SHARE:  
mgb-mgh-logo-1200x135.png

Scan Times

An MGH Radiology Research Newsletter

December 2022

As we settle into the holidays, we'd like to take a moment to wish all of you a joyous season and a happy and fruitful new year. We look forward to working with you further in 2023 to help support and promote your research.


For now, we wanted to share with you news from the 2022 annual meeting of the Radiological Society of North America (RSNA). As always, you turned out in force at the meeting. And as always, the research you presented was consistently top-notch. The news you'll see below is only a sample of the many Mass General studies reported in Chicago. Please let us know if we've missed any coverage of your work or any awards or honors you received.


Speaking of RSNA, we are excited to share below a Q&A with the Cardiovascular Imaging Research Center's Michael Lu, MD, MPH and Vineet Raghu, PhD about work they presented at the meeting: “Deep learning to predict 10-year cardiovascular risk from chest radiographs.”


This issue of Scan Times also offers up some of our usual features, including Radiology research updates and select papers by department researchers published last month. And don't miss the two items from the Mass General Research Institute: a roundup of Mass General researchers on Clarivate Analytics’ Highly Cited Researchers List for 2022 - including several Radiology researchers - and a new video feature called Break It Down for Me, in which investigators, in this case, one of our own in the department, explain the typically complex titles of their papers in more lay-friendly terms.


Have a wonderful holiday season, everyone.

Bruce Rosen, Vice-Chair for Research

In This Issue

News from RSNA

Q&A: Using AI to predict the 10-year risk of heart attack and stroke from x-ray images

From the Research Institute

Research Updates

Select Publications from November 2022

NEWS FROM RSNA

RSNA Recognizes Gold Medalists


We are thrilled to report that the society has awarded its highest honor both to radiologist-in-chief James A. Brink, MD and to Katherine Andriole, PhD, director of academic research and education at the Mass General Brigham Data Science Office.

James A. Brink, MD


An internationally known advocate for the monitoring and control of medical radiation exposure, James A. Brink, MD, is chair of the Department of Radiology at Brigham and Women's Hospitals, radiologist-in-chief at Massachusetts General Hospital, chief of enterprise radiology for Mass General Brigham health system, and the Juan M. Taveras Professor of Radiology at Harvard Medical School, all in Boston.


Dr. Brink also focuses on the critical role radiology plays in advancing quality care at an affordable cost. He champions radiologists as poised to use technological innovation toward medical imaging advances that will improve public health.

Katherine P. Andriole, PhD


A leading expert in radiological imaging informatics, Katherine P. Andriole, PhD, holds a long-standing interest in using concepts from computer science, engineering and data science to advance medical research, augment medical education and ultimately improve clinical care.


Dr. Andriole is currently an associate professor of radiology at Harvard Medical School, Brigham and Women's Hospital and the director of academic research and education at the Mass General Brigham Data Science Office.

Dr. Brink hosted the first joint Mass General Brigham Radiology Reception on November 27 during the RSNA meeting. BWH and MGH faculty, trainees, staff and alumni enjoyed the best views of the city from Skydeck Chicago. (Thank you to Carmen Alvarez for the photos, montage and caption information!)

Saving Time, Building Confidence and Expanding Patient Access: How AI-Generated Impressions Can Reliably Improve Reporting Workflows


This Daily Bulletin item from Sunday, November 27 covers work by Parisa Kaviani, MD and colleagues.


Disparities in Cancer Imaging Trends During the COVID-19 Pandemic and Recovery


Another Daily Bulletin item, from Tuesday, November 29, looks at work by Ottavia Zattra, MD, Marc Succi, MD and colleagues.


