KAIST researchers proposed new technology that reduces MRI (magnetic resonance imaging) acquisition time to less than a sixth of the conventional method. They made a reconstruction method using machine learning of multilayer perception (MLP) algorithm to accelerate imaging time.
High-quality image can be reconstructed from subsampled data using the proposed method. This method can be further applied to various k-space subsampling patterns in a phase encoding direction, and its processing can be performed in real time.
The research, led by Professor Hyun Wook Park from the Department of Electrical Engineering, was described in Medical Physics as the cover paper last December. Ph.D. candidate Kinam Kwon is the first author.
MRI is an imaging technique that allows various contrasts of soft tissues without using radioactivity. Since MRI could image not only anatomical structures, but also functional and physiological features, it is widely used in medical diagnoses. However, one of the major shortcomings of MRI is its long imaging time. It induces patients’ discomfort, which is closely related to voluntary and involuntary motions, thereby deteriorating the quality of the MR images. In addition, lengthy imaging times limit the system’s throughput, which results in the long waiting times of patients as well as the increased medical expenses.
To reconstruct MR images from subsampled data, the team applied the MLP to reduce aliasing artifacts generated by subsampling in k-space. The MLP is learned from training data to map aliased input images into desired alias-free images. The input of the MLP is all voxels in the aliased lines of multichannel real and imaginary images from the subsampled k-space data, and the desired output is all voxels in the corresponding alias-free line of the root-sum-of-squares of multichannel images from fully sampled k-space data. Aliasing artifacts in an image reconstructed from subsampled data were reduced by line-by-line processing of the learned MLP architecture.
Reconstructed images from the proposed method are better than those from compared methods in terms of normalized root-mean-square error. The proposed method can be applied to image reconstruction for any k-space subsampling patterns in a phase encoding direction. Moreover, to further reduce the reconstruction time, it is easily implemented by parallel processing.
To address the aliasing artifact phenomenon, the team employed a parallel imaging technique using several receiver coils of various sensitivities and a compressed sensing technique using sparsity of signals.
Existing methods are heavily affected by sub-sampling patterns, but the team’s technique is applicable for various sub-sampling patterns, resulting in superior reconstructed images compared to existing methods, as well as allowing real-time reconstruction.
Professor Park said, "MRIs have become essential equipment in clinical diagnosis. However, the time consumption and the cost led to many inconveniences." He continued, "This method using machine learning could greatly improve the patients’ satisfaction with medical service." This research was funded by the Ministry of Science and ICT.
(Firgure 1. Cover of Medical Physics for December 2017)
(Figure 2. Concept map for the suggested network)
(Figure 3. Concept map for conventional MRI image acquisition and accelerated image acquisiton)
KAIST Future Mobility of the Year Awards recognize the most innovative concept cars of the year The Renault 5 EV from France and a pickup truck from the US startup Canoo won the 2021 Future Mobility of the Year Awards (FMOTY) hosted by the Cho Chun Shik Graduate School of Green Transportation at KAIST. The awards ceremony was held at Renault Samsung Motors in Seoul on November 25. KAIST began the FMOTY in 2019 to advance future car technology and stimulate growth in the industry. The award r2021-11-26
A research team led by Professor Sung-Ju Lee at the School of Electrical Engineering won the Best Paper Award and the Methods Recognition Award from ACM CSCW (International Conference on Computer-Supported Cooperative Work and Social Computing) 2021 for their paper “Reflect, not Regret: Understanding Regretful Smartphone Use with App Feature-Level Analysis”. Founded in 1986, CSCW has been a premier conference on HCI (Human Computer Interaction) and Social Computing. This year, 3402021-11-22
Researchers identified a single amino acid change in the tumor suppressor protein in PTEN that extends healthy periods while maintaining longevity Living a long, healthy life is everyone’s wish, but it is not an easy one to achieve. Many aging studies are developing strategies to increase health spans, the period of life spent with good health, without chronic diseases and disabilities. Researchers at KAIST presented new insights for improving the health span by just regulating the acti2021-11-19
Research analyzed player experiences with a polarizing game and found differences in how the players related to their characters The action adventure game ‘The Last of Us’ was a big hit worldwide in 2014. However, its sequel, the Last of Us Part II divided opinions in the game community when it was released in 2020. A research team from the Games and Life Lab in the Graduate School of Culture Technology at KAIST analyzed why the game players’ reviews were so polarized and fo2021-11-15
Global healthcare and humanitarian activist honored by the Grand Award for Future Strategy The Moon Soul Graduate School of Future Strategy awarded the 9th Grand Award for Future Strategy to Marine Buissonniere, an independent advisor and practitioner in the fields of global health and humanitarian action. She currently works as a senior advisor to the Prevent Epidemics team at Resolve to Save Lives. She also co-chairs Doctors Without Borders’ Transformational Investment Capacity. Bu2021-11-11