1
|
Chatterjee N, Duda J, Gee J, Elahi A, Martin K, Doan V, Liu H, Maclean M, Rader D, Borthakur A, Kahn C, Sagreiya H, Witschey W. A Cloud-Based System for Automated AI Image Analysis and Reporting. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01200-z. [PMID: 39085717 DOI: 10.1007/s10278-024-01200-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/08/2024] [Revised: 06/01/2024] [Accepted: 07/05/2024] [Indexed: 08/02/2024]
Abstract
Although numerous AI algorithms have been published, the relatively small number of algorithms used clinically is partly due to the difficulty of implementing AI seamlessly into the clinical workflow for radiologists and for their healthcare enterprise. The authors developed an AI orchestrator to facilitate the deployment and use of AI tools in a large multi-site university healthcare system and used it to conduct opportunistic screening for hepatic steatosis. During the 60-day study period, 991 abdominal CTs were processed at multiple different physical locations with an average turnaround time of 2.8 min. Quality control images and AI results were fully integrated into the existing clinical workflow. All input into and output from the server was in standardized data formats. The authors describe the methodology in detail; this framework can be adapted to integrate any clinical AI algorithm.
Collapse
Affiliation(s)
- Neil Chatterjee
- Department of Radiology, University of Pennsylvania, Philadelphia, USA.
- Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, USA.
| | - Jeffrey Duda
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - James Gee
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
- Perlman School of Medicine, University of Pennsylvania, Philadelphia, USA
| | - Ameena Elahi
- Department of Information Services, University of Pennsylvania, Philadelphia, USA
| | - Kristen Martin
- Department of Information Services, University of Pennsylvania, Philadelphia, USA
| | - Van Doan
- Department of Information Services, University of Pennsylvania, Philadelphia, USA
| | - Hannah Liu
- Department of Bioengineering, University of Pennsylvania, Philadelphia, USA
| | - Matthew Maclean
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Daniel Rader
- Department of Medicine, University of Pennsylvania, Philadelphia, USA
| | - Arijitt Borthakur
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Charles Kahