Receive KAIST news by email!
Type your e-mail address here.
by recently order
by view order
Deep-Learning and 3D Holographic Microscopy Beats Scientists at Analyzing Cancer Immunotherapy
Live tracking and analyzing of the dynamics of chimeric antigen receptor (CAR) T-cells targeting cancer cells can open new avenues for the development of cancer immunotherapy. However, imaging via conventional microscopy approaches can result in cellular damage, and assessments of cell-to-cell interactions are extremely difficult and labor-intensive. When researchers applied deep learning and 3D holographic microscopy to the task, however, they not only avoided these difficultues but found that AI was better at it than humans were. Artificial intelligence (AI) is helping researchers decipher images from a new holographic microscopy technique needed to investigate a key process in cancer immunotherapy “live” as it takes place. The AI transformed work that, if performed manually by scientists, would otherwise be incredibly labor-intensive and time-consuming into one that is not only effortless but done better than they could have done it themselves. The research, conducted by the team of Professor YongKeun Park from the Department of Physics, appeared in the journal eLife last December. A critical stage in the development of the human immune system’s ability to respond not just generally to any invader (such as pathogens or cancer cells) but specifically to that particular type of invader and remember it should it attempt to invade again is the formation of a junction between an immune cell called a T-cell and a cell that presents the antigen, or part of the invader that is causing the problem, to it. This process is like when a picture of a suspect is sent to a police car so that the officers can recognize the criminal they are trying to track down. The junction between the two cells, called the immunological synapse, or IS, is the key process in teaching the immune system how to recognize a specific type of invader. Since the formation of the IS junction is such a critical step for the initiation of an antigen-specific immune response, various techniques allowing researchers to observe the process as it happens have been used to study its dynamics. Most of these live imaging techniques rely on fluorescence microscopy, where genetic tweaking causes part of a protein from a cell to fluoresce, in turn allowing the subject to be tracked via fluorescence rather than via the reflected light used in many conventional microscopy techniques. However, fluorescence-based imaging can suffer from effects such as photo-bleaching and photo-toxicity, preventing the assessment of dynamic changes in the IS junction process over the long term. Fluorescence-based imaging still involves illumination, whereupon the fluorophores (chemical compounds that cause the fluorescence) emit light of a different color. Photo-bleaching or photo-toxicity occur when the subject is exposed to too much illumination, resulting in chemical alteration or cellular damage. One recent option that does away with fluorescent labelling and thereby avoids such problems is 3D holographic microscopy or holotomography (HT). In this technique, the refractive index (the way that light changes direction when encountering a substance with a different density—why a straw looks like it bends in a glass of water) is recorded in 3D as a hologram. Until now, HT has been used to study single cells, but never cell-cell interactions involved in immune responses. One of the main reasons is the difficulty of “segmentation,” or distinguishing the different parts of a cell and thus distinguishing between the interacting cells; in other words, deciphering which part belongs to which cell. Manual segmentation, or marking out the different parts manually, is one option, but it is difficult and time-consuming, especially in three dimensions. To overcome this problem, automatic segmentation has been developed in which simple computer algorithms perform the identification. “But these basic algorithms often make mistakes,” explained Professor YongKeun Park, “particularly with respect to adjoining segmentation, which of course is exactly what is occurring here in the immune response we’re most interested in.” So, the researchers applied a deep learning framework to the HT segmentation problem. Deep learning is a type of machine learning in which artificial neural networks based on the human brain recognize patterns in a way that is similar to how humans do this. Regular machine learning requires data as an input that has already been labelled. The AI “learns” by understanding the labeled data and then recognizes the concept that has been labelled when it is fed novel data. For example, AI trained on a thousand images of cats labelled “cat” should be able to recognize a cat the next time it encounters an image with a cat in it. Deep learning involves multiple layers of artificial neural networks attacking much larger, but unlabeled datasets, in which the AI develops its own ‘labels’ for concepts it encounters. In essence, the deep learning framework that KAIST researchers developed, called