1
|
MacLean MT, Jehangir Q, Vujkovic M, Ko YA, Litt H, Borthakur A, Sagreiya H, Rosen M, Mankoff DA, Schnall MD, Shou H, Chirinos J, Damrauer SM, Torigian DA, Carr R, Rader DJ, Witschey WR. Quantification of abdominal fat from computed tomography using deep learning and its association with electronic health records in an academic biobank. J Am Med Inform Assoc 2021; 28:1178-1187. [PMID: 33576413 DOI: 10.1093/jamia/ocaa342] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2020] [Revised: 11/30/2020] [Accepted: 01/06/2021] [Indexed: 11/14/2022] Open
Abstract
OBJECTIVE The objective was to develop a fully automated algorithm for abdominal fat segmentation and to deploy this method at scale in an academic biobank. MATERIALS AND METHODS We built a fully automated image curation and labeling technique using deep learning and distributive computing to identify subcutaneous and visceral abdominal fat compartments from 52,844 computed tomography scans in 13,502 patients in the Penn Medicine Biobank (PMBB). A classification network identified the inferior and superior borders of the abdomen, and a segmentation network differentiated visceral and subcutaneous fat. Following technical evaluation of our method, we conducted studies to validate known relationships with visceral and subcutaneous fat. RESULTS When compared with 100 manually annotated cases, the classification network was on average within one 5-mm slice for both the superior (0.4 ± 1.1 slice) and inferior (0.4 ± 0.6 slice) borders. The segmentation network also demonstrated excellent performance with intraclass correlation coefficients of 1.00 (P < 2 × 10-16) for subcutaneous and 1.00 (P < 2 × 10-16) for visceral fat on 100 testing cases. We performed integrative analyses of abdominal fat with the phenome extracted from the electronic health record and found highly significant associations with diabetes mellitus, hypertension, and renal failure, among other phenotypes. CONCLUSIONS This work presents a fully automated and highly accurate method for the quantification of abdominal fat that can be applied to routine clinical imaging studies to fuel translational scientific discovery.
Collapse
Affiliation(s)
- Matthew T MacLean
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.,Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Qasim Jehangir
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Marijana Vujkovic
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Yi-An Ko
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Harold Litt
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Arijitt Borthakur
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Hersh Sagreiya
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Mark Rosen
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - David A Mankoff
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Mitchell D Schnall
- Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Haochang Shou
- Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Julio Chirinos
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Scott M Damrauer
- Department of Surgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Drew A Torigian
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Rotonya Carr
- Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Daniel J Rader
- Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.,Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Walter R Witschey
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| |
Collapse
|
2
|
Pendergrass SA, Crawford DC. Using Electronic Health Records To Generate Phenotypes For Research. CURRENT PROTOCOLS IN HUMAN GENETICS 2019; 100:e80. [PMID: 30516347 PMCID: PMC6318047 DOI: 10.1002/cphg.80] [Citation(s) in RCA: 35] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
Electronic health records contain patient-level data collected during and for clinical care. Data within the electronic health record include diagnostic billing codes, procedure codes, vital signs, laboratory test results, clinical imaging, and physician notes. With repeated clinic visits, these data are longitudinal, providing important information on disease development, progression, and response to treatment or intervention strategies. The near universal adoption of electronic health records nationally has the potential to provide population-scale real-world clinical data accessible for biomedical research, including genetic association studies. For this research potential to be realized, high-quality research-grade variables must be extracted from these clinical data warehouses. We describe here common and emerging electronic phenotyping approaches applied to electronic health records, as well as current limitations of both the approaches and the biases associated with these clinically collected data that impact their use in research. © 2018 by John Wiley & Sons, Inc.
Collapse
Affiliation(s)
- Sarah A. Pendergrass
- Biomedical and Translational Informatics Institute,
Geisinger Research, Rockville MD
| | - Dana C. Crawford
- Institute for Computational Biology, Department of
Population and Quantitative Health Sciences, Case Western Reserve University,
Cleveland, OH
| |
Collapse
|