Browse AI research papers authored by Onur Afacan. Found 4 papers.

arXiv:2511.16854v1 Announce Type: new Abstract: High-resolution (HR) magnetic resonance imaging (MRI) is crucial for many clinical and research applications. However, achieving it remains costly and constrained by technical trade-offs and experimental limitations. Super-resolution (SR) presents a promising computational approach to overcome these challenges by generating HR images from more affordable low-resolution (LR) scans, potentially improving diagnostic accuracy and efficiency without requiring additional hardware. This survey reviews recent advances in MRI SR techniques, with a focus on deep learning (DL) approaches. It examines DL-based MRI SR methods from the perspectives of computer vision, computational imaging, inverse problems, and MR physics, covering theoretical foundations, architectural designs, learning strategies, benchmark datasets, and performance metrics. We propose a systematic taxonomy to categorize these methods and present an in-depth study of both established and emerging SR techniques applicable to MRI, considering unique challenges in clinical and research contexts. We also highlight open challenges and directions that the community needs to address. Additionally, we provide a collection of essential open-access resources, tools, and tutorials, available on our GitHub: https://github.com/mkhateri/Awesome-MRI-Super-Resolution.  IEEE keywords: MRI, Super-Resolution, Deep Learning, Computational Imaging, Inverse Problem, Survey.

MRI Super-Resolution with Deep Learning: A Comprehensive Survey

Quantitative analysis of pseudo-diffusion in diffusion-weighted magnetic resonance imaging (DWI) data shows potential for assessing fetal lung maturation and generating valuable imaging biomarkers. Yet, the clinical utility of DWI data is hindered by unavoidable fetal motion during acquisition. We present IVIM-morph, a self-supervised deep neural network model for motion-corrected quantitative analysis of DWI data using the Intra-voxel Incoherent Motion (IVIM) model. IVIM-morph combines two sub-networks, a registration sub-network, and an IVIM model fitting sub-network, enabling simultaneous estimation of IVIM model parameters and motion. To promote physically plausible image registration, we introduce a biophysically informed loss function that effectively balances registration and model-fitting quality. We validated the efficacy of IVIM-morph by establishing a correlation between the predicted IVIM model parameters of the lung and gestational age (GA) using fetal DWI data of 39 subjects. IVIM-morph exhibited a notably improved correlation with gestational age (GA) when performing in-vivo quantitative analysis of fetal lung DWI data during the canalicular phase. IVIM-morph shows potential in developing valuable biomarkers for non-invasive assessment of fetal lung maturity with DWI data. Moreover, its adaptability opens the door to potential applications in other clinical contexts where motion compensation is essential for quantitative DWI analysis. The IVIM-morph code is readily available at: https://github.com/TechnionComputationalMRILab/qDWI-Morph.

## Overview

- New method called **IVIM-Morph** for analyzing fetal lung development using MRI
- Compensates for fetal motion during scanning to improve image quality
- Aims to assess lung maturity non-invasively using diffusion-weighted MRI
- Combines motion correction with quantitative analysis of lung tissue properties
- Designed for clinical use in evaluating fetal development

## Plain English Explanation 

During pregnancy, doctors need to check if a baby's lungs are developing properly. Currently, this often requires invasive tests. IVIM-Morph offers a safer way using MRI scans. 

The challenge is that babies move in the womb, which blurs the images. Think of trying to photograph a moving object - you get a blurry picture. [IVIM-Morph](https://aimodels.fyi/papers/arxiv/ivim-morph-motion-compensated-quantitative-intra-voxel) fixes this by tracking and correcting for movement, similar to how modern cameras have image stabilization.

The system analyzes how water molecules move in lung tissue. Mature lungs have a different pattern of water movement compared to immature lungs. By measuring these patterns, doctors can assess lung development without any risk to mother or baby.

## Key Findings

The research demonstrates that:

- Motion correction significantly improves image quality and analysis accuracy
- The system can distinguish between different stages of lung development
- [Motion compensation techniques](https://aimodels.fyi/papers/arxiv/physics-informed-deep-learning-motion-corrected-reconstruction) make previously unusable scans viable for analysis
- Results are consistent with existing clinical knowledge about fetal lung development

## Technical Explanation

IVIM-Morph uses a two-step approach. First, it applies advanced image processing to detect and correct motion artifacts. This uses **deformable registration** techniques to align images from different time points.

The second step employs [diffusion MRI analysis](https://aimodels.fyi/papers/arxiv/detailed-delineation-fetal-brain-diffusion-mri-via) to measure microscopic water movement within lung tissue. The system calculates specific parameters that indicate lung maturity.