Mass General Investigators Receive Trainee Research Prizes


Four members of the Mass General Radiology community were awarded Trainee Research Prizes at RSNA2022:


Giridhar Dasegowda, MBBS (Fellow)

Are We Choosing Quantity over Quality? Incidence and Distribution of Poor-Quality Chest Radiographs in A Multinational Imaging Practice Study


Yosef Berlyand, MD (Resident) 

Impact of Iodinated Contrast Allergies on Emergency Department Operations


Parisa Kaviani, MD (Fellow) 

Artificial Intelligence-generated Auto-impression from 9.8-Million Radiology Reports as Training Datasets from Multiple Sites and Imaging Modalities


Sebastian Gallo-Bernal, MD (Medical Student)

COVID-19 and the Impact of Health Inequities in Pediatric Radiology Exam Cancellations 

Q&A: USING AI TO PREDICT THE 10-YEAR RISK OF HEART ATTACK AND STROKE FROM X-RAY IMAGES

On November 29th at RSNA 2022, researchers from the MGH Cardiovascular Imaging Research Center (CIRC) presented their work using AI to predict heart attack and stroke from chest radiograph (x-ray) images. This study was featured in the RSNA daily bulletin and on CNN. We spoke with co-authors Michael Lu, MD, MPH, Co-Director of CIRC and Associate Chair of Imaging Science, and Vineet Raghu, PhD, Instructor of Radiology at Harvard Medical School, about the study.


What motivated the work?

 

Cardiovascular disease, including heart attack and stroke, is the most common cause of death. There are effective tools to prevent cardiovascular disease, including diet, exercise and statin medications. However, cardiovascular prevention is underutilized, and there’s a need for a better way to identify those at highest risk who would see the most benefit. 


In the USA, the 2019 American College of Cardiology/American Heart Association guidelines recommend determining statin eligibility using an online risk calculator called the Pooled Cohort Equations. This calculator requires a lipid panel, blood pressure, smoking information, and history of diabetes/hypertension. This data is often not available in the electronic medical record, which has made it difficult to automate identification of high-risk patients who should be on a statin.


We aimed to address this by developing a tool, deep learning convolutional neural network (CXR-CVD Risk), that predicts the 10-year risk of heart attack and stroke based on existing chest radiograph (x-ray) images. 


What was the most important finding of the study?


Based on the pixels on a chest radiograph image, our CXR-CVD Risk model predicted 10-year risk for cardiovascular events with similar performance to the current clinical standard, the Pooled Cohort Equation risk calculator. 


This is important because chest radiographs are among the most common tests in medicine, especially in older adults. Many people have existing chest radiographs but not the inputs to the Pooled Cohort Equation risk calculator. Opportunistic screening of chest radiographs could identify additional patients who may benefit from statins and ultimately prevent heart attack and stroke.


What was most novel about the study?


Chest radiographs are ordered to make a specific diagnosis, like pneumonia. The underlying idea of our research is that there is additional “hidden” information about aging and cardiovascular risk on the radiograph that can be extracted using AI. By showing a machine learning model hundreds of thousands of chest radiographs, we can train it to predict long-term mortality, biological age, incident lung cancer, postop mortality, and coronary calcium score from chest radiographs and CT. This work is made possible by: (1) availability of large databases of chest radiograph and CT images; and (2) recent advances in machine learning technology.


How does this work fit with the overall mission of the Cardiovascular Imaging Research Center?


The MGH Cardiovascular Imaging Research Center (CIRC) is a joint program between Radiology and Cardiology focused on using imaging to improve cardiovascular health. Much of CIRC’s focus has been on conducting large multicenter clinical trials. Access to these large databases and our trial expertise have helped accelerate our machine learning program. We are excited to apply our first machine learning tools in a clinical trial setting.


-----


Authors on the RSNA abstract are Jakob Weiss, MD, Vineet Raghu, PhD, Kaavya Paruchuri, MD, Pradeep Natarajan, MD, MMSC, Hugo Aerts, PhD, and Michael T. Lu, MD, MPH. The work was supported in part by funding from the National Academy of Medicine and the American Heart Association.

FROM THE RESEARCH INSTITUTE

Radiology Researchers Named to Clarivate Analytics’ Highly Cited Researchers List for 2022


The department researchers below are among those who have "demonstrated significant and broad influence reflected in their publication of multiple highly cited papers over the last decade."


Keith A. Johnson, MD, PhD

Physician Investigator, Gordon Center for Medical Imaging

Professor of Radiology, Harvard Medical School


Matthias Naherndorf, MD, PhD

Investigator, Center for Systems Biology

Professor of Radiology, Harvard Medical School

Richard Moerschner Endowed MGH Research Institute Chair in Men’s Health

Weissman Family MGH Research Scholar 2014-2019


Ralph Weissleder, MD, PhD

Director, Center for Systems Biology

Thrall Family Professor of Radiology, Harvard Medical School

Break It Down for Me: David Izquierdo-Garcia, PhD


The Mass General Research Institute has introduced a fun new video series. Break it Down for Me challenges investigators to break down the complex titles of their papers and present them in simple and relatable terms for the audience.


