Mahmut Yurt
YOU?
Author Swipe
View article: LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving
LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving Open
3D perception plays an essential role for improving the safety and performance of autonomous driving. Yet, existing models trained on real-world datasets, which naturally exhibit long-tail distributions, tend to underperform on rare and sa…
View article: ALN-P3: Unified Language Alignment for Perception, Prediction, and Planning in Autonomous Driving
ALN-P3: Unified Language Alignment for Perception, Prediction, and Planning in Autonomous Driving Open
Recent advances have explored integrating large language models (LLMs) into end-to-end autonomous driving systems to enhance generalization and interpretability. However, most existing approaches are limited to either driving performance o…
View article: Deep learning initialized compressed sensing (Deli-CS) in volumetric spatio-temporal subspace reconstruction
Deep learning initialized compressed sensing (Deli-CS) in volumetric spatio-temporal subspace reconstruction Open
Object Spatio-temporal MRI methods offer rapid whole-brain multi-parametric mapping, yet they are often hindered by prolonged reconstruction times or prohibitively burdensome hardware requirements. The aim of this project is to reduce reco…
View article: On the Foundation Model for Cardiac MRI Reconstruction
On the Foundation Model for Cardiac MRI Reconstruction Open
In recent years, machine learning (ML) based reconstruction has been widely investigated and employed in cardiac magnetic resonance (CMR) imaging. ML-based reconstructions can deliver clinically acceptable image quality under substantially…
View article: Spherical echo‐planar time‐resolved imaging (sEPTI) for rapid 3D quantitative T2* and susceptibility imaging
Spherical echo‐planar time‐resolved imaging (sEPTI) for rapid 3D quantitative T2* and susceptibility imaging Open
Purpose To develop a 3D spherical EPTI (sEPTI) acquisition and a comprehensive reconstruction pipeline for rapid high‐quality whole‐brain submillimeter and QSM quantification. Methods For the sEPTI acquisition, spherical k‐space coverage i…
View article: I2I-Mamba: Multi-modal medical image synthesis via selective state space modeling
I2I-Mamba: Multi-modal medical image synthesis via selective state space modeling Open
Multi-modal medical image synthesis involves nonlinear transformation of tissue signals between source and target modalities, where tissues exhibit contextual interactions across diverse spatial distances. As such, the utility of a network…
View article: Spherical Echo-Planar Time-resolved Imaging (sEPTI) for rapid 3D quantitative T2* and Susceptibility imaging
Spherical Echo-Planar Time-resolved Imaging (sEPTI) for rapid 3D quantitative T2* and Susceptibility imaging Open
Purpose To develop a 3D spherical EPTI (sEPTI) acquisition and a comprehensive reconstruction pipeline for rapid high-quality whole-brain submillimeter T2* and QSM quantification. Methods For the sEPTI acquisition, spherical k-space covera…
View article: Rapid and accurate navigators for motion and <scp>B</scp><sub>0</sub> tracking using QUEEN: Quantitatively enhanced parameter estimation from navigators
Rapid and accurate navigators for motion and <span>B</span><sub>0</sub> tracking using QUEEN: Quantitatively enhanced parameter estimation from navigators Open
Purpose To develop a framework that jointly estimates rigid motion and polarizing magnetic field (B 0 ) perturbations () for brain MRI using a single navigator of a few milliseconds in duration, and to additionally allow for navigator acqu…
View article: Deep Learning Reconstruction for Free-breathing Radial Cine Imaging
Deep Learning Reconstruction for Free-breathing Radial Cine Imaging Open
View article: GRJointNET: Synergistic Completion and Part Segmentation on 3D Incomplete Point Clouds
GRJointNET: Synergistic Completion and Part Segmentation on 3D Incomplete Point Clouds Open
Segmentation of three-dimensional (3D) point clouds is an important task for autonomous systems. However, success of segmentation algorithms depends greatly on the quality of the underlying point clouds (resolution, completeness etc.). In …
View article: <scp>DTI‐MR</scp> fingerprinting for rapid high‐resolution whole‐brain <scp>T<sub>1</sub></scp>, <scp>T<sub>2</sub></scp>, proton density, <scp>ADC,</scp> and fractional anisotropy mapping
<span>DTI‐MR</span> fingerprinting for rapid high‐resolution whole‐brain <span>T<sub>1</sub></span>, <span>T<sub>2</sub></span>, proton density, <span>ADC,</span> and fractional anisotropy mapping Open
Purpose This study aims to develop a high‐efficiency and high‐resolution 3D imaging approach for simultaneous mapping of multiple key tissue parameters for routine brain imaging, including T 1 , T 2 , proton density (PD), ADC, and fraction…
View article: Deep Learning Initialized Compressed Sensing (Deli-CS) in Volumetric Spatio-Temporal Subspace Reconstruction
Deep Learning Initialized Compressed Sensing (Deli-CS) in Volumetric Spatio-Temporal Subspace Reconstruction Open
Introduction Spatio-temporal MRI methods enable whole-brain multi-parametric mapping at ultra-fast acquisition times through efficient k-space encoding, but can have very long reconstruction times, which limit their integration into clinic…
View article: Deep Learning-Based Reconstruction for Cardiac MRI: A Review
Deep Learning-Based Reconstruction for Cardiac MRI: A Review Open
Cardiac magnetic resonance (CMR) is an essential clinical tool for the assessment of cardiovascular disease. Deep learning (DL) has recently revolutionized the field through image reconstruction techniques that allow unprecedented data und…
View article: DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models
DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models Open
Magnetic resonance imaging (MRI) is a common and life-saving medical imaging technique. However, acquiring high signal-to-noise ratio MRI scans requires long scan times, resulting in increased costs and patient discomfort, and decreased th…
View article: ResViT: Residual Vision Transformers for Multimodal Medical Image Synthesis
ResViT: Residual Vision Transformers for Multimodal Medical Image Synthesis Open
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 compa…
View article: Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers
Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers Open
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 s…
View article: Deep learning for multi-contrast MRI synthesis
Deep learning for multi-contrast MRI synthesis Open
View article: Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial\n Transformers
Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial\n Transformers Open
Supervised reconstruction models are characteristically trained on matched\npairs of undersampled and fully-sampled data to capture an MRI prior, along\nwith supervision regarding the imaging operator to enforce data consistency. To\nreduc…
View article: A Few-Shot Learning Approach for Accelerated MRI via Fusion of\n Data-Driven and Subject-Driven Priors
A Few-Shot Learning Approach for Accelerated MRI via Fusion of\n Data-Driven and Subject-Driven Priors Open
Deep neural networks (DNNs) have recently found emerging use in accelerated\nMRI reconstruction. DNNs typically learn data-driven priors from large datasets\nconstituting pairs of undersampled and fully-sampled acquisitions. Acquiring\nsuc…
View article: A Few-Shot Learning Approach for Accelerated MRI via Fusion of Data-Driven and Subject-Driven Priors
A Few-Shot Learning Approach for Accelerated MRI via Fusion of Data-Driven and Subject-Driven Priors Open
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 l…
View article: mustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis
mustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis Open
View article: Three Dimensional MR Image Synthesis with Progressive Generative Adversarial Networks
Three Dimensional MR Image Synthesis with Progressive Generative Adversarial Networks Open
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 othe…
View article: Semi-Supervised Learning of Mutually Accelerated MRI Synthesis without Fully-Sampled Ground Truths
Semi-Supervised Learning of Mutually Accelerated MRI Synthesis without Fully-Sampled Ground Truths Open
Learning-based synthetic multi-contrast MRI commonly involves deep models trained using high-quality images of source and target contrasts, regardless of whether source and target domain samples are paired or unpaired. This results in unde…
View article: Progressively Volumetrized Deep Generative Models for Data-Efficient Contextual Learning of MR Image Recovery
Progressively Volumetrized Deep Generative Models for Data-Efficient Contextual Learning of MR Image Recovery Open
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 …
View article: Prior-Guided Image Reconstruction for Accelerated Multi-Contrast MRI via Generative Adversarial Networks
Prior-Guided Image Reconstruction for Accelerated Multi-Contrast MRI via Generative Adversarial Networks Open
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…
View article: mustGAN: Multi-Stream Generative Adversarial Networks for MR Image\n Synthesis
mustGAN: Multi-Stream Generative Adversarial Networks for MR Image\n Synthesis Open
Multi-contrast MRI protocols increase the level of morphological information\navailable for diagnosis. Yet, the number and quality of contrasts is limited in\npractice by various factors including scan time and patient motion. Synthesis\no…
View article: Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks
Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks Open
Acquiring images of the same anatomy with multiple different contrasts increases the diversity of diagnostic information available in an MR exam. Yet, scan time limitations may prohibit acquisition of certain contrasts, and images for some…
View article: Synergistic Reconstruction and Synthesis via Generative Adversarial Networks for Accelerated Multi-Contrast MRI
Synergistic Reconstruction and Synthesis via Generative Adversarial Networks for Accelerated Multi-Contrast MRI Open
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 approaches for enhanced scan…
View article: Synergistic Reconstruction and Synthesis via Generative Adversarial\n Networks for Accelerated Multi-Contrast MRI
Synergistic Reconstruction and Synthesis via Generative Adversarial\n Networks for Accelerated Multi-Contrast MRI Open
Multi-contrast MRI acquisitions of an anatomy enrich the magnitude of\ninformation available for diagnosis. Yet, excessive scan times associated with\nadditional contrasts may be a limiting factor. Two mainstream approaches for\nenhanced s…
View article: Hamit Fendoğlu'nun hayatı ve 1970-1980 yılları arasında Türk siyasetine etkisi
Hamit Fendoğlu'nun hayatı ve 1970-1980 yılları arasında Türk siyasetine etkisi Open
Ankara : İhsan Doğramacı Bilkent Üniversitesi İktisadi, İdari ve Sosyal Bilimler Fakültesi, Tarih Bölümü, 2016.