deciphering the black-box behavior of word embeddings. BiImp separat...

Generative adversarial models with convolutional neural network (CNN) backbones have recently been established as state-of-the-art in numerous medical image synthesis tasks. However, CNNs are designed to perform local processing with compact filters, and this inductive bias compromises learning of contextual features. Here, we propose a novel gener...

Magnetic resonance imaging (MRI) offers the flexibility to image a given anatomic volume under a multitude of tissue contrasts. Yet, scan time considerations put stringent limits on the quality and diversity of MRI data. The gold-standard approach to alleviate this limitation is to recover high-quality images from data undersampled across various d...

Multi-institutional efforts can facilitate training of deep MRI reconstruction models, albeit privacy risks arise during cross-site sharing of imaging data. Federated learning (FL) has recently been introduced to address privacy concerns by enabling distributed training without transfer of imaging data. Existing FL methods for MRI reconstruction em...

Purpose Image quality in accelerated MRI rests on careful selection of various reconstruction parameters. A common yet tedious and error-prone practice is to hand-tune each parameter to attain visually appealing reconstructions. Here, we propose a parameter tuning strategy to automate hybrid parallel imaging (PI) – compressed sensing (CS) reconstru...

Supervised reconstruction models are characteristically trained on matched pairs of undersampled and fully-sampled data to capture an MRI prior, along with supervision regarding the imaging operator to enforce data consistency. To reduce supervision requirements, the recent deep image prior framework instead conjoins untrained MRI priors with the i...

Magnetic particle imaging (MPI) is a recent modality that offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used to setup an inverse problem to reconstruct images of the particle distribution durin...

Magnetic Particle Imaging (MPI) is a new imaging technique that allows high resolution & high frame-rate imaging of magnetic nanoparticles (MNP). It relies on the nonlinear response of MNPs under a magnetic field. The imaging process can be modeled linearly, and then image reconstruction can be case as an inverse problem using a measured system mat...

Supervised training of deep network models for MRI reconstruction requires access to large databases of fully-sampled MRI acquisitions. To alleviate dependency on costly databases, unsupervised learning strategies have received interest. A powerful framework that eliminates the need for training data altogether is the deep image prior (DIP). To do...

Deep learning techniques have recently been adopted for accelerating dynamic MRI acquisitions. Yet, common frameworks for model training rely on availability of large sets of fully-sampled MRI data to construct a ground-truth for the network output. This heavy reliance is undesirable as it is challenging to collect such large datasets in many appli...

Balanced steady-state free precession (bSSFP) imaging enables high scan efficiency in MRI, but differs from conventional sequences in terms of elevated sensitivity to main field inhomogeneity and nonstandard ${\text {T}}_{{2}}/{\text {T}}_{{1}}$ -weighted tissue contrast. To address these limitations, multiple bSSFP images of the same anatomy are...

Humans have an impressive ability to rapidly process global information in natural scenes to infer their category. Yet, it remains unclear whether and how scene categories observed dynamically in the natural world are represented in cerebral cortex beyond few canonical scene-selective areas. To address this question, here we examined the representa...

Multi-modal imaging is a key healthcare technology in the diagnosis and management of disease, but it is often underutilized due to costs associated with multiple separate scans. This limitation yields the need for synthesis of unacquired modalities from the subset of available modalities. In recent years, generative adversarial network (GAN) model...

Object and action perception in cluttered dynamic natural scenes relies on efficient allocation of limited brain resources to prioritize the attended targets over distractors. It has been suggested that during visual search for objects, distributed semantic representation of hundreds of object categories is warped to expand the representation of ta...

Humans are remarkably adept in listening to a desired speaker in a crowded environment, while filtering out nontarget speakers in the background. Attention is key to solving this difficult cocktail-party task, yet a detailed characterization of attentional effects on speech representations is lacking. It remains unclear across what levels of speech...

Balanced steady-state free precession (bSSFP) imaging enables high scan efficiency in MRI, but differs from conventional sequences in terms of elevated sensitivity to main field inhomogeneity and nonstandard T2/T1-weighted tissue contrast. To address these limitations, multiple bSSFP images of the same anatomy are commonly acquired with a set of di...

Supervised deep learning has swiftly become a workhorse for accelerated MRI in recent years, offering state-of-the-art performance in image reconstruction from undersampled acquisitions. Training deep supervised models requires large datasets of undersampled and fully-sampled acquisitions typically from a matching set of subjects. Given scarce acce...

Complex natural tasks likely recruit many different functional brain networks, but it is difficult to predict how such tasks will be represented across cortical areas and networks. Previous electrophysiology studies suggest that task variables are represented in a low-dimensional subspace within the activity space of neural populations. Here we dev...