The first to take up the challenge was the Martinos Center's David Izquierdo-Garcia, PhD, who broke down the title of his paper "Detection and Characterization of Thrombosis in Humans Using Fibrin-Targeted Positron Emission Tomography and Magnetic Resonance." See how he did below!

RESEARCH UPDATES

FDG PET/CT Imaging for Stroke Risk Stratification in Patients without Atrial Fibrillation


Shady Abohashem, MD, a researcher in the Cardiovascular Imaging Research Center in the Department of Radiology at Massachusetts General Hospital, discusses the potential of FDG imaging with PET/CT for stroke risk stratification in patients without atrial fibrilation.


Mass General Develops an Open-Source, Low-Cost, Wearable Cerebral Oximeter


Kuan-Cheng (Tony) Wu, Marco Renna, PhD, Maria Angela Franceschini, PhD and others at Massachusetts General Hospital have developed and built a low-cost, wireless, and wearable cerebral oximeter that can track individual cerebral health and is also suitable for use at the community level and in telehealth visits.


Fast fMRI Detects Specific Cascade of Thalamic Activity at Transitions in Behavioral Arousal State


The Martinos Center's Laura Lewis, PhD and colleagues used fast functional MRI to map the specific cascade of neural activity during the transition from sleep to wakefulness, shedding light on this central but poorly understood aspect of human consciousness.


Review: A New Science of Emotion and Its Implications for Functional Neurological Disorder


David L. Perez, MD, MMSc, Lisa Feldman Barrett, PhD, and colleagues recently reviewed the theory of constructed emotion and posit that deficits in the brain's predictive process of constructing emotion categories are integral to the pathogenesis of functional neurological disorder.

SELECT PAPERS FROM NOVEMBER 2022

1: Almansour H, O'Shea A, England RW, Afat S, Nikolaou K, Othman AE. Fellowship Training: Navigating the Decision to Be a Generalist or a Subspecialist-Radiology In Training. Radiology. 2022 Nov;305(2):E63-E65. doi: 10.1148/radiol.220422. Epub 2022 Jul 12. PMID: 35819323.



2: Bonkhoff AK, Schirmer MD, Bretzner M, Hong S, Regenhardt RW, Donahue KL, Nardin MJ, Dalca AV, Giese AK, Etherton MR, Hancock BL, Mocking SJT, McIntosh EC, Attia J, Cole JW, Donatti A, Griessenauer CJ, Heitsch L, Holmegaard L, Jood K, Jimenez-Conde J, Kittner SJ, Lemmens R, Levi CR, McDonough CW, Meschia JF, Phuah CL, Ropele S, Rosand J, Roquer J, Rundek T, Sacco RL, Schmidt R, Sharma P, Slowik A, Sousa A, Stanne TM, Strbian D, Tatlisumak T, Thijs V, Vagal A, Wasselius J, Woo D, Zand R, McArdle PF, Worrall BB, Jern C, Lindgren AG, Maguire J, Wu O, Rost NS; MRI-GENIE and GISCOME Investigators and the International Stroke Genetics Consortium. The relevance of rich club regions for functional outcome post-stroke is enhanced in women. Hum Brain Mapp. 2022 Nov 28. doi: 10.1002/hbm.26159. Epub ahead of print. PMID: 36440953.



3: Calixto C, Machado-Rivas F, Karimi D, Cortes-Albornoz MC, Acosta-Buitrago LM, Gallo-Bernal S, Afacan O, Warfield SK, Gholipour A, Jaimes C. Detailed anatomic segmentations of a fetal brain diffusion tensor imaging atlas between 23 and 30 weeks of gestation. Hum Brain Mapp. 2022 Nov 24. doi: 10.1002/hbm.26160. Epub ahead of print. PMID: 36421003.



