News | RSNA | December 24, 2019

Alzheimer’s Disease AI Research Receives RSNA Margulis Award

The Radiological Society of North America (RSNA) presented its eighth Alexander R. Margulis Award for Scientific Excellence to Jae Ho Sohn, M.D., from the Radiology & Biomedical Imaging Department at the University of California in San Francisco (UCSF)

Jae Ho Sohn, M.D.

December 24, 2019 — The Radiological Society of North America (RSNA) presented its eighth Alexander R. Margulis Award for Scientific Excellence to Jae Ho Sohn, M.D., from the Radiology & Biomedical Imaging Department at the University of California in San Francisco (UCSF), for the article, “A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain,” published online in November 2018. The groundbreaking study shows the significant potential of artificial intelligence (AI) as a diagnostic tool in Alzheimer’s disease (AD). Sohn was presented with the award today at RSNA 2019 in Chicago.

Named for Alexander R. Margulis, M.D., a distinguished investigator and inspiring visionary in the science of radiology, this annual award recognizes the best original scientific article published in RSNA’s peer-reviewed journal Radiology.

A radiology resident with an engineering background,  Sohn co-authored the study with the goal of developing a deep learning algorithm to detect patterns on complex brain images to identify AD as early as possible.

“Alzheimer’s is a costly, devastating disease and by the time a clinical diagnosis is made, it’s often too late,” said Sohn, who leads the UCSF Big Data in Radiology (BDRAD) multidisciplinary team of physicians and engineers focusing on radiological data science. “We hypothesized we could use AI as an early prediction tool for Alzheimer’s in conjunction with other biochemical and imaging tests. If we can detect the disease early enough, physicians have a chance of slowing it down or halting it through therapeutic intervention.”

The results far exceeded Sohn’s expectations. Using 18F fluorodeoxyglucose (FDG) PET scans to train a deep learning algorithm, Sohn and colleagues were able to detect early-stage AD about six years before it was clinically diagnosed.

“This research is groundbreaking,” said Radiology editor David A. Bluemke, M.D. “It demonstrates the potential for state-of-the-art AI technology to help interpret the remarkably complex patterns on FDG PET imaging in patients with Alzheimer's disease. Even more hopeful for Alzheimer’s patients, this same line of research will also apply to more specific PET tracers for detecting the disease.”

The study began when UCSF colleagues Benjamin Franc, M.D., a nuclear medicine specialist, and Youngho Seo, Ph.D., a nuclear medicine physicist, approached Sohn and undergraduate student Yiming Ding about developing an algorithm to interpret FDG PET brain scans. Research has linked the disease process to changes in metabolism, which can be difficult to recognize. PET scans can measure the uptake of FDG in brain cells, indicating metabolic activity.

The research team used data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), a major multi-site study focused on clinical trials to improve prevention and treatment of this disease. The ADNI dataset included more than 2,100 FDG PET brain images from 1,002 patients. The researchers trained the deep learning algorithm on 90 percent of the dataset and then tested it on the remaining 10 percent of the dataset.

Finally, they tested the algorithm on an independent set of 40 FDG PET imaging exams from 40 patients that it had never studied. Results showed that algorithm achieved 82 percent specificity and 100 percent sensitivity at detecting the disease an average of more than six years prior to the final diagnosis.

“I was surprised at how high the numbers were, but I already knew AI was going to be more effective than humans,” Sohn said. “The very special nature of AI detects very global, subtle changes that the human eye cannot.”

Sohn, who plans to continue researching the vast capabilities of AI in radiology, was extremely honored to be chosen for Margulis Award, which he believes will open doors for future research.

“I was completely surprised and shocked to receive the award,” Sohn said. “This recognition will pave the way for my research career and will allow me to connect with other researchers doing important work.”

Sohn stresses that further validation with larger and prospective external tests must be performed before the Alzheimer’s detection algorithm can be used clinically. However, he believes that researchers united in the fight against Alzheimer’s are on the brink of a significant breakthrough.