Deep neural networks (DNNs) have recently found emerging use in accelerated MRI reconstruction. DNNs typically learn data-driven priors from large datasets constituting pairs of undersampled and fully-sampled acquisitions. Acquiring such large datasets, however, might be impractical. To mitigate this limitation, we propose a few-shot learning appro...

Multi-contrast MRI protocols increase the level of morphological information available for diagnosis. Yet, the number and quality of contrasts are limited in practice by various factors including scan time and patient motion. Synthesis of missing or corrupted contrasts from other high-quality ones can alleviate this limitation. When a single target...

Mainstream deep models for three-dimensional MRI synthesis are either cross-sectional or volumetric depending on the input. Cross-sectional models can decrease the model complexity, but they may lead to discontinuity artifacts. On the other hand, volumetric models can alleviate the discontinuity artifacts, but they might suffer from loss of spatial...

Humans are remarkably adept in listening to a desired speaker in a crowded environment, while filtering out non-target speakers in the background. Attention is key to solving this difficult cocktail-party task, yet a detailed characterization of attentional effects on speech representations is lacking. It remains unclear across what levels of speec...

This study proposes a novel semi-supervised learning framework for mutually accelerated multi-contrast MRI synthesis that recovers high-quality images without demanding large training sets of costly fully-sampled source or ground-truth target images. The proposed method presents a selective loss function expressed only on a subset of the acquired k...

Magnetic resonance imaging (MRI) offers the flexibility to image a given anatomic volume under a multitude of tissue contrasts. Yet, scan time considerations put stringent limits on the quality and diversity of MRI data. The gold-standard approach to alleviate this limitation is to recover high-quality images from data undersampled across various d...

Multi-contrast MRI acquisitions of an anatomy enrich the magnitude of information available for diagnosis. Yet, excessive scan times associated with additional contrasts may be a limiting factor. Two mainstream frameworks for enhanced scan efficiency are reconstruction of undersampled acquisitions and synthesis of missing acquisitions. Recently, de...

Voxelwise modeling is a powerful framework to predict single‐voxel functional selectivity for the stimulus features that exist in complex natural stimuli. Yet, because VM disregards potential correlations across stimulus features or neighboring voxels, it may yield suboptimal sensitivity in measuring functional selectivity in the presence of high l...

Purpose Magnetostimulation, also known as peripheral nerve stimulation (PNS), is the dominant safety constraint in magnetic resonance imaging (MRI) for the gradient magnetic fields that operate around 0.1–1 kHz, and for the homogeneous drive field in magnetic particle imaging (MPI) that operates around 10–150 kHz. Previous studies did not report co...

Objective: Balanced steady-state free precession (bSSFP) imaging suffers from banding artifacts in the presence of magnetic field inhomogeneity. The purpose of this study is to identify an efficient strategy to reconstruct banding-free bSSFP images from multi-coil multi-acquisition datasets. Method: Previous techniques either assume that a naïve...

Multi-contrast images are commonly acquired together to maximize complementary diagnostic information, albeit at the expense of longer scan times. A time-efficient strategy to acquire high-quality multi-contrast images is to accelerate individual sequences and then reconstruct undersampled data with joint regularization terms that leverage common i...

Purpose Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally, network performance should be optimized by drawing the training and testing data from the same domain. In practice, however, large datasets comprising hundreds of subjects scanned under a common protocol are rare. The goal of this stud...

Humans divide their attention among multiple visual targets in daily life, and visual search can get more difficult as the number of targets increases. The biased competition hypothesis (BC) has been put forth as an explanation for this phenomenon. BC suggests that brain responses during divided attention are a weighted linear combination of the re...

Multi-contrast MRI protocols increase the level of morphological information available for diagnosis. Yet, the number and quality of contrasts is limited in practice by various factors including scan time and patient motion. Synthesis of missing or corrupted contrasts can alleviate this limitation to improve clinical utility. Common approaches for...

Human brain integrates sensory information across time to represent dynamic complex daily-life environments. Previous studies have shown that higher level perceptual and cognitive cortical areas tend to integrate information over longer time windows, suggesting presence of a hierarchy of temporal receptive windows (TRW) across the brain. Yet, atten...

Magnetic particle imaging (MPI) is an emerging biomedical imaging modality that exploits the nonlinear response of superparamagnetic iron oxide (SPIO) nanoparticles to image their spatial distribution. Previously, various scanning trajectories were analyzed for the system function reconstruction (SFR) approach, providing important insight regarding...

Humans divide their attention among multiple visual targets in daily life, and visual search gets more difficult as the number of targets increases. The biased competition hypothesis (BC) has been put forth as an explanation for this phenomenon. BC suggests that brain responses during divided attention are a weighted linear combination of the respo...