Curated by THEOUTPOST
On Tue, 1 Oct, 12:03 AM UTC
3 Sources
[1]
Better MRI videos thanks to new machine learning method
Using smartly trained neural networks, researchers at TU Graz have succeeded in generating precise real-time images of the beating heart from just a few MRI measurement data. Other MRI applications can also be accelerated using this procedure. Medical imaging using magnetic resonance imaging (MRI) is very time-consuming since an image has to be compiled from data from many individual measurements. Thanks to the use of machine learning, imaging is also possible with less MRI measurement data, which saves time and costs. However, the prerequisite for this is perfect images that can be used to train the AI models. Such perfect training images do not exist for certain applications, such as real-time (moving image) MRI, as such images are always somewhat blurred. An international research team led by Martin Uecker and Moritz Blumenthal from the Institute of Biomedical Imaging at Graz University of Technology (TU Graz) has now succeeded in generating precise live MRI images of the beating heart even without such training images and with very little MRI data with the help of smartly trained neural networks. Thanks to these improvements, real-time MRI could be used more frequently in practice in the future. Calibration of imaging through withheld data Martin Uecker and Moritz Blumenthal used self-supervised learning methods to train their machine learning model for MRI imaging. The basis for training the model is not pre-curated perfect images, but a subset of the initial data from which the model is to reconstruct the images. Moritz Blumenthal explains it like this: "We divided the measurement data provided by the MRI device into two portions. From the first, larger data portion, our machine learning model reconstructs the image. It then attempts to calculate the second portion of the measurement data withheld from it on the basis of the image." If the system fails to do this or does so poorly -- according to the underlying logic -- the previously reconstructed image must have been incorrect. The model is updated, it creates a new improved image variant and attempts to calculate the second data portion again. This process runs for a number of rounds until the result is consistent. In this training process, the system learns from a large number of such reconstructions what good MRI images should look like. Later, during the application, the model can then directly calculate a good image. This procedure can make many MRI applications faster and cheaper "Our process is ready for application," says Martin Uecker, "even if it will probably be a while before it is actually used in practice." The method can be used for many other MRI applications to make them faster and therefore cheaper. This includes quantitative MRI, for example, in which physical tissue parameters are precisely measured and quantified. "This allows radiologists to access precise data for diagnoses instead of having to interpret images based on differences in brightness using their professional experience," explains Martin Uecker. "Up to now, however, quantitative MRI measurements have often taken a very long time. With our machine learning model, we were able to speed up these measurements considerably without any loss of quality." The research results, which were recently published in the journal Magnetic Resonance in Medicine are the result of an international and interdisciplinary collaboration of the Institute of Biomedical Imaging. Participants included Christina Unterberg (cardiologist at the University Medical Centre Göttingen), Markus Haltmeier (mathematician at the University of Innsbruck), Xiaoqing Wang (MRI researcher at Harvard Medical School) and Chiara Fantinato (Erasmus student from Italy). The algorithms and MRI data are freely available so that other researchers can reproduce the results directly and build on the new method.