“I really think we are at an inflection point with Alzheimer’s disease,” Sohn said. “I believe we will see major progress in the next decade or two.”

Access the study at https://pubs.rsna.org/doi/10.1148/radiol.2018180958.  

Related content:

Clinical Implementation of Artificial Intelligence in Radiology

Related Content

In a study of more than 1,000 patients published in the journal Radiology, chest CT outperformed lab testing in the diagnosis of 2019 novel coronavirus disease (COVID-19) #COVID19 #COVID-2019 #2019nCoV

Chest CT images of a 29-year-old man with fever for 6 days. RT-PCR assay for the SARS-CoV-2 using a swab sample was performed on Feb. 5, 2020, with a positive result. (A column) Normal chest CT with axial and coronal planes was obtained at the onset. (B column) Chest CT with axial and coronal planes shows minimal ground-glass opacities in the bilateral lower lung lobes (yellow arrows). (C column) Chest CT with axial and coronal planes shows increased ground-glass opacities (yellow arrowheads). (D column) Chest CT with axial and coronal planes shows the progression of pneumonia with mixed ground-glass opacities and linear opacities in the subpleural area. (E column) Chest CT with axial and coronal planes shows the absorption of both ground-glass opacities and organizing pneumonia. Image courtesy of Radiology

News | Computed Tomography (CT) | February 26, 2020 | Melinda Taschetta-Millane and Dave Fornell
February 26, 2020 — In a study of m
 over the course of a week and a half #coronavirus #COVID19 #COVID-2019 #2019nCoV

29-year old male with unknown exposure history, presenting with fever and cough, ultimately requiring intensive care unit admission. (a) Axial thin-section non-contrast CT scan shows diffuse bilateral confluent and patchy ground-glass (solid arrows) and consolidative (dashed arrows) pulmonary opacities. (b) The disease in the right middle and lower lobes has a striking peripheral distribution (arrow). Image courtesy of Radiology 

News | Computed Tomography (CT) | February 26, 2020
February 26, 2020 — Mount Sinai Health System physicians—the
Christopher Comstock, M.D., ECOG-ACRIN Cancer Research Group study published in JAMA builds evidence for use of abbreviated MRI in women with dense breasts

Christopher Comstock, M.D., (Memorial Sloan Kettering Cancer Center) is the lead author of a paper in JAMA that reports that abbreviated breast MRI detected significantly more (almost 2 and a half times as many) breast cancers than digital breast tomosynthesis (3-D mammography) in average-risk women with dense breasts. Photo courtesy of Memorial Sloan Kettering Cancer Center

News | Breast Imaging | February 26, 2020
February 26, 2020 — According to a study
Images in a 41-year-old woman who presented with fever and positive polymerase chain reaction assay for the 2019 novel coronavirus (2019-nCoV) #coronavirus #nCoV2019 #2019nCoV #COVID19

Images in a 41-year-old woman who presented with fever and positive polymerase chain reaction assay for the 2019 novel coronavirus (2019-nCoV). Three representative axial thin-section chest CT images show multifocal ground glass opacities without consolidation. Three-dimensional volume-rendered reconstruction shows the distribution of the ground-glass opacities (arrows). Image courtesy of the Radiological Society of North America (RSNA)

News | Radiology Imaging | February 25, 2020
February 24, 2020 — The U.S.
Carestream’s state-of-the-art OnSight 3D Extremity System
News | Computed Tomography (CT) | February 25, 2020
February 25, 2020 — Carestream’s state-of-the-art...
Sponsored Content | Videos | Artificial Intelligence | February 21, 2020
In Artificial Intelligence at RSNA 2019, ITN Contributing Editor Greg Freiherr offers an overview of artificial intel
Sponsored Content | Videos | Enterprise Imaging | February 21, 2020
In Enterprise Imaging at RSNA 2019, ITN Contributing Editor Greg Freiherr offers an overvie