Browsing by Author "Bedel, Hasan Atakan"

Now showing 1 - 8 of 8

Open Access
A plug-in graph neural network to boost temporal sensitivity in fMRI analysis
(IEEE, 2024-09) Şıvgın, Irmak; Bedel, Hasan Atakan; Ozturk, Saban; Çukur, Tolga
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 static FC features that summarize inter-regional interactions across an entire scan, reducing the temporal sensitivity of classifiers by limiting their ability to leverage information on dynamic FC features of brain activity. To improve the performance of baseline classification models without compromising efficiency, here we propose a novel plug-in based on a graph neural network, GraphCorr, to provide enhanced input features to baseline models. The proposed plug-in computes a set of latent FC features with enhanced temporal information while maintaining comparable dimensionality to static features. Taking brain regions as nodes and blood-oxygen-level-dependent (BOLD) signals as node inputs, GraphCorr leverages a node embedder module based on a transformer encoder to capture dynamic latent representations of BOLD signals. GraphCorr also leverages a lag filter module to account for delayed interactions across nodes by learning correlational features of windowed BOLD signals across time delays. These two feature groups are then fused via a message passing algorithm executed on the formulated graph. Comprehensive demonstrations on three public datasets indicate improved classification performance for several state-of-the-art graph and convolutional baseline models when they are augmented with GraphCorr.
Open Access
Adaptive diffusion priors for accelerated MRI reconstruction
(Elsevier B.V., 2023-07-20) Güngör, Alper; Dar, Salman Ul Hassan; Öztürk, Şaban; Korkmaz, Yılmaz; Bedel, Hasan Atakan; Elmas, Gökberk; Özbey, Muzaffer; Çukur, Tolga
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 image priors decoupled from the operator to improve reliability against domain shifts related to the imaging operator. Recent diffusion models are particularly promising given their high sample fidelity. Nevertheless, inference with a static image prior can perform suboptimally. Here we propose the first adaptive diffusion prior for MRI reconstruction, AdaDiff, to improve performance and reliability against domain shifts. AdaDiff leverages an efficient diffusion prior trained via adversarial mapping over large reverse diffusion steps. A two-phase reconstruction is executed following training: a rapid-diffusion phase that produces an initial reconstruction with the trained prior, and an adaptation phase that further refines the result by updating the prior to minimize data-consistency loss. Demonstrations on multi-contrast brain MRI clearly indicate that AdaDiff outperforms competing conditional and unconditional methods under domain shifts, and achieves superior or on par within-domain performance. © 2023 Elsevier B.V.
Open Access
BolT: Fused window transformers for fMRI time series analysis
(Elsevier B.V., 2023-05-18) Bedel, Hasan Atakan; Şıvgın, Irmak; Dalmaz, Onat; Ul Hassan Dar, Salman ; Çukur, Tolga
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 leverages a cascade of transformer encoders equipped with a novel fused window attention mechanism. Encoding is performed on temporally-overlapped windows within the time series to capture local representations. To integrate information temporally, cross-window attention is computed between base tokens in each window and fringe tokens from neighboring windows. To gradually transition from local to global representations, the extent of window overlap and thereby number of fringe tokens are progressively increased across the cascade. Finally, a novel cross-window regularization is employed to align high-level classification features across the time series. Comprehensive experiments on large-scale public datasets demonstrate the superior performance of BolT against state-of-the-art methods. Furthermore, explanatory analyses to identify landmark time points and regions that contribute most significantly to model decisions corroborate prominent neuroscientific findings in the literature.
Open Access
DreaMR: diffusion driven counterfactual explanation for functional MRI
(IEEE, 2024-11-27) Bedel, Hasan Atakan; Çukur, Tolga
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 explanation approaches for deep fMRI classifiers, attribution methods show poor specificity and perturbation methods show limited sensitivity. While counterfactual generation promises to address these limitations, previous counterfactual methods based on variational or adversarial priors can yield suboptimal sample fidelity. Here, we introduce the first diffusion-driven counterfactual method, DreaMR, to enable fMRI interpretation with high fidelity. DreaMR performs diffusion-based resampling of an input fMRI sample to alter the decision of a downstream classifier, and then computes the difference between the original sample and the counterfactual sample for explanation. Unlike conventional diffusion methods, DreaMR leverages a novel fractional multi-phase-distilled diffusion prior to improve inference efficiency without compromising fidelity, and it employs a transformer architecture to account for long-range spatiotemporal context in fMRI scans. Comprehensive experiments on neuroimaging datasets demonstrate the superior fidelity and efficiency of DreaMR in sample generation over state-of-the-art counterfactual methods for fMRI explanation.