[2]
Better MRI videos thanks to new machine learning method
Using smartly trained neural networks, researchers at TU Graz have succeeded in generating precise real-time images of the beating heart from just a few MRI measurement data. Other MRI applications can also be accelerated using this procedure. The study is published in Magnetic Resonance in Medicine. Medical imaging using magnetic resonance imaging (MRI) is very time-consuming since an image has to be compiled from data from many individual measurements. Thanks to the use of machine learning, imaging is also possible with less MRI measurement data, which saves time and costs. However, the prerequisite for this is perfect images that can be used to train the AI models. Such perfect training images do not exist for certain applications, such as real-time (moving image) MRI, as such images are always somewhat blurred. An international research team led by Martin Uecker and Moritz Blumenthal from the Institute of Biomedical Imaging at Graz University of Technology (TU Graz) has now succeeded in generating precise live MRI images of the beating heart even without such training images and with very little MRI data with the help of smartly trained neural networks. Thanks to these improvements, real-time MRI could be used more frequently in practice in the future. Uecker and Blumenthal used self-supervised learning methods to train their machine learning model for MRI imaging. The basis for training the model is not pre-curated perfect images, but a subset of the initial data from which the model is to reconstruct the images. Blumenthal explains, "We divided the measurement data provided by the MRI device into two portions. From the first, larger data portion, our machine learning model reconstructs the image. It then attempts to calculate the second portion of the measurement data withheld from it on the basis of the image." If the system fails to do this or does so poorly -- according to the underlying logic -- the previously reconstructed image must have been incorrect. The model is updated, it creates a new improved image variant and attempts to calculate the second data portion again. This process runs for a number of rounds until the result is consistent. In this training process, the system learns from a large number of such reconstructions what good MRI images should look like. Later, during the application, the model can then directly calculate a good image. "Our process is ready for application," says Uecker, "even if it will probably be a while before it is actually used in practice." The method can be used for many other MRI applications to make them faster and therefore cheaper. This includes quantitative MRI, for example, in which physical tissue parameters are precisely measured and quantified. "This allows radiologists to access precise data for diagnoses instead of having to interpret images based on differences in brightness using their professional experience," explains Uecker. "Up to now, however, quantitative MRI measurements have often taken a very long time. With our machine learning model, we were able to speed up these measurements considerably without any loss of quality." The research results are the result of an international and interdisciplinary collaboration of the Institute of Biomedical Imaging. Participants included Christina Unterberg (cardiologist at the University Medical Center Göttingen), Markus Haltmeier (mathematician at the University of Innsbruck), Xiaoqing Wang (MRI researcher at Harvard Medical School) and Chiara Fantinato (Erasmus student from Italy). The algorithms and MRI data are freely available so that other researchers can reproduce the results directly and build on the new method.
[3]
Innovative machine learning technique transforms MRI imaging efficiency
TU GrazSep 30 2024 Using smartly trained neural networks, researchers at TU Graz have succeeded in generating precise real-time images of the beating heart from just a few MRI measurement data. Other MRI applications can also be accelerated using this procedure. Medical imaging using magnetic resonance imaging (MRI) is very time-consuming since an image has to be compiled from data from many individual measurements. Thanks to the use of machine learning, imaging is also possible with less MRI measurement data, which saves time and costs. However, the prerequisite for this is perfect images that can be used to train the AI models. Such perfect training images do not exist for certain applications, such as real-time (moving image) MRI, as such images are always somewhat blurred. An international research team led by Martin Uecker and Moritz Blumenthal from the Institute of Biomedical Imaging at Graz University of Technology (TU Graz) has now succeeded in generating precise live MRI images of the beating heart even without such training images and with very little MRI data with the help of smartly trained neural networks. Thanks to these improvements, real-time MRI could be used more frequently in practice in the future. Calibration of imaging through withheld data Martin Uecker and Moritz Blumenthal used self-supervised learning methods to train their machine learning model for MRI imaging. The basis for training the model is not pre-curated perfect images, but a subset of the initial data from which the model is to reconstruct the images. Moritz Blumenthal explains it like this: "We divided the measurement data provided by the MRI device into two portions. From the first, larger data portion, our machine learning model reconstructs the image. It then attempts to calculate the second portion of the measurement data withheld from it on the basis of the image." If the system fails to do this or does so poorly - according to the underlying logic - the previously reconstructed image must have been incorrect. The model is updated, it creates a new improved image variant and attempts to calculate the second data portion again. This process runs for a number of rounds until the result is consistent. In this training process, the system learns from a large number of such reconstructions what good MRI images should look like. Later, during the application, the model can then directly calculate a good image. This procedure can make many MRI applications faster and cheaper "Our process is ready for application," says Martin Uecker, "even if it will probably be a while before it is actually used in practice." The method can be used for many other MRI applications to make them faster and therefore cheaper. This includes quantitative MRI, for example, in which physical tissue parameters are precisely measured and quantified. "This allows radiologists to access precise data for diagnoses instead of having to interpret images based on differences in brightness using their professional experience," explains Martin Uecker. "Up to now, however, quantitative MRI measurements have often taken a very long time. With our machine learning model, we were able to speed up these measurements considerably without any loss of quality." The research results, which were recently published in the journal Magnetic Resonance in Medicine are the result of an international and interdisciplinary collaboration of the Institute of Biomedical Imaging. Participants included Christina Unterberg (cardiologist at the University Medical Centre Göttingen), Markus Haltmeier (mathematician at the University of Innsbruck), Xiaoqing Wang (MRI researcher at Harvard Medical School) and Chiara Fantinato (Erasmus student from Italy). The algorithms and MRI data are freely available so that other researchers can reproduce the results directly and build on the new method. TU Graz Journal reference: Blumenthal, M., et al. (2024). Selfâsupervised learning for improved calibrationless radial MRI with NLINVâNet. Magnetic Resonance in Medicine. doi.org/10.1002/mrm.30234.