DeepIS, came up with its own concepts by which it distinguishes the different parts of the IS junction process. To validate this method, the research team applied it to the dynamics of a particular IS junction formed between chimeric antigen receptor (CAR) T-cells and target cancer cells. They then compared the results to what they would normally have done: the laborious process of performing the segmentation manually. They found not only that DeepIS was able to define areas within the IS with high accuracy, but that the technique was even able to capture information about the total distribution of proteins within the IS that may not have been easily measured using conventional techniques. “In addition to allowing us to avoid the drudgery of manual segmentation and the problems of photo-bleaching and photo-toxicity, we found that the AI actually did a better job,” Professor Park added. The next step will be to combine the technique with methods of measuring how much physical force is applied by different parts of the IS junction, such as holographic optical tweezers or traction force microscopy. -Profile Professor YongKeun Park Department of Physics Biomedical Optics Laboratory http://bmol.kaist.ac.kr KAIST
‘OSK Rising Stars 30’ Recognizes Four KAISTians
Four KAISTians were selected as star researchers to brighten the future of optics in commemoration of the 30th anniversary of the Optical Society of Korea (OSK). As ‘OSK Rising Stars 30’, the OSK named 27 domestic researchers under the age of 40 who have made significant contributions and will continue contributing to the development of Korea’s optics academia and industry. Professor YongKeun Park from the Department of Physics was selected in recognition of his contributions to the field of biomedical optics. Professor Park focuses on developing novel optical methods for understanding, diagnosing, and treating human diseases, based on light scattering, light manipulation, and interferometry. As a member of numerous international optics societies including the OSA and the SPIE and a co-founder of two start-up companies, Professor Park continues to broaden his boundaries as a leading opticist and entrepreneur. Professor Jonghwa Shin from the Department of Materials Science and Engineering was recognized for blazing a trail in the field of broadband metamaterials. Professor Shin’s research on the broadband enhancement of the electric permittivity and refractive index of metamaterials has great potential in both academia and industry. Professor Hongki Yoo from the Department of Mechanical Engineering is expected to create a significant ripple effect in the diagnosis of cardiovascular disorders through the development of new optical imaging techniques and applications. Finally, Dr. Sejeong Kim, a KAIST graduate and a Chancellor’s postdoctoral research fellow at the University of Technology Sydney (UTS), was acknowledged for her optical device research utilizing two-dimensional materials. Dr. Kim’s research at UTS now focuses on the introduction of micro/nano cavities for new materials. (END)
Professor YongKeun Park Wins the 2018 Fumio Okano Award
(Professor Park) Professor YongKeun Park from the Department of Physics won the 2018 Fumio Okano Award in recognition of his contributions to 3D display technology development during the annual conference of the International Society for Optics and Photonics (SPIE) held last month in Orlando, Florida in the US. The Fumio Okano Best 3D Paper Prize is presented annually in memory of Dr. Fumio Okano, a pioneer and innovator of 3D displays who passed away in 2013, for his contributions to the field of 3D TVs and displays. The award is sponsored by NHK-ES. Professor Park and his team are developing novel technology for measuring and visualizing 3D images by applying random light scattering. He has published numerous papers on 3D holographic camera technology and 3000x enhanced performance of 3D holographic displays in renowned international journals such as Nature Photonics, Nature Communications, and Science Advances. His technology has drawn international attention from renowned media outlets including Newsweek and Forbes. He has established two startups to commercialize his technology. Tomocube specializes in 3D imaging microscopes using holotomographic technology and the company exports their products to several countries including the US and Japan. The.Wave.Talk is exploring technology for examining pre-existing bacteria anywhere and anytime. Professor Park’s innovations have already been recognized in and out of KAIST. In February, he was selected as the KAISTian of the Year for his outstanding research, commercialization, and startups. He was also decorated with the National Science Award in April by the Ministry of Science and ICT and the Hong Jin-Ki Innovation Award later in May by the Yumin Cultural Foundation. Professor Park said, “3D holography is emerging as a significant technology with growing potential and positive impacts on our daily lives. However, the current technology lags far behind the levels displayed in SF movies. We will do our utmost to reach this level with more commercialization."
