On May 22, 2024, David Dreizin, MD founded the University of Maryland Trauma Radiology Artificial Intelligence Lab (TRAIL) to promote timely, accurate diagnosis for hemorrhage-related injuries in trauma victims using computer vision and machine learning.

Hemorrhage is the leading reversible cause of death after severe trauma. The University of Maryland School of Medicine and the renowned R Adams Cowley Shock Trauma Center (STC) are well-positioned leaders in this area. STC is among the busiest trauma centers worldwide.

Dr. Dreizin has led numerous projects to detect and grade injuries, quantify injury severity, and predict clinical outcomes, with emphasis on explainable approaches and personalized precision diagnostics. Selected works are found below.

He is recently funded through an NIH R01 to develop clinically impactful tools in this area. His lab has created a unique, very large torso trauma CT dataset with outcome data and high-quality voxelwise labeling of multiple hemorrhage-related features.

He is currently seeking research assistants, associates, scholars, and post-doctoral fellows to join TRAIL, with a current major focus on solving detection tasks in unbalanced CT datasets. Candidates with a high level of motivation and technical proficiency on public CT datasets, such as the RSNA CT pulmonary embolus dataset and the MICCAI RibFrac dataset, are particularly well-aligned with current goals.

There is a wealth of opportunity to gain experience developing, implementing, and locally deploying algorithms, and publishing extensively in this domain. The work will be very impactful for the management of victims of severe trauma. This is currently an understudied area, and the unique data provides many unique opportunities.  

If you would like to work at TRAIL and the University of Maryland School of Medicine, please email Dr. Dreizin at ddrezin@som.umaryland.edu  with any questions. Job description postings are forthcoming.

Publications

Relevant prior work (sorted by most recent) includes:

Sarkar N, Kumagai M, Meyr S, Pothapragada S, Unberath M, Li G, Ahmed SR, Smith EB, Davis MA, Khatri GD, Agrawal A, Delproposto ZS, Chen H, Caballero CG, Dreizin D. An ASER AI/ML expert panel formative user research study for an interpretable interactive splenic AAST grading graphical user interface prototype. Emerg Radiol. 2024 Apr;31(2):167-178. doi: 10.1007/s10140-024-02202-8. Epub 2024 Feb 2. PMID: 38302827.

Zhang L, LaBelle W, Unberath M, Chen H, Hu J, Li G, Dreizin D. A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow. Front Med (Lausanne). 2023 Oct 26;10:1241570. doi: 10.3389/fmed.2023.1241570. PMID: 37954555; PMCID: PMC10637622.

Dreizin D, Zhang L, Sarkar N, Bodanapally UK, Li G, Hu J, Chen H, Khedr M, Khetan U, Campbell P, Unberath M. Accelerating voxelwise annotation of cross-sectional imaging through AI collaborative labeling with quality assurance and bias mitigation. Front Radiol. 2023;3:1202412. doi: 10.3389/fradi.2023.1202412. Epub 2023 Jul 11. PMID: 37485306; PMCID: PMC10362988.

Sarkar N, Zhang L, Campbell P, Liang Y, Li G, Khedr M, Khetan U, Dreizin D. Pulmonary contusion: automated deep learning-based quantitative visualization. Emerg Radiol. 2023 Aug;30(4):435-441. doi: 10.1007/s10140-023-02149-2. Epub 2023 Jun 15. PMID: 37318609; PMCID: PMC10527354.

Dreizin D, Staziaki PV, Khatri GD, Beckmann NM, Feng Z, Liang Y, Delproposto ZS, Klug M, Spann JS, Sarkar N, Fu Y. Artificial intelligence CAD tools in trauma imaging: a scoping review from the American Society of Emergency Radiology (ASER) AI/ML Expert Panel. Emerg Radiol. 2023 Jun;30(3):251-265. doi: 10.1007/s10140-023-02120-1. Epub 2023 Mar 14. PMID: 36917287; PMCID: PMC10640925.

Agrawal A, Khatri GD, Khurana B, Sodickson AD, Liang Y, Dreizin D. A survey of ASER members on artificial intelligence in emergency radiology: trends, perceptions, and expectations. Emerg Radiol. 2023 Jun;30(3):267-277. doi: 10.1007/s10140-023-02121-0. Epub 2023 Mar 13. PMID: 36913061; PMCID: PMC10362990.