Open Access
Employing transformer encoders for enhanced functional connectivity mapping
(IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Bedel, Hasan Atakan; Çukur, Tolga
Functional magnetic resonance imaging (fMRI) provides a way to spatially and temporally map brain activity, making it a crucial tool in many advanced psychology and neuroscience studies. A variety of techniques are suggested to analyze the four-dimensional data produced by fMRI scans. When it comes to classification tasks, the most prevalent method involves examining functional connectivity. This process involves dividing the brain volume into separate regions and determining the correlation between the series of events occurring over time in these regions. While deep graph models and deep convolutional models are frequently employed to process functional connectivity, these methods can sometimes overcomplicate the procedure. In contrast, we present a straightforward approach that utilizes transformer encoders to map functional connectivity to labels. Our method demonstrates superior performance in gender classification tasks when compared to existing deep graph and convolution models. We've validated this on two publicly accessible datasets.
Open Access
A graphical network layer for lagged analysis of FMRI data
(IEEE, 2022-08-29) Bedel, Hasan Atakan; Şıvgın, Irmak; Çukur, Tolga
Functional magnetic resonance imaging (fMRI) enables recording the brain’s neural activity spatiotemporally and is the center of much cutting-edge psychology and neuroscience research. Many methods are proposed to process the 4-dimensional data the fMRI scans provide. The most common approach for classification tasks is to analyze functional connectivity, where brain volume is parcelled to regions, and the correlation between their time series is calculated. Such an approach is very suitable for graphical neural networks, a popular deep learning method for graphical data analysis. A graph is constructed by formulating the parcelled brain regions as the graph nodes, while their features and edges are constructed from the correlations. However, in many studies, the correlations are calculated from simple methods that do not take account of the lagged relations between the node time-series. This paper addresses this issue by proposing a new graphical neural network layer. This layer accounts for lagged relationships between the nodes and learns reacher features rather than simple zero-lag correlations. We show that our graphical layer can be used in front of a known graphical model and increase its performance for two different downstream tasks in a large fMRI dataset.
Open Access
Novel deep learning approaches for functional FMRI data analysis
(2024-08) Bedel, Hasan Atakan
Functional MRI (fMRI) has revolutionized our ability to analyze brain activity by providing insights into high-dimensional, time-series data. Despite advancements, existing methods often fall short in their ability to effectively capture contextual representations across varying time scales and interpret the resulting data. Addressing these challenges, this thesis introduces three innovative ap-proaches: BolT, GraphCorr, and DreaMR, each designed to enhance the analysis and interpretability of fMRI data. BolT represents a significant advancement in modeling fMRI time series by utilizing a blood-oxygen-level-dependent trans-former architecture. This model incorporates a novel fused window attention mechanism, which enables the extraction of both local and global representations by processing temporally-overlapped windows and employing cross-window regularization. BolT’s approach improves upon existing methods, offering enhanced sensitivity and aligning with key neuroscientific findings through extensive experimentation. GraphCorr addresses limitations in static functional connectivity (FC) features used in classification models by introducing a graph neural network-based plug-in. This method captures dynamic latent FC features while preserving dimensional efficiency, employing a node embedder and lag filter module to re-fine temporal information. The integration of these features through a message passing algorithm significantly enhances the performance of baseline classification models, as demonstrated through comprehensive testing on public datasets. Finally, DreaMR tackles the interpretability of deep fMRI classifiers through a novel diffusion-driven counterfactual approach. By using fractional multi-phase-distilled diffusion, DreaMR generates high-fidelity counterfactual samples and employs a transformer architecture to account for long-range spatiotemporal contexts. This method surpasses traditional counterfactual techniques in both fidelity and efficiency, offering a more precise and actionable explanation of classifier decisions. Together, these contributions advance the field of fMRI analysis by improving model performance and interpretability, thereby facilitating more effective and insightful neuroimaging research.
Open Access
Unsupervised medical image translation with adversarial diffusion models
(Institute of Electrical and Electronics Engineers , 2023-11-30) Özbey, Muzaffer; Dalmaz, Onat; Dar, Salman Ul Hassan; Bedel, Hasan Atakan; Özturk, Şaban; Güngör, Alper; Çukur, Tolga
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 fidelity. Here, we propose a novel method based on adversarial diffusion modeling, SynDiff, for improved performance in medical image translation. To capture a direct correlate of the image distribution, SynDiff leverages a conditional diffusion process that progressively maps noise and source images onto the target image. For fast and accurate image sampling during inference, large diffusion steps are taken with adversarial projections in the reverse diffusion direction. To enable training on unpaired datasets, a cycle-consistent architecture is devised with coupled diffusive and non-diffusive modules that bilaterally translate between two modalities. Extensive assessments are reported on the utility of SynDiff against competing GAN and diffusion models in multi-contrast MRI and MRI-CT translation. Our demonstrations indicate that SynDiff offers quantitatively and qualitatively superior performance against competing baselines.