KAIST Professors Selected as Y-KAST Members
Professor YongKeun Park, Professor Bumjoon Kim, Professor Keon Jae Lee, and Professor Young Seok Ju were selected as the newest members of the Young Korean Academy of Science and Technology (Y-KAST). The Korean Academy of Science and Technology, an academic institution of professional experts, selected 26 promising scientists under the age of 43 to join Y-KAST. and four KAIST professors were included in the list. The newest members were conferred on February 26. Research Field Name Natural Sciences YongKeun Park (Dept. of Physics) Engineering Bumjoon Kim (Dept. of Chemical and Biomolecular Engineering) Agricultural & Fishery Sciences Keon Jae Lee (Dept. of Materials Science and Engineering) Medical Sciences Young Seok Ju (Graduate School of Medical Science and Engineering)
Meet the KAISTian of 2017, Professor YongKeun Park
Professor YongKeun Park from the Department of Physics is one of the star professors in KAIST. Rising to the academic stardom, Professor Park’s daily schedule is filled with series of business meetings in addition to lab meetings and lectures. The year 2017 must have been special for him. During the year, he published numerous papers in international journals, such as Nature Photonics, Nature Communications and Science Advances. These high performances drew international attention from renowned media, including Newsweek and Forbes. Moreover, recognizing his research performance, he was elected as a fellow member of the Optical Society (OSA) in his mid-30s. Noting that the members’ age ranges from late 50s to early 60s, Professor Park’s case considered to be quite exceptional. Adding to his academic achievement, he has launched two startups powered of his own technologies. One is called Tomocube, a company specialized in 3-D imaging microscope using holotomography technology. His company is currently exporting the products to multiple countries, including the United States and Japan. The other one is The.Wave.Talk which has technologies for examining pre-existing bacteria anywhere and anytime. His research career and entrepreneurship are well deserved recipient of many honors. At the 2018 kick-off ceremony, Professor Park was awarded the KAISTian of 2017 in recognition of his developing holographic measure and control technology as well as founding a new field for technology application. KAISTian of the Year, first presented in 2001, is an award to recognize the achievements and exemplary contribution of KAIST member who has put significant effort nationally and internationally, enhancing the value of KAIST. While receiving the award, he thanked his colleagues and his students who have achieved this far together. He said, “I would like to thank KAIST for providing environment for young professors like me so that we can engage themselves in research. Also, I would like to mention that I am an idea seeder and my students do the most of the research. So, I appreciate my students for their hard works, and it is very pleasure to have them. Lastly, I thank the professors for teaching these outstanding students. I feel great responsibility over this title. I will dedicate myself to make further progress in commercializing technology in KAIST.” Expecting his successful startup cases as a model and great inspiration to students as well as professors, KAIST interviewed Professor Park. Q What made you decide to found your startups? A I believed that my research areas could be further used. As a professor, I believe that it is a university’s role to create added value through commercializing technology and creating startups. Q You have co-founded two startups. What is your role in each company? A So, basically I have two full-time jobs, professor in KAIST and CTO in Tomocube. After transferring the technology, I hold the position of advisor in The.Wave.Talk. (Holographic images captured by the product Professor Park developed) Q Do your students also participate in your companies or can they? A No, the school and companies are separate spaces; in other words, they are not participating in my companies. They have trained my employees when transferring the technologies, but they are not directly working for the companies. However, they can participate if they want to. If there’s a need to develop a certain technology, an industry-academia contract can be made. According to the agreement, students can work for the companies. Q Were there any hardships when preparing the startups? A At the initial stage, I did not have a financial problem, thanks to support from Startup KAIST. Yet, inviting capital is the beginning, and I think every step I made to operate, generate revenue, and so on is not easy. Q Do you believe KAIST is startup-friendly? A Yes, there’s no school like KAIST in Korea and any other country. Besides various programs to support startup activities, Startup KAIST has many professors equipped with a great deal of experience. Therefore, I believe that KAIST provides an excellent environment for both students and professors to create startups. Q Do you have any suggestion to KAIST institutionally? A Well, I would like to make a comment to students and professors in KAIST. I strongly recommend them to challenge themselves by launching startups if they have good ideas. Many students wish to begin their jobs in government-funded research institutes or major corporates, but I believe that engaging in a startup company will also give them valuable and very productive experience. Unlike before, startup institutions are well established, so attracting good capital is not so hard. There are various activities offered by Startup KAIST, so it’s worthwhile giving it a try. Q What is your goal for 2018 as a professor and entrepreneur? A I don’t have a grand plan, but I will work harder to produce good students with new topics in KAIST while adding power to my companies to grow bigger. By Se Yi Kim from the PR Office
Professor YongKeun Park Elected as a Fellow of the Optical Society
Professor YongKeun Park, from the Department of Physics at KAIST, was elected as a fellow member of the Optical Society (OSA) in Washington, D.C. on September 12. Fellow membership is given to members who have made a significant contribution to the advancement of optics and photonics. Professor Park was recognized for his research on digital holography and wavefront control technology. Professor Park has been producing outstanding research outcomes in the field of holographic technology and light scattering control since joining KAIST in 2010. In particular, he developed and commercialized technology for a holographic telescope. He applied it to various medical and biological research projects, leading the field worldwide. In the past, cells needed to be dyed with fluorescent materials to capture a 3-D image. However, Professor Park’s holotomography (HT) technology can capture 3-D images of living cells and tissues in real time without color dyeing. This technology allows diversified research in the biological and medical field. Professor Park established a company, Tomocube, Inc. in 2015 to commercialize the technology. In 2016, he received funding from SoftBank Ventures and Hanmi Pharmaceutical. Currently, major institutes, including MIT, the University of Pittsburgh, the German Cancer Research Center, and Seoul National University Hospital are using his equipment. Recently, Professor Park and his team developed technology based on light scattering measurements. With this technology, they established a company called The Wave Talk and received funding from various organizations, such as NAVER. Its first product is about to be released. Professor Park said, “I am glad to become a fellow member based on the research outcomes I produced since I was appointed as a professor at KAIST. I would like to thank the excellent researchers as well as the school for its support. I will devote myself to continuously producing novel outcomes in both basic and applied fields.” Professor Park has published nearly 100 papers in renowned journals including Nature Photonics, Nature Communications, Science Advances, and Physical Review Letters.
