Ronald Summers

{{short description|Radiologist at the National Institutes of Health}} {{Infobox scientist | name = Ronald M. Summers | image = | image_size = 200px | alt = | caption = | birth_date =  | birth_place = | death_date =  | death_place = | citizenship = USA | nationality = | fields = | workplaces = NIH | alma_mater = University of Pennsylvania | doctoral_advisor = | academic_advisors = | doctoral_students = | notable_students = | known_for = CT Colonography, deep learning in radiology | author_abbrev_bot = | author_abbrev_zoo = | influences = | influenced = | awards = | signature =  | signature_alt = | footnotes = | spouse = }} '''Ronald Marc Summers''' is an American radiologist and senior investigator at the Diagnostic Radiology Department at the NIH Clinical Center in Bethesda, Maryland. He is chief of the Clinical Image Processing Service and directs the Imaging Biomarkers and Computer-Aided Diagnosis (CAD) Laboratory. A researcher in the field of radiology and computer-aided diagnosis, he has co-authored over 500 journal articles and conference proceedings papers and is a coinventor on 12 patents.<ref name="googlescholar">{{cite web |title=Ronald M. Summers, MD, PhD |url=https://scholar.google.com/citations?user=j4cvq80AAAAJ&hl=en |website=scholar.google.com |publisher=Google Scholar Citations |access-date=21 December 2018}}</ref> His lab has conducted research applying artificial intelligence and deep learning to radiology.<ref name="healthimaging">{{cite news |last1=Pearson |first1=Dave |title=Radiologists sharing more abdominal duties with computers |url=https://www.healthimaging.com/topics/imaging-informatics/radiologists-sharing-more-abdominal-duties-computers |access-date=22 December 2018 |work=Health Imaging |date=1 July 2016 |language=en}}</ref><ref name="nihblog">{{cite web |title=Doctor Data: How Computers Are Invading the Clinic |url=https://irp.nih.gov/blog/post/2018/08/doctor-data-how-computers-are-invading-the-clinic |website=NIH Intramural Research Program |access-date=22 December 2018 |language=en |date=2 August 2018}}</ref><ref>{{cite web |title=Share Your Science: The Impact of Deep Learning on Radiology |url=https://news.developer.nvidia.com/share-your-science-the-impact-of-deep-learning-on-radiology/ |publisher=NVIDIA Developer News Center |access-date=21 December 2018 |date=13 December 2016}}</ref>

== Background == Summers received his B.A. degree in physics from the University of Pennsylvania in 1981, where he also obtained his M.D. and Ph.D. degrees in Medicine/Anatomy & Cell Biology in 1988.<ref name="cv">{{cite news |title=NIH Clinical Center: Curriculum Vitae for Ronald M. Summers, MD, PhD |url=https://www.cc.nih.gov/radis/summers |access-date=21 December 2018 |work=www.cc.nih.gov |language=en}}</ref> He completed a medical internship at the Penn Presbyterian Medical Center in Philadelphia, Pennsylvania, a radiology residency at the University of Michigan, Ann Arbor, MI (1989–1993) and an MRI fellowship at Duke University, Durham, NC (1993–1994).<ref name="NIH"/>

== Research == Summers' lab is known for developing software for "virtual colonoscopy" and computer aided detection (CAD) algorithms which assist in the detection of colon polyps.<ref>{{cite journal |last1=Summers |first1=Ronald M. |last2=Yao |first2=Jianhua |last3=Pickhardt |first3=Perry J. |last4=Franaszek |first4=Marek |last5=Bitter |first5=Ingmar |last6=Brickman |first6=Daniel |last7=Krishna |first7=Vamsi |last8=Choi |first8=J. Richard |title=Computed Tomographic Virtual Colonoscopy Computer-Aided Polyp Detection in a Screening Population |journal=Gastroenterology |date=December 2005 |volume=129 |issue=6 |pages=1832–1844 |doi=10.1053/j.gastro.2005.08.054|pmid=16344052 |pmc=1576342 }}</ref> His lab is also known for multi-organ multi-atlas registration and the development of large radiologic image databases. Summers is also a practicing clinician – his clinical areas of specialty are thoracic and gastrointestinal radiology and body cross-sectional imaging.<ref name="NIH">{{cite web |title=NIH Clinical Center Senior Staff |url=http://www.cc.nih.gov/about/SeniorStaff/ronald_summers.html |archive-url=https://web.archive.org/web/20090109063733/http://www.cc.nih.gov/about/SeniorStaff/ronald_summers.html |archive-date=January 9, 2009 |publisher=NIH Clinical Center |access-date=24 December 2018 |language=en}} {{PD-notice}}</ref>

