Original language | English (US) |
---|---|
Pages (from-to) | 1-4 |
Number of pages | 4 |
Journal | Medical physics |
Volume | 47 |
Issue number | 1 |
DOIs | |
State | Published - Jan 1 2020 |
ASJC Scopus subject areas
- Biophysics
- Radiology Nuclear Medicine and imaging
Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS
In: Medical physics, Vol. 47, No. 1, 01.01.2020, p. 1-4.
Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - Clinical implementation of AI technologies will require interpretable AI models
AU - Jia, Xun
AU - Ren, Lei
AU - Cai, Jing
N1 - Funding Information: Artificial intelligence (AI) technologies have been heavily investigated in recent years in various contexts of science and technology. AI models are known to be powerful tools to help us resolve complex problems even though most of us have little understanding of their working principles and even experts may not appreciate which data features drive deep‐learning performance in specific applications. These complex models are therefore often referred to as black box models. While some are supportive to the idea that clinical adoption of AI technologies should be only for interpretable models, others believe that it is not required to interpret the AI models as long as they serve the purposes. This is the premise debated in this month's Point/Counterpoint. Arguing for the Proposition is Xun Jia, Ph.D. Dr. Jia is Associate Professor and Director of Medical Physics research at the Department of Radiation Oncology, University of Texas Southwestern Medical Center (UTSW). He received his Master degree in applied mathematics in 2007 and Ph.D. degree in physics in 2009, both from the University of California Los Angeles. After receiving his postdoctoral training in medical physics from the Department of Radiation Physics and Applied Sciences, University of California San Diego in 2009–2011, he became a faculty in the same department. In 2013, he moved to UTSW. Over the years, Dr. Jia has conducted productive research on low‐dose cone beam CT reconstruction, GPU‐based Monte Carlo radiation transport simulation, deep‐learning based image processing and radiotherapy treatment planning, and development of a preclinical small animal radiation research platform. He has published over 110 peer‐reviewed manuscripts. His research has been funded by NIH, the State of Texas, industrial, and charitable funding agencies. Dr. Jia currently serves as an Editorial board member of Physics in Medicine and Biology and an Associate editor of Medical Physics. He is the recipient of John Laughlin Young Scientist Award of American Association of Physicists in Medicine in 2017. Arguing against the proposition is Lei Ren, Ph.D. Dr. Ren received his Ph.D. degree in Medical Physics from Duke University in 2009, and then worked as a medical physicist in the radiation oncology department at Henry Ford Hospital in Detroit, MI for 2 yr. He joined Duke University as a faculty for both the radiation oncology department and the Medical Physics program in 2011, and is currently an Associate Professor in the department. He is certified by the American Board of Radiology in Therapeutic Medical Physics. In research, Dr. Ren’s focus is image‐guided radiation therapy (IGRT), including imaging dose reduction, image reconstruction, synthesis, augmentation and registration, 4D imaging, and applications of AI in IGRT. He has published over 50 papers in peer‐reviewed journals, including featured articles, and six book chapters. His research has been funded by both NIH and Industry grants and has won multiple awards from AAPM, ASTRO, and ISMRM. Dr. Ren regularly provides scientific reviews for peer‐reviewed journals, conferences, book proposals, and NIH grant applications. He has served in editorial roles for different journals and has been actively involved in multiple committees and annual meeting organization for AAPM and ASTRO. Dr. Ren has mentored seven Ph.D. students, and 16 master students and has received the Mentorship Award from Duke Medical Physics program.
PY - 2020/1/1
Y1 - 2020/1/1
UR - http://www.scopus.com/inward/record.url?scp=85075297765&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075297765&partnerID=8YFLogxK
U2 - 10.1002/mp.13891
DO - 10.1002/mp.13891
M3 - Article
C2 - 31663612
AN - SCOPUS:85075297765
SN - 0094-2405
VL - 47
SP - 1
EP - 4
JO - Medical physics
JF - Medical physics
IS - 1
ER -