4: Chen J, Frey EC, He Y, Segars WP, Li Y, Du Y. TransMorph: Transformer for unsupervised medical image registration. Med Image Anal. 2022 Nov;82:102615. doi: 10.1016/j.media.2022.102615. Epub 2022 Sep 14. PMID: 36156420.



5: Collins MA, Ji JL, Chung Y, Lympus CA, Afriyie-Agyemang Y, Addington JM, Goodyear BG, Bearden CE, Cadenhead KS, Mirzakhanian H, Tsuang MT, Cornblatt BA, Carrión RE, Keshavan M, Stone WS, Mathalon DH, Perkins DO, Walker EF, Woods SW, Powers AR, Anticevic A, Cannon TD. Accelerated cortical thinning precedes and predicts conversion to psychosis: The NAPLS3 longitudinal study of youth at clinical high-risk. Mol Psychiatry. 2022 Nov 25. doi: 10.1038/s41380-022-01870-7. Epub ahead of print. PMID: 36434057.



6: Cury RC, Leipsic J, Abbara S, Achenbach S, Berman D, Bittencourt M, Budoff M, Chinnaiyan K, Choi AD, Ghoshhajra B, Jacobs J, Koweek L, Lesser J, Maroules C, Rubin GD, Rybicki FJ, Shaw LJ, Williams MC, Williamson E, White CS, Villines TC, Blankstein R. CAD-RADS™ 2.0 - 2022 Coronary Artery Disease-Reporting and Data System: An Expert Consensus Document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Cardiology (ACC), the American College of Radiology (ACR), and the North America Society of Cardiovascular Imaging (NASCI). JACC Cardiovasc Imaging. 2022 Nov;15(11):1974-2001. doi: 10.1016/j.jcmg.2022.07.002. Epub 2022 Sep 14. PMID: 36115815.



7: Dincer A, Chen CD, McKay NS, Koenig LN, McCullough A, Flores S, Keefe SJ, Schultz SA, Feldman RL, Joseph-Mathurin N, Hornbeck RC, Cruchaga C, Schindler SE, Holtzman DM, Morris JC, Fagan AM, Benzinger TLS, Gordon BA. APOE ε4 genotype, amyloid-β, and sex interact to predict tau in regions of high APOE mRNA expression. Sci Transl Med. 2022 Nov 16;14(671):eabl7646. doi: 10.1126/scitranslmed.abl7646. Epub 2022 Nov 16. PMID: 36383681.



8: Evans SB, Blitzblau RC, Chapman CH, Chollet-Lipscomb C, Deville C, Ford E, Gibbs IC, Howell K, Peters GW, Ponce SB, Seldon C, Spector-Bagdady K, Tarbell N, Terezakis S, Vyfhius MAL, Wright J, Zietman A, Jagsi R. Restricted Access to Abortion, the Dobbs Ruling, and Radiation Oncology: Standing United Against Reproductive Injustice. Int J Radiat Oncol Biol Phys. 2022 Nov 1;114(3):385-389. doi: 10.1016/j.ijrobp.2022.07.1843. Epub 2022 Aug 10. PMID: 35963470.



9: Ferencik M. Is Coronary Plaque Quantification More Important Than Stenosis Detection in Patients With Acute Coronary Syndrome? JACC Cardiovasc Imaging. 2022 Nov;15(11):1926-1928. doi: 10.1016/j.jcmg.2022.05.014. Epub 2022 Aug 17. PMID: 36357134.



10: Fetzer DT, Rosado-Mendez IM, Wang M, Robbin ML, Ozturk A, Wear KA, Ormachea J, Stiles TA, Fowlkes JB, Hall TJ, Samir AE. Pulse-Echo Quantitative US Biomarkers for Liver Steatosis: Toward Technical Standardization. Radiology. 2022 Nov;305(2):265-276. doi: 10.1148/radiol.212808. Epub 2022 Sep 13. PMID: 36098640; PMCID: PMC9613608.



11: Hossbach J, Splitthoff DN, Cauley S, Clifford B, Polak D, Lo WC, Meyer H, Maier A. Deep learning-based motion quantification from k-space for fast model- based MRI motion correction. Med Phys. 2022 Nov 26. doi: 10.1002/mp.16119. Epub ahead of print. PMID: 36433748.