The method builds on existing IVIM (Intravoxel Incoherent Motion) techniques but adds robust motion handling capabilities. This makes it practical for real clinical use where fetal movement is inevitable.

## Critical Analysis

While promising, several limitations exist:

- Requires high-quality MRI equipment and expertise
- Processing time may be longer than conventional methods
- Limited validation against current clinical gold standards
- Need for larger scale clinical trials to confirm reliability

Future work should focus on:
- Reducing computation time for real-time analysis
- Expanding validation across different patient populations
- Integration with existing clinical workflows
- Comparison with other [motion correction approaches](https://aimodels.fyi/papers/arxiv/sismik-brain-mri-deep-learning-based-motion)

## Conclusion

IVIM-Morph represents a significant advance in fetal monitoring technology. It addresses the crucial need for non-invasive lung maturity assessment while solving the persistent challenge of fetal motion during imaging.

The potential impact extends beyond lung assessment to other aspects of fetal development monitoring. Success in clinical implementation could reduce reliance on invasive testing procedures and improve prenatal care quality.

IVIM-Morph: Motion-compensated quantitative Intra-voxel Incoherent Motion (IVIM) analysis for functional fetal lung maturity assessment from diffusion-weighted MRI data

Diffusion-weighted magnetic resonance imaging (DW-MRI) is a powerful, non-invasive tool for detecting and characterizing abdominal lesions to facilitate early diagnosis, but respiratory motion during a scan reduces image quality and accuracy of quantitative biomarkers. Respiratory binning, which groups image slices into motion phase bins based on a navigator signal, can help mitigate motion artifacts. However, in DW-MRI, the standard binning technique often generates volumes with missing slices along the superior-inferior axis. Thus, longer scans are required to obtain volumes without gaps. In this study, we proposed a new binning technique to minimize missing slices without increasing scan time. We first designed an algorithm using dynamic programming and prefix sum approaches to optimize the initial binning of MR images. Then, we developed a probabilistic refinement phase, selecting some slices to belong in two neighboring bins to further reduce missing slices. We tested our two-phase technique on free-breathing abdominal DW-MRI scans from eight subjects, including one with tumors. The proposed technique significantly reduced missing slices compared to standard binning (p<1.0*10-15), yielding an average reduction of 81.74+/-7.58%. Our technique also reduced motion artifacts, improving the conspicuity of malignant lesions. Apparent Diffusion Coefficient (ADC) maps generated from free-breathing scans corrected using the proposed technique had lower intra-subject variability compared to ADC maps from uncorrected free-breathing and shallow-breathing scans (p<0.001). Additionally, ADC maps from shallow-breathing scans were more consistent with corrected free-breathing maps rather than uncorrected free-breathing maps (p<0.01). The proposed technique corrects for motion while simultaneously reducing missing slices, allowing for shorter acquisition times compared to standard binning.

## Overview

- Abdominal diffusion-weighted magnetic resonance imaging (DW-MRI) is a valuable non-invasive technique for identifying and characterizing lesions, enabling early diagnosis.
- Respiratory motion during scans can degrade image quality.
- Dividing images into "respiratory phases" can reduce motion artifacts, but standard binning algorithms often result in incomplete volumes with missing slices.
- This study proposes a new binning algorithm to minimize missing slices and improve image quality.

## Plain English Explanation

Abdominal [DW-MRI](https://aimodels.fyi/papers/arxiv/simultaneous-multi-slice-diffusion-imaging-using-navigator) is a powerful imaging technique that helps doctors spot and understand abnormal growths, called lesions, without needing to perform surgery. However, when people breathe during the scan, it can cause the images to become blurry and distorted.

One way to reduce these breathing artifacts is to separate the images into "bins" based on the stage of the breathing cycle. But the standard binning method often results in missing slices of the body, leaving gaps in the final 3D image. This can make it harder for doctors to get a complete picture of what's going on.

In this study, the researchers developed a new binning algorithm to address this issue. They tested it on scans of volunteers, and found that it was able to significantly reduce the number of missing slices compared to the standard approach. This improved the quality of the images and the [Apparent Diffusion Coefficient (ADC) maps](https://aimodels.fyi/papers/arxiv/resolving-variable-respiratory-motion-from-unsorted-4d) derived from them. The ADC maps also showed more consistency between different breathing conditions, which could make it easier for doctors to interpret the results.

Overall, this new binning algorithm has the potential to enhance the usefulness of abdominal DW-MRI scans, leading to more accurate diagnoses and better patient care.

## Technical Explanation

The researchers acquired free-breathing and shallow-breathing abdominal DW-MRI scans from seven volunteers. They then used a new binning algorithm to correct for motion in the free-breathing scans.

