Welcome to the January issue of the
Medical Imaging and Data Resource Center (MIDRC) newsletter!
MIDRC continues to fortify its ingestion pipeline and data portal, and has recently published new imaging cases! To date, registered users can run queries on, and build cohorts with, approximately 15,500+ published imaging studies. Additionally, there are upwards of 30,000 contributed imaging studies scheduled for release in the next quarter, MIDRC data quality, harmonization, curation and annotation processes before publication. Currently users can build cohorts of both chest radiographs and CT scans, with plans to publish COVID-related MRI, ultrasound and PET scans in the near future.
|
|
News and Events:
MIDRC at RSNA!
The 107th Scientific Assembly and Annual Meeting (RSNA 2021), was held Nov. 28-Dec. 2, 2021, at McCormick Place in Chicago, IL
Pictured above are five of the seven MIDRC PIs presenting at RSNA 2021:
Paul Kinahan, PhD (University of Washington & AAPM Research Committee Chair)
Michael Tilkin, MS (ACR Chief Information Officer)
Maryellen Giger, PhD (Contract PI: University of Chicago & AAPM Data Science Committee Chair)
Curt Langlotz, MD, PhD (Stanford University & RSNA Board Liaison for IT & Annual Meeting)
Adam Flanders, MD (Thomas Jefferson University & Member RSNA/ACR Common Data Element (CDE) Steering Committee)
|
|
Save the date for RSNA 2022!
November 27 to December 1, 2022
|
|
You Ask, We Answer:
We have had great success with our MIDRC monthly Seminar Series, held on the 3rd Tuesday of every month, highlighting the work of our individual researchers, Our November speaker was Dr. Berkman Sahiner (FDA), a MIDRC researcher from the Bias and Diversity working group (BDWG) and a MIDRC technology development project focused on performance assessment and benchmarking methods, who presented on, "Task-specific performance evaluation metrics for machine learning algorithms employing MIDRC data".
Our January speaker will be Dr. Judy Wawira-Gichoya (Emory University), a researcher from BDWG and MIDRC collaborative research projects focused on machine learning algorithm validation and visualization and multi-modality data, who will be presenting on, "Reading Race: AI Recognizes Patient’s Racial Identity In Medical Images".
Register Here!
MIDRC continues to host quarterly Town Hall Meetings, as a forum to engage directly with the medical community at-large and answer all of their research and contribution questions, as well as provide regular publication updates and news on the research and achievements of the 109 investigators collaborating as part of the MIDRC team. Please visit our YouTube page for the Town Hall and monthly Seminar Series recordings.
Additional Online Resources about the Gen3 platform hosting MIDRC data:
The Gen3 YouTube channel
The Gen3 Forum
CTDS GitHub Organization
|
|
MIDRC Researcher Spotlights
|
|
|
Dr.Judy Wawira-Gichoya
Dr.Judy Wawira-Gichoya is a multidisciplinary researcher, trained as both an informatician and a clinically active radiologist. She is an assistant professor at Emory University, and works in Interventional Radiology and Informatics. She is seconded to the National Institutes of Health as a data scholar to help with the Open Data Science Platform (OSDP) component of the DSI Africa Initiative to “Harness Data Science for Health In Africa”. Her career focus is on validating machine learning models for health in real clinical settings, exploring explainability, fairness, and a specific focus on how algorithms fail. She has worked on the curation of datasets for the SIIM (Society for Imaging Informatics in Medicine) hackathon and ML committee. She volunteers on the ACR and RSNA machine learning committees to support the AI ecosystem to advance development and use of AI in medicine.
Judy's dream job involves being a radiologist working in the Maasai Mara National Park.
|
|
|
|
Dr.Weijie Chen
Dr.Weijie Chen is a regulatory scientist in the Division of Imaging, Diagnostics, and Software Reliability in the Office of Science and Engineering Laboratories, CDRH, US Food and Drug Administration. Within MIDRC, Dr. Chen is leading the Collaborative Research Project 11 “Investigation of image-based biomarkers for radiogenomics of COVID-19”, where he and his collaborators are investigating the development and assessment issues in the use of AI/ML models and multimodal data for COVID-19. He is well-suited to helm this work as he has over 15 years of experience in academia and the federal government on development of image analysis algorithms and assessment methodologies for imaging, AI/ML algorithms, and general diagnostics.
Weijie earned his PhD in Medical Physics in 2007 from University of Chicago, and has served as PI or co-investigator in numerous FDA intramural funded projects. Additionally, he’s a committee member of the Digital Pathology Conference and the Computer-Aided Diagnosis Conference at the SPIE Medical Imaging Symposium and an associate editor for the SPIE Journal of Medical Imaging.
Weijie lives with his family in Rockville, Maryland, where he especially enjoys hiking, biking, reading, and playing with his two kids.
|
|
|
|
Dr. Akshay S. Chaudhari
Trained in bioengineering with a focus in electrical engineering, Akshay S. Chaudhari, PhD, has developed expertise in rapid, low-cost and quantitative MRI for musculoskeletal MRI. He currently works to develop novel machine learning tools for enhancing the efficiency and efficacy of medical imaging data acquisition and post-processing. His current research focuses on improving the value of medical imaging using a combination of machine learning and physics with a particular focus on combining the two for building machine learning models with limited annotated datasets. Within MIDRC, he is exploring how to build robust and interpretable machine learning models using self-supervised learning.
Dr. Chaudhari earned an MS and PhD in bioengineering at Stanford University in California. He is an Assistant Professor in the Department of Radiology and (by courtesy) Biomedical Data Science at Stanford. He is the Associate Director of Research and Education at the Stanford Center for Artificial Intelligence in Medicine and Imaging. When not working (or on zoom), you can most likely find Akshay either skiing, cycling, or playing ultimate frisbee!
|
|
|
Earn MIPS Improvement Activity Credits
By Contributing COVID images and data to CIRR and RICORD
Medical imaging practices and radiologists now can claim
Merit-based Incentive Payment System (MIPS) "Improvement Activity" credits for contributing COVID-related data and images to MIDRC’s two intake portals through American College of Radiology’s (ACR), COVID-19 Imaging Research Registry (CIRR) and Radiological Society of North America’s (RSNA) The RSNA International COVID-19 Open Radiology Database (RICORD).
Practices and clinicians can earn Centers for Medicare and Medicaid Services (CMS) points by completing MIPS requirements.
|
|
|
MIDRC Released 11,804 additional Imaging Studies with 20,000 currently undergoing de-identification
|
|
|
|
|