Summers' lab is known for pioneering work in the application of deep learning to problems in medical imaging such as computer aided detection, classification, and segmentation. A February 2016 paper from his lab exploring convolutional neural network architectures and transfer learning for lymph node detection and interstitial lung disease classification had over 1,000 citations as of early 2019.<ref>{{cite journal |last1=Shin |first1=Hoo-Chang |last2=Roth |first2=Holger R. |last3=Gao |first3=Mingchen |last4=Lu |first4=Le |last5=Xu |first5=Ziyue |last6=Nogues |first6=Isabella |last7=Yao |first7=Jianhua |last8=Mollura |first8=Daniel |last9=Summers |first9=Ronald M. |title=Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning |journal=IEEE Transactions on Medical Imaging |date=May 2016 |volume=35 |issue=5 |pages=1285–1298 |doi=10.1109/TMI.2016.2528162|pmid=26886976 |pmc=4890616 |arxiv=1602.03409 |bibcode=2016arXiv160203409S }}</ref> In 2018 he was the keynote speaker at the inaugural Medical Imaging and Deep Learning (MIDL) conference.<ref>{{cite web |title=MIDL2018, Day 1: Keynote by Prof. Ronald Summers | website=YouTube | date=18 July 2018 |url=https://www.youtube.com/watch?v=_hqT3cS4aa0 |access-date=22 December 2018}}</ref>

In September 2017 his lab released 100,000 anonymized chest x-ray images from 30,000 patients, including many with advanced lung disease.<ref>{{cite news |title=NIH Clinical Center provides one of the largest publicly available chest x-ray datasets to scientific community |url=https://www.nih.gov/news-events/news-releases/nih-clinical-center-provides-one-largest-publicly-available-chest-x-ray-datasets-scientific-community |archive-url=https://web.archive.org/web/20170930024818/https://www.nih.gov/news-events/news-releases/nih-clinical-center-provides-one-largest-publicly-available-chest-x-ray-datasets-scientific-community |archive-date=September 30, 2017 |access-date=22 December 2018 |work=National Institutes of Health (NIH) |date=27 September 2017 |language=EN}}</ref><ref>Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. [http://openaccess.thecvf.com/content_cvpr_2017/papers/Wang_ChestX-ray8_Hospital-Scale_Chest_CVPR_2017_paper.pdf ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases]. ''IEEE CVPR'' 2017</ref>

In July 2018, his lab released ''DeepLesion'', a dataset of 32,000 annotated lesions identified on CT images spread over 4,400 patients.<ref name="32000images">{{cite news |title=NIH Clinical Center releases dataset of 32,000 CT images |url=https://www.nih.gov/news-events/news-releases/nih-clinical-center-releases-dataset-32000-ct-images |access-date=22 December 2018 |work=National Institutes of Health (NIH) |date=20 July 2018 |language=EN}}</ref><ref>{{cite web |title=DeepLesion dataset |url=https://nihcc.app.box.com/v/DeepLesion |access-date=22 December 2018}}</ref><ref>{{cite journal |last1=Yan |first1=Ke |last2=Wang |first2=Xiaosong |last3=Lu |first3=Le |last4=Summers |first4=Ronald M. |title=DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning |journal=Journal of Medical Imaging |date=20 July 2018 |volume=5 |issue=3 |article-number=036501 |doi=10.1117/1.JMI.5.3.036501|pmid=30035154 |pmc=6052252 }}</ref><ref>{{cite journal |last1=Summers |first1=Ronald M. |last2=Bagheri |first2=Mohammad Hadi |last3=Harrison |first3=Adam P. |last4=Zhang |first4=Ling |last5=Lu |first5=Le |last6=Wang |first6=Xiaosong |last7=Yan |first7=Ke |title=Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database |date=2018 |pages=9261–9270 |url=http://openaccess.thecvf.com/content_cvpr_2018/html/Yan_Deep_Lesion_Graphs_CVPR_2018_paper.html}}</ref> At the 2019 IEEE Symposium on Biomedical Imaging (ISBI) Youbao Tang, a postdoc in Summers' lab, unveiled a universal lesion detector (nicknamed "ULDor") which uses a mask R-CNN architecture to detect many types of lesions throughout the body with high precision.<ref>{{cite journal |last1=Summers |first1=Ronald M. |last2=Xiao |first2=Jing |last3=Liu |first3=Jiamin |last4=Tang |first4=Yuxing |last5=Yan |first5=Ke |last6=Tang |first6=Youbao |title=ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining |date=18 January 2019 |arxiv=1901.06359 |bibcode=2019arXiv190106359T |language=en}}</ref>