First, they employed a dynamic programming approach to determine the optimal rigid bin partitions in the respiratory signal, assigning each slice to one bin. They then developed a probabilistic method to select some slices to belong to two bins, in order to minimize missing slices.

Compared to the standard binning algorithm, the researchers' proposed method resulted in significantly fewer missing slices (p<1.0e-16), with an average reduction of 82.98±6.07%. This improved lesion conspicuity and reduced motion artifacts in the DW-MR images and [ADC maps](https://aimodels.fyi/papers/arxiv/improved-3d-whole-heart-geometry-from-sparse).

The ADC maps created from the motion-corrected free-breathing images showed lower intra-subject variability compared to the uncorrected free-breathing and shallow-breathing maps (p<0.001). Additionally, the shallow-breathing ADC maps were more consistent with the corrected free-breathing maps than the uncorrected free-breathing maps (p<0.01).

The researchers' proposed binning algorithm's effectiveness in reducing missing slices increases anatomical accuracy and allows for shorter scan times compared to the standard binning approach.

## Critical Analysis

The researchers acknowledge several limitations of their study. First, they only tested the algorithm on a small sample size of seven volunteers. Larger studies will be needed to further validate the algorithm's performance.

Additionally, the study did not directly compare the diagnostic accuracy or clinical utility of the motion-corrected DW-MRI images to standard approaches. Future research should investigate how the improved image quality translates to improved clinical outcomes, such as more reliable lesion detection and characterization.

It would also be valuable to explore the algorithm's robustness to different respiratory patterns and pathologies. The researchers noted that their method may be less effective for patients with irregular or erratic breathing patterns, which could limit its real-world applicability.

Overall, this study presents a promising new binning algorithm that appears to significantly enhance the quality of abdominal DW-MRI scans by reducing motion-related artifacts. However, more extensive validation and clinical testing will be necessary to fully assess its potential impact on [disease diagnosis and management](https://aimodels.fyi/papers/arxiv/evaluating-impact-sequence-combinations-breast-tumor-segmentation).

## Conclusion

This study introduces a new binning algorithm for abdominal DW-MRI that can dramatically reduce the number of missing slices in the reconstructed volumes, leading to higher-quality images and more consistent quantitative measurements. By improving the accuracy and reliability of this valuable diagnostic tool, the proposed algorithm has the potential to facilitate earlier disease detection and more informed clinical decision-making. Further research is needed to fully evaluate the algorithm's real-world performance and clinical utility, but these initial results are highly promising.

An Optimized Binning and Probabilistic Slice Sharing Algorithm for Motion Correction in Abdominal DW-MRI

Diffusion magnetic resonance imaging (dMRI) is pivotal for probing the microstructure of the rapidly-developing fetal brain. However, fetal motion during scans and its interaction with magnetic field inhomogeneities result in artifacts and data scattering across spatial and angular domains. The effects of those artifacts are more pronounced in high-angular resolution fetal dMRI, where signal-to-noise ratio is very low. Those effects lead to biased estimates and compromise the consistency and reliability of dMRI analysis. This work presents HAITCH, the first and the only publicly available tool to correct and reconstruct multi-shell high-angular resolution fetal dMRI data. HAITCH offers several technical advances that include a blip-reversed dual-echo acquisition for dynamic distortion correction, advanced motion correction for model-free and robust reconstruction, optimized multi-shell design for enhanced information capture and increased tolerance to motion, and outlier detection for improved reconstruction fidelity. The framework is open-source, flexible, and can be used to process any type of fetal dMRI data including single-echo or single-shell acquisitions, but is most effective when used with multi-shell multi-echo fetal dMRI data that cannot be processed with any of the existing tools. Validation experiments on real fetal dMRI scans demonstrate significant improvements and accurate correction across diverse fetal ages and motion levels. HAITCH successfully removes artifacts and reconstructs high-fidelity fetal dMRI data suitable for advanced diffusion modeling, including fiber orientation distribution function estimation. These advancements pave the way for more reliable analysis of the fetal brain microstructure and tractography under challenging imaging conditions.

## Overview

- This paper presents a new framework called HAITCH for correcting distortions and motion in fetal multi-shell diffusion-weighted MRI data.
- The framework combines several techniques, including bias field correction, eddy current distortion correction, and motion correction, to improve the quality of fetal diffusion MRI data.
- Experiments on both simulated and real fetal diffusion MRI data demonstrate the effectiveness of the HAITCH framework in enhancing image quality and improving downstream analyses.