Share
Share
Copy Link
Researchers at TU Graz have developed a novel machine learning technique that generates precise real-time MRI images of the beating heart using minimal data, potentially revolutionizing medical imaging practices.
Researchers at Graz University of Technology (TU Graz) have made a significant advancement in magnetic resonance imaging (MRI) technology. Led by Martin Uecker and Moritz Blumenthal from the Institute of Biomedical Imaging, the team has developed a machine learning method that generates precise real-time images of the beating heart using minimal MRI measurement data 1.
The novel technique employs self-supervised learning methods to train neural networks for MRI imaging. Unlike traditional approaches that require perfect training images, this method uses a subset of the initial MRI data to reconstruct images 2.
Moritz Blumenthal explains the process: "We divided the measurement data provided by the MRI device into two portions. From the first, larger data portion, our machine learning model reconstructs the image. It then attempts to calculate the second portion of the measurement data withheld from it on the basis of the image" 3.
The system undergoes multiple rounds of reconstruction and validation. If the model fails to accurately calculate the withheld data, it updates itself and creates an improved image variant. This iterative process continues until a consistent result is achieved, allowing the system to learn what constitutes a good MRI image 1.
While the process is ready for application, practical implementation may take some time. The method has potential applications beyond cardiac imaging, including:
The research, published in the journal Magnetic Resonance in Medicine, is the result of an international and interdisciplinary collaboration. Contributors include Christina Unterberg (University Medical Centre Göttingen), Markus Haltmeier (University of Innsbruck), Xiaoqing Wang (Harvard Medical School), and Chiara Fantinato (Erasmus student from Italy) 3.
To promote further advancements in the field, the researchers have made their algorithms and MRI data freely available, allowing other scientists to reproduce the results and build upon this innovative method 1.
Reference
[1]
[2]
[3]
Researchers at UCSF have developed an AI model that enhances 3T MRI images to mimic 7T MRI quality, potentially improving the diagnosis of brain disorders like traumatic brain injury and multiple sclerosis.
3 Sources
3 Sources
A new AI model called TotalSegmentator MRI, developed by Swiss researchers, can automatically segment major anatomic structures in MRI images across different sequences, potentially reducing radiologists' workload and improving diagnostic accuracy.
3 Sources
3 Sources
Researchers from the University of Bonn and the Lamarr Institute have developed a hybrid AI method that improves tractography, a crucial brain imaging technique for neurosurgery planning. This approach combines AI with traditional methods to provide more accurate reconstructions of nerve pathways in the brain.
2 Sources
2 Sources
A groundbreaking MRI technique developed by researchers at University College London (UCL) and Royal Free Hospital could revolutionize heart failure diagnosis and risk assessment, potentially replacing invasive procedures.
2 Sources
2 Sources
Researchers from MIT and Harvard Medical School have developed CHAIS, an AI model that analyzes ECG data to predict heart failure risk, potentially replacing invasive procedures with comparable accuracy.
2 Sources
2 Sources
The Outpost is a comprehensive collection of curated artificial intelligence software tools that cater to the needs of small business owners, bloggers, artists, musicians, entrepreneurs, marketers, writers, and researchers.
© 2025 TheOutpost.AI All rights reserved