12: Howard AF, Cottaar M, Drakesmith M, Fan Q, Huang SY, Jones DK, Lange FJ, Mollink J, Rudrapatna SU, Tian Q, Miller KL, Jbabdi S. Estimating axial diffusivity in the NODDI model. Neuroimage. 2022 Nov 15;262:119535. doi: 10.1016/j.neuroimage.2022.119535. Epub 2022 Aug 2. PMID: 35931306.



13: Iglesias JE, Schleicher R, Laguna S, Billot B, Schaefer P, McKaig B, Goldstein JN, Sheth KN, Rosen MS, Kimberly WT. Quantitative Brain Morphometry of Portable Low-Field-Strength MRI Using Super-Resolution Machine Learning. Radiology. 2022 Nov 8:220522. doi: 10.1148/radiol.220522. Epub ahead of print. PMID: 36346311.



14: Kim E, Deng F, Trofimova A. Thank You from the Radiology In Training Editors to Their Mentors. Radiology. 2022 Nov;305(2):292-293. doi: 10.1148/radiol.221386. Epub 2022 Jul 19. PMID: 35852427.



15: Lee SI, Kang SK. MRI Improves the Characterization of Incidental Adnexal Masses Detected at Sonography. Radiology. 2022 Nov 22:222866. doi: 10.1148/radiol.222866. Epub ahead of print. PMID: 36413134.



16: Lennartz S, Li P, Consul N, Lee SI. 2022 Top Images in Radiology: Radiology In Training Editors' Choices. Radiology. 2022 Nov 29:229031. doi: 10.1148/radiol.229031. Epub ahead of print. PMID: 36445227.



17: Liu G, Ni C, Zhan J, Li W, Luo J, Liao Z, Locascio JJ, Xian W, Chen L, Pei Z, Corvol JC, Maple-Grødem J, Campbell MC, Elbaz A, Lesage S, Brice A, Hung AY, Schwarzschild MA, Hayes MT, Wills AM, Ravina B, Shoulson I, Taba P, Kõks S, Beach TG, Cormier-Dequaire F, Alves G, Tysnes OB, Perlmutter JS, Heutink P, van Hilten JJ, Barker RA, Williams-Gray CH, Scherzer CR; International Genetics of Parkinson Disease Progression (IGPP) Consortium. Mitochondrial haplogroups and cognitive progression in Parkinson's disease. Brain. 2022 Nov 8:awac327. doi: 10.1093/brain/awac327. Epub ahead of print. PMID: 36343661.



18: Liu X, Marin T, Amal T, Woo J, Fakhri GE, Ouyang J. Posterior estimation using deep learning: a simulation study of compartmental modeling in dynamic positron emission tomography. Med Phys. 2022 Nov 4. doi: 10.1002/mp.16078. Epub ahead of print. PMID: 36331429.



19: Pinho Meneses B, Stockmann JP, Arango N, Gapais PF, Giacomini E, Mauconduit F, Gras V, Boulant N, Vignaud A, Luong M, Amadon A. Shim coils tailored for correcting B0 inhomogeneity in the human brain (SCOTCH): Design methodology and 48-channel prototype assessment in 7-Tesla MRI. Neuroimage. 2022 Nov 1;261:119498. doi: 10.1016/j.neuroimage.2022.119498. Epub 2022 Jul 30. PMID: 35917918.



20: Price J. 2022 SNMMI Highlights Lecture: Neuroscience. J Nucl Med. 2022 Nov;63(11):15N-22N. PMID: 36319112.



21: Qian DC, Ulrich BC, Peng G, Zhao H, Conneely KN, Miller AH, Bruner DW, Eldridge RC, Wommack EC, Higgins KA, Shin DM, Saba NF, Smith AK, Burtness B, Park HS, Stokes WA, Beitler JJ, Xiao C. Outcomes stratification of head and neck cancer using pre- and post-treatment DNA methylation from peripheral blood. Int J Radiat Oncol Biol Phys. 2022 Nov 18:S0360-3016(22)03521-0. doi: 10.1016/j.ijrobp.2022.11.009. Epub ahead of print. PMID: 36410685.



22: Quinaglia T, Gongora C, Awadalla M, Hassan MZO, Zafar A, Drobni ZD, Mahmood SS, Zhang L, Coelho-Filho OR, Suero-Abreu GA, Rizvi MA, Sahni G, Mandawat A, Zatarain-Nicolás E, Mahmoudi M, Sullivan R, Ganatra S, Heinzerling LM, Thuny F, Ederhy S, Gilman HK, Sama S, Nikolaidou S, Mansilla AG, Calles A, Cabral M, Fernández-Avilés F, Gavira JJ, González NS, García de Yébenes Castro M, Barac A, Afilalo J, Zlotoff DA, Zubiri L, Reynolds KL, Devereux R, Hung J, Picard MH, Yang EH, Gupta D, Michel C, Lyon AR, Chen CL, Nohria A, Fradley MG, Thavendiranathan P, Neilan TG. Global Circumferential and Radial Strain Among Patients With Immune Checkpoint Inhibitor Myocarditis. JACC Cardiovasc Imaging. 2022 Nov;15(11):1883-1896. doi: 10.1016/j.jcmg.2022.06.014. Epub 2022 Sep 14. PMID: 36357131.



23: Schwamm LH, Kamel H, Granger CB, Piccini JP, Katz JM, Sethi PP, Sidorov EV, Kasner SE, Silverman SB, Merriam TT, Franco N, Ziegler PD, Bernstein RA; STROKE AF Investigators. Predictors of Atrial Fibrillation in Patients With Stroke Attributed to Large- or Small-Vessel Disease: A Prespecified Secondary Analysis of the STROKE AF Randomized Clinical Trial. JAMA Neurol. 2022 Nov 14:e224038. doi: 10.1001/jamaneurol.2022.4038. Epub ahead of print. PMID: 36374508; PMCID: PMC9664367.



24: Shams S, Prokopiou P, Esmaelbeigi A, Mitsis GD, Chen JJ. Modeling the dynamics of cerebrovascular reactivity to carbon dioxide in fMRI under task and resting-state conditions. Neuroimage. 2022 Nov 25;265:119758. doi: 10.1016/j.neuroimage.2022.119758. Epub ahead of print. PMID: 36442732.



25: Strain JF, Brier MR, Tanenbaum A, Gordon BA, McCarthy JE, Dincer A, Marcus DS, Chhatwal JP, Graff-Radford NR, Day GS, la Fougère C, Perrin RJ, Salloway S, Schofield PR, Yakushev I, Ikeuchi T, Vöglein J, Morris JC, Benzinger TLS, Bateman RJ, Ances BM, Snyder AZ; Dominantly Inherited Alzheimer Network. Covariance-based vs. correlation-based functional connectivity dissociates healthy aging from Alzheimer disease. Neuroimage. 2022 Nov 1;261:119511. doi: 10.1016/j.neuroimage.2022.119511. Epub 2022 Jul 30. PMID: 35914670.



26: Strom JB, Zhao Y, Shen C, Wasfy JH, Xu J, Yucel E, Tanguturi V, Hyland PM, Markson LJ, Kazi DS, Cui J, Hung J, Yeh RW, Manning WJ. Development and validation of an echocardiographic algorithm to predict long-term mitral and tricuspid regurgitation progression. Eur Heart J Cardiovasc Imaging. 2022 Nov 17;23(12):1606-1616. doi: 10.1093/ehjci/jeab254. PMID: 34849685.



27: Tootell RBH, Nasiriavanaki Z, Babadi B, Greve DN, Nasr S, Holt DJ. Interdigitated Columnar Representation of Personal Space and Visual Space in Human Parietal Cortex. J Neurosci. 2022 Nov 30;42(48):9011-9029. doi: 10.1523/JNEUROSCI.0516-22.2022. Epub 2022 Oct 5. PMID: 36198501.



28: Wu J, Li J, Eickhoff SB, Hoffstaedter F, Hanke M, Yeo BTT, Genon S. Cross- cohort replicability and generalizability of connectivity-based psychometric prediction patterns. Neuroimage. 2022 Nov 15;262:119569. doi: 10.1016/j.neuroimage.2022.119569. Epub 2022 Aug 17. PMID: 35985618; PMCID: PMC9611632.