Fast, Accurate 3D Imaging to Track Optically-Trapped Particles
KAIST researchers published an article on the development of a novel technique to precisely track the 3-D positions of optically-trapped particles having complicated geometry in high speed in the April 2015 issue of Optica. Optical tweezers have been used as an invaluable tool for exerting micro-scale force on microscopic particles and manipulating three-dimensional (3-D) positions of particles. Optical tweezers employ a tightly-focused laser whose beam diameter is smaller than one micrometer (1/100 of hair thickness), which generates attractive force on neighboring microscopic particles moving toward the beam focus. Controlling the positions of the beam focus enabled researchers to hold the particles and move them freely to other locations so they coined the name “optical tweezers.” To locate the optically-trapped particles by a laser beam, optical microscopes have usually been employed. Optical microscopes measure light signals scattered by the optically-trapped microscopic particles and the positions of the particles in two dimensions. However, it was difficult to quantify the particles’ precise positions along the optic axis, the direction of the beam, from a single image, which is analogous to the difficulty of determining the front and rear positions of objects when closing an eye due to a lack of depth perception. Furthermore, it became more difficult to measure precisely 3-D positions of particles when scattered light signals were distorted by optically-trapped particles having complicated shapes or other particles occlude the target object along the optic axis. Professor YongKeun Park and his research team in the Department of Physics at the Korea Advanced Institute of Science and Technology (KAIST) employed an optical diffraction tomography (ODT) technique to measure 3-D positions of optically-trapped particles in high speed. The principle of ODT is similar to X-ray CT imaging commonly used in hospitals for visualizing the internal organs of patients. Like X-ray CT imaging, which takes several images from various illumination angles, ODT measures 3-D images of optically-trapped particles by illuminating them with a laser beam in various incidence angles. The KAIST team used optical tweezers to trap a glass bead with a diameter of 2 micrometers, and moved the bead toward a white blood cell having complicated internal structures. The team measured the 3-D dynamics of the white blood cell as it responded to an approaching glass bead via ODT in the high acquisition rate of 60 images per second. Since the white blood cell screens the glass bead along an optic axis, a conventionally-used optical microscope could not determine the 3-D positions of the glass bead. In contrast, the present method employing ODT localized the 3-D positions of the bead precisely as well as measured the composition of the internal materials of the bead and the white blood cell simultaneously. Professor Park said, “Our technique has the advantage of measuring the 3-D positions and internal structures of optically-trapped particles in high speed without labelling exogenous fluorescent agents and can be applied in various fields including physics, optics, nanotechnology, and medical science.” Kyoohyun Kim, the lead author of this paper (“Simultaneous 3D Visualization and Position Tracking of Optically Trapped Particles Using Optical Diffraction Tomography”), added, “This ODT technique can also apply to cellular-level surgeries where optical tweezers are used to manipulate intracellular organelles and to display in real time and in 3-D the images of the reaction of the cell membrane and nucleus during the operation or monitoring the recovery process of the cells from the surgery.” The research results were published as the cover article in the April 2014 issue of Optica, the newest journal launched last year by the Optical Society of America (OSA) for rapid dissemination of high-impact results related to optics. Figure 1: This picture shows the concept image of tweezing an optically-trapped glass bead on the cellular membrane of a white blood cell. Figure 2: High-speed 3-D images produced from optical diffraction tomography technique
마지막 페이지 1
KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
Copyright(C) 2020, Korea Advanced Institute of Science and Technology,
All Rights Reserved.