In 2019 his lab has demonstrated how to generate weak labels from clinically generated medical reports using deep learning and natural language processing techniques, thus greatly reducing the need for burdensome hand annotation of datasets.<ref>{{cite journal |last1=Summers |first1=Ronald M. |last2=Lu |first2=Zhiyong |last3=Bagheri |first3=Mohammadhadi |last4=Sandfort |first4=Veit |last5=Peng |first5=Yifan |last6=Yan |first6=Ke |title=Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning from Radiology Reports and Label Ontology |date=9 April 2019 |arxiv=1904.04661 |bibcode=2019arXiv190404661Y |language=en}}</ref>

Summers and collaborators have also developed a tool for opportunistic fully automated bone mineral density (BMD) measurement in CT scans which has been used to track BMD changes in large longitudinal cohorts.<ref>{{cite journal |last1=Summers |first1=Ronald M. |last2=Baecher |first2=Nicolai |last3=Yao |first3=Jianhua |last4=Liu |first4=Jiamin |last5=Pickhardt |first5=Perry J. |last6=Choi |first6=J. Richard |last7=Hill |first7=Suvimol |title=Feasibility of Simultaneous Computed Tomographic Colonography and Fully Automated Bone Mineral Densitometry in a Single Examination |journal=Journal of Computer Assisted Tomography |date=March 2011 |volume=35 |issue=2 |pages=212–216 |doi=10.1097/RCT.0b013e3182032537|pmid=21412092 |pmc=3077119 }}</ref><ref>{{cite journal |last1=Pickhardt |first1=Perry J. |last2=Lee |first2=Scott J. |last3=Liu |first3=Jiamin |last4=Yao |first4=Jianhua |last5=Lay |first5=Nathan |last6=Graffy |first6=Peter M |last7=Summers |first7=Ronald M |title=Population-based opportunistic osteoporosis screening: Validation of a fully automated CT tool for assessing longitudinal BMD changes |journal=The British Journal of Radiology |date=February 2019 |volume=92 |issue=1094 |article-number=20180726 |doi=10.1259/bjr.20180726|pmid=30433815 |pmc=6404831 }}</ref> Together with Perry Pickhardt and collaborators, the tool was used to track bone mineral density changes in 20,000 subjects.<ref>{{cite news |last1=Pearson |first1=Dave |title=Opportunity emerges for osteoporosis screening via routine CT |url=https://www.healthimaging.com/topics/diagnostic-imaging/osteoporosis-screening-opportunity |access-date=15 June 2019 |work=Health Imaging |date=28 March 2019 |language=en}}</ref><ref>{{cite journal |last1=Jang |first1=Samuel |last2=Graffy |first2=Peter M. |last3=Ziemlewicz |first3=Timothy J. |last4=Lee |first4=Scott J. |last5=Summers |first5=Ronald M. |last6=Pickhardt |first6=Perry J. |title=Opportunistic Osteoporosis Screening at Routine Abdominal and Thoracic CT: Normative L1 Trabecular Attenuation Values in More than 20 000 Adults |journal=Radiology |date=May 2019 |volume=291 |issue=2 |pages=360–367 |doi=10.1148/radiol.2019181648 |pmid=30912719 |pmc=6492986 }}</ref> Summers' lab has also demonstrated the utility of deep learning for performing automated measurement of muscle,<ref>{{cite journal|last1=Burns |first1=Joseph E. |last2=Yao |first2=Jianhua |last3=Chalhoub |first3=Didier |last4=Chen |first4=Joseph J. |last5=Summers |first5=Ronald M. |title=A Machine Learning Algorithm to Estimate Sarcopenia on Abdominal CT |journal=Academic Radiology |pages=311–320 |language=en |doi=10.1016/j.acra.2019.03.011 |date=March 2020|volume=27 |issue=3 |pmid=31126808 |s2cid=164219063 }}</ref> liver fat,<ref>{{cite journal |last1=Graffy |first1=Peter M. |last2=Sandfort |first2=Veit |last3=Summers |first3=Ronald M. |last4=Pickhardt |first4=Perry J. |title=Automated Liver Fat Quantification at Nonenhanced Abdominal CT for Population-based Steatosis Assessment |journal=Radiology |pages=334–342 |language=en |doi=10.1148/radiol.2019190512 |date=November 2019|volume=293 |issue=2 |pmid=31526254 |pmc=6822771 }}</ref> vertebral levels,<ref>{{cite book |last1=Elton |first1=Daniel |last2=Sandfort |first2=Veit |last3=Pickhardt |first3=Perry J. |last4=Summers |first4=Ronald M. |title=Medical Imaging 2020: Computer-Aided Diagnosis |chapter=Accurately identifying vertebral levels in large datasets |editor1-first=Horst K |editor1-last=Hahn |editor2-first=Maciej A |editor2-last=Mazurowski |website=Medical Imaging 2020: Computer-Aided Diagnosis |publisher=SPIE |page=23 |doi=10.1117/12.2551247 |date=16 March 2020|arxiv=2001.10503 |isbn=978-1-5106-3395-7 |s2cid=210932251 }}</ref> and plaque in large datasets.<ref>{{cite journal|last1=Pickhardt |first1=Perry J |last2=Graffy |first2=Peter M |last3=Zea |first3=Ryan |last4=Lee |first4=Scott J |last5=Liu |first5=Jiamin |last6=Sandfort |first6=Veit |last7=Summers |first7=Ronald M |title=Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study |journal=The Lancet Digital Health |pages=e192–e200 |language=en |doi=10.1016/S2589-7500(20)30025-X |date=April 2020|volume=2 |issue=4 |pmid=32864598 |pmc=7454161 |doi-access=free }}</ref> A 2022 paper from Summers' lab published in ''Radiology'' showed how computed tomography (CT) biomarkers are associated with diabetes and pre-diabetes.<ref>{{cite journal |last1=Tallam |first1=Hima |last2=Elton |first2=Daniel C. |last3=Lee |first3=Sungwon |last4=Wakim |first4=Paul |last5=Pickhardt |first5=Perry J. |last6=Summers |first6=Ronald M. |title=Fully Automated Abdominal CT Biomarkers for Type 2 Diabetes Using Deep Learning |journal=Radiology |date=July 2022 |volume=304 |issue=1 |pages=85–95 |doi=10.1148/radiol.211914|pmid=35380492 |pmc=9270681 }}</ref><ref>{{cite news |title=Artificial intelligence may improve diabetes diagnosis |url=https://www.eurekalert.org/news-releases/948056 |access-date=15 February 2023 |work=EurekAlert! |language=en}}</ref> Summers has served as a member of the editorial boards of the journals ''Radiology: Artificial Intelligence'', ''Journal of Medical Imaging'', and ''Academic Radiology'' and is a Fellow of the Society of Abdominal Radiologists and the American Institute for Medical and Biological Engineering (AIMBE).<ref name="NIH"/>

== Awards == {{BLP unreferenced section|date=April 2021}} * Presidential Early Career Award for Scientists and Engineers, 1999 * NIH Director's Award, 2012

== References == {{reflist}}

{{DEFAULTSORT:Summers, Ronald}} Category:Living people Category:National Institutes of Health faculty Category:American radiologists Category:University of Pennsylvania alumni Category:Year of birth missing (living people) Category:University of Michigan people Category:Recipients of the Presidential Early Career Award for Scientists and Engineers