Chen H, Unberath M, Dreizin D. Toward automated interpretable AAST grading for blunt splenic injury. Emerg Radiol. 2023 Feb;30(1):41-50. doi: 10.1007/s10140-022-02099-1. Epub 2022 Nov 12. PMID: 36371579; PMCID: PMC10314366.

Dreizin D, Nixon B, Hu J, Albert B, Yan C, Yang G, Chen H, Liang Y, Kim N, Jeudy J, Li G, Smith EB, Unberath M. A pilot study of deep learning-based CT volumetry for traumatic hemothorax. Emerg Radiol. 2022 Dec;29(6):995-1002. doi: 10.1007/s10140-022-02087-5. Epub 2022 Aug 16. PMID: 35971025; PMCID: PMC9649862.

Zhou Y, Dreizin D, Wang Y, Liu F, Shen W, Yuille AL. External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation With Limited Data. IEEE Trans Med Imaging. 2022 Jun;41(6):1346-1357. doi: 10.1109/TMI.2021.3139637. Epub 2022 Jun 1. PMID: 34968179; PMCID: PMC9167782.

Zapaishchykova A, Dreizin D, Li Z, Wu JY, Roohi SF, Unberath M. An Interpretable Approach to Automated Severity Scoring in Pelvic Trauma. Med Image Comput Comput Assist Interv. 2021 Sep-Oct;12903:424-433. doi: 10.1007/978-3-030-87199-4_40. Epub 2021 Sep 21. PMID: 37483538; PMCID: PMC10362989.

Dreizin D, Goldmann F, LeBedis C, Boscak A, Dattwyler M, Bodanapally U, Li G, Anderson S, Maier A, Unberath M. An Automated Deep Learning Method for Tile AO/OTA Pelvic Fracture Severity Grading from Trauma whole-Body CT. J Digit Imaging. 2021 Feb;34(1):53-65. doi: 10.1007/s10278-020-00399-x. Epub 2021 Jan 21. PMID: 33479859; PMCID: PMC7886919.

Dreizin D, Chen T, Liang Y, Zhou Y, Paes F, Wang Y, Yuille AL, Roth P, Champ K, Li G, McLenithan A, Morrison JJ. Added value of deep learning-based liver parenchymal CT volumetry for predicting major arterial injury after blunt hepatic trauma: a decision tree analysis. Abdom Radiol (NY). 2021 Jun;46(6):2556-2566. doi: 10.1007/s00261-020-02892-x. Epub 2021 Jan 19. PMID: 33469691; PMCID: PMC8205942.

Dreizin D, Zhou Y, Fu S, Wang Y, Li G, Champ K, Siegel E, Wang Z, Chen T, Yuille AL. A Multiscale Deep Learning Method for Quantitative Visualization of Traumatic Hemoperitoneum at CT: Assessment of Feasibility and Comparison with Subjective Categorical Estimation. Radiol Artif Intell. 2020 Nov 11;2(6):e190220. doi: 10.1148/ryai.2020190220. PMID: 33330848; PMCID: PMC7706875.

Dreizin D, Zhou Y, Chen T, Li G, Yuille AL, McLenithan A, Morrison JJ. Deep learning-based quantitative visualization and measurement of extraperitoneal hematoma volumes in patients with pelvic fractures: Potential role in personalized forecasting and decision support. J Trauma Acute Care Surg. 2020 Mar;88(3):425-433. doi: 10.1097/TA.0000000000002566. PMID: 32107356; PMCID: PMC7830753.

Zhou Y, Dreizin D, Li Y, Zhang Z, Wang Y, Yuille A. Multi-Scale Attentional Network for Multi-Focal Segmentation of Active Bleed after Pelvic Fractures. Mach Learn Med Imaging. 2019 Oct;11861:461-469. doi: 10.1007/978-3-030-32692-0_53. Epub 2019 Oct 10. PMID: 37396112; PMCID: PMC10314367.

Dreizin D, Zhou Y, Zhang Y, Tirada N, Yuille AL. Performance of a Deep Learning Algorithm for Automated Segmentation and Quantification of Traumatic Pelvic Hematomas on CT. J Digit Imaging. 2020 Feb;33(1):243-251. doi: 10.1007/s10278-019-00207-1. PMID: 31172331; PMCID: PMC7064706.

A complete list of Dr. Dreizin’s published works can be found on PubMed (nih.gov)