Sung Lab
The Sung Lab, directed by Kyung Sung, is part of Magnetic Resonance Research Labs (MRRL) in the Department of Radiological Sciences within the School of Medicine at UCLA. Our mission is to advance patient healthcare through the development and application of artificial intelligence and quantitative imaging technologies in order to improve diagnostic contrast integrated with multi-scale information. Our research focuses on novel artificial intelligence and medical image analysis technologies and has successfully developed and deployed novel deep-learning algorithms and quantitative MRI techniques for early diagnosis, treatment guidance, and therapeutic response assessment. Our current research projects include:
Clinical Applications
- Quantitative Multi-parametric MRI for Prostate Cancer
- Multi-Parametric Human Placenta Imaging
- Liver Perfusion MRI
- Quantitative Breast Perfusion MRI
- Pituitary Microadenoma Imaging with a Deployable Microcoil
Technical Developments
- Machine Learning / Deep Learning Algorithms
- Advanced Image Reconstruction
- Quantitative Image Analysis / Modeling
- Rapid / Real-Time Imaging
Media Coverage / Awards / Invited Lectures
- Human Placenta Project - Media Release
- Placenta Arterial Spin Labeling - Media Release
- Artificial Intelligence in Prostate MRI - 10th MAGNETOM World Summit
- Placenta Multi-parametric MRI - 2018 NIH Human Placenta Project (from 1:03:00)
- 2019 IEEE International Symposium on Biomedical Imaging (ISBI) - Runners-up Best Paper Award | News Coverage
- Multi-parametric MRI for Prostate Cancer - News Coverage
- Artificial Intelligence in Prostate MRI - Media Release
- Improved Prostate Cancer Diagnosis - Daily Bruin
- Placenta Arterial Spin Labeling MRI - NICHD News | News Coverage | JMRI Editorial
- AI Applications in Medical Imaging - RSNA News
- NIH National Cancer Institute Award - UCLA Newsroom | The Cancer Letter
- Nature - How AI is improving cancer diagnosis
- Blood test to predict pregnancy complications - UCLA Newsroom
- MRI technique may predict impaired fetal growth and small size at birth - NICHD News
- NIH National Cancer Institute Award - UCLA Newsroom | UCLA Health Newsroom
Faculty:
Project Scientists / Postdoctoral Scholars / Visiting Scholars:
Ph.D. / Master's Students:
Qiudi He, B.S.
(Electrical Engineering)
Clinical Fellows / Medical Students / Undergraduate Students:
Brian Chau
(Statistics)
Khang Doan
(Bioengineering)
Yeadam Kim
(Mathematics and Computer Science)
Swasktik Purathepparambil
(Computational Math & Data Science)
Eileen Zhang
(Bioengineering)
Jeffrey Le
(Computational Math)
Junying Li
(Applied Math)
Jimmy Hou
(Computational Math)
Administrative Staffs:
Study Coordinators:
Nashla Barroso
Previous Members:
Novena Rangwala, Ph.D. – Postdoctoral Fellow, 2013 — 2016 (Currently: GE Healthcare)
Dapeng Liu, Ph.D. – Postdoctoral Fellow, 2016 — 2017 (Currently: Research Associate, Dept. of Radiology, Johns Hopkins University)
Yeejin Lee, Ph.D. – Postdoctoral Fellow, 2017 — 2018 (Currently: Associate Professor, Dept. of Electrical and Information Engineering, Seoul National University of Science and Technology)
Thomas Martin, Ph.D. – Ph.D. Student, 2012 — 2018 (Currently: Assistant Professor, Dept. of Radiation Oncology, University of Utah and a Medical Physicist at Huntsman Cancer Hospital)
Xinran Zhong, Ph.D. - Ph.D. Student, 2014 — 2019 (Currently: Assistant Professor, Dept. of Radiation Oncology, Univ. of Texas Southwestern)
Ruiming Cao, M.S. – Masters Student, 2017 — 2019 (Currently: Research Scientist at Chan Zuckerberg Imaging Institute)
Yongkai Liu, Ph.D. – Ph.D. Student, 2017— 2022 (Currently: Postdoctoral Scholar, Dept. of Radiology, Stanford)
Fatemeh Zabihollahy, Ph.D. – Postdoctoral Fellow / Project Scientist, 2021— 2023 (Currently: Applied Deep Learning Scientist, University of Toronto)
Jiahao Lin, Ph.D. – Ph.D. Student, 2016— 2023 (Currently: Software Engineer, Meta Platforms, Inc.)
Haoxin Zheng, Ph.D. – Ph.D. Student, 2019— 2024 (Currently: Applied Scientist, Amazon)
Previous Visitors:
Duanduan (Sally) Liu – Visiting Graduate Student, Feb 2013 — July 2013
Eric Cho – Visiting Student, May 2013 — July 2013
ByungJoo (Joshua) Park, Ph.D. – Visiting Scholar, Feb 2013 — Feb 2014
Wenrui Yang – Visiting Undergraduate Student, Sep 2013 — Mar 2014
Marina Miranda – Summer Research Student, Brazil Scientific Mobility Program (BSMP), May 2016 — Aug 2016
Tianle Cao – Summer Research Student, Tsinghua University, June 2017 — Sep 2017
Kang-Sun Choi, Ph.D. – Visiting Scholar, Jan 2017 — Jan 2018
Wakana Murakami, M.D. – Visiting Scholar, Sep 2020 — Nov 2022
Tianxing Ma – Visiting Graduate Student, May 2024 — Aug 2024
Eungsun Oh, M.D., Ph.D. – Visiting Scholar, Jan 2024 — Dec 2024
We are seeking an excellent postdoctoral fellow/graduate student with a strong background in signal and image processing, with an interest in developing novel MRI methods. Please see here for more details.
Publications:
Published Manuscripts @Pubmed or @Google Scholar
Research Funding:
- 2020-2025 NIH: R01 CA248506 (PI: Sung/Wu): Integrating Quantitative MRI and Artificial Intelligence to Improve Prostate Cancer Classification
- 2022-2024 NIH: R01 CA248506-S1 (PI: Sung/Wu): A Structured Multi-scale Dataset with Prostate MRI for AI/ML Research
- 2023-2028 NIH: R01 CA272702 (PI: Sung/Kim): Racially-associated MRI Analysis and Modeling for Predicting Aggressive Prostate Cancer
- 2024-2026 NIH: R01 CA272702-W1 (PI: Sung/Kim): Diversity Supplements for Imaging Research in Prostate Cancer Health Disparities
- 2024-2025 Siemens Healthineers (PI: Sung): A Through-plane Super-Resolution Framework in MRI: Enhancing Image Quality and Diagnostic Efficiency
- 2023-2028 NIH: U01 CA230705 (PI: Zhou): The UCLA Center in Early Detection of Liver Cancer
- 2019-2024 NIH: R01 HD10015 (PI: Devaskar): Electrochemical Liquid Biopsy Assessing Placenta Health
- 2020-2024 NIH: R01 DK124417 (PI: Wu/Calkins): Quantifying Body Composition and Liver Disease in Children Using Free-Breathing MRI and MRE
- 2020-2022 Tate Fund (PI: Lee-Felker/Sung): Combined Conventional and Ultrafast MRI-Based Integrated Radiomic Models for Predicting Response to Neoadjuvant Chemotherapy in Women with Triple Negative Breast Cancer