## Plain English Explanation

Fetal magnetic resonance imaging (MRI) is a powerful tool for studying brain development, but it can be challenging to obtain high-quality images due to the constant motion of the fetus and distortions in the MRI data. The HAITCH framework addresses these issues by combining several techniques to correct for different types of distortions and motion in the data.

First, the framework corrects for bias fields, which are uneven intensity variations across the MRI image. This helps ensure that the intensity values are consistent throughout the image. Next, it corrects for eddy current distortions, which are caused by the rapid switching of the magnetic fields during the MRI scan. These distortions can cause the image to appear warped or stretched.

Finally, the HAITCH framework corrects for motion of the fetus during the scan. Fetal movement can cause the image to appear blurry or misaligned, so the framework aligns the different images taken during the scan to account for this motion.

By combining these various correction techniques, the HAITCH framework is able to significantly improve the quality of fetal diffusion MRI data, making it easier for researchers to analyze and understand brain development in utero. This could lead to important insights into how the brain grows and changes during pregnancy, which could have implications for understanding and treating developmental disorders.

## Technical Explanation

The HAITCH framework combines several techniques to correct for distortions and motion in fetal multi-shell diffusion-weighted MRI data:

1. **Bias Field Correction**: The framework first applies a bias field correction algorithm to remove uneven intensity variations across the MRI image. This helps ensure that the intensity values are consistent throughout the image.

2. **Eddy Current Distortion Correction**: Next, the framework corrects for eddy current distortions, which are caused by the rapid switching of the magnetic fields during the diffusion-weighted MRI scan. These distortions can cause the image to appear warped or stretched. The HAITCH framework uses a technique called [field-view extension](https://aimodels.fyi/papers/arxiv/field-view-extension-diffusion-mri-via-deep) to correct for these distortions.

3. **Motion Correction**: Finally, the framework corrects for motion of the fetus during the scan. Fetal movement can cause the image to appear blurry or misaligned. The HAITCH framework uses a technique called [SISMIK](https://aimodels.fyi/papers/arxiv/sismik-brain-mri-deep-learning-based-motion) to align the different images taken during the scan and account for this motion.

The authors evaluate the HAITCH framework on both simulated and real fetal diffusion MRI data. The results demonstrate that the framework is effective in enhancing image quality and improving downstream analyses, such as diffusion tensor imaging and tractography.

## Critical Analysis

The HAITCH framework represents a promising approach for addressing the significant challenges associated with fetal diffusion MRI. By combining several state-of-the-art techniques, the framework is able to effectively correct for bias fields, eddy current distortions, and fetal motion, leading to substantial improvements in image quality.

One potential limitation of the framework is that it relies on several different algorithms, each of which may have its own set of parameters and hyperparameters that need to be carefully tuned. This could make the framework somewhat complex to implement and optimize in practice. Additionally, the authors do not provide a detailed analysis of the relative contributions of each correction step, which could make it difficult to understand the specific aspects of the framework that are most important for improving image quality.

Another area for further research could be the integration of the HAITCH framework with other advanced techniques for analyzing fetal diffusion MRI data, such as [physics-guided diffusion models](https://aimodels.fyi/papers/arxiv/phy-diff-physics-guided-hourglass-diffusion-model) or [3D MRI synthesis from multi-gradient-echo signals](https://aimodels.fyi/papers/arxiv/diffgepci-3d-mri-synthesis-from-mgre-signals). By combining the HAITCH framework with these types of techniques, it may be possible to further enhance the utility of fetal diffusion MRI for studying brain development and identifying potential abnormalities.

## Conclusion

The HAITCH framework represents a significant advancement in the field of fetal diffusion MRI, providing a comprehensive approach for correcting a range of distortions and motion-related artifacts that can plague these types of scans. By leveraging state-of-the-art techniques for bias field correction, eddy current distortion correction, and motion correction, the framework is able to substantially improve the quality of fetal diffusion MRI data, paving the way for more accurate and reliable analyses of brain development in utero.

While the framework does have some potential limitations, the overall approach represents an important step forward in addressing the unique challenges of fetal imaging. As the field of fetal MRI continues to evolve, the HAITCH framework and other innovative techniques will likely play a crucial role in unlocking the full potential of this powerful imaging modality for understanding early brain development and identifying potential developmental disorders.

Onur Afacan

Authored papers

Could AI-upscaled MRIs replace expensive scanners, and finally make diagnostics cheaper?

Can AI finally make fetal lung scans clear enough to predict a baby's breathing readiness before birth?

Can a smarter way of organizing and sharing MRI slices beat the blur caused by breathing?

Can we unlock sharper insights into a baby's brain development, even when they wiggle during the MRI?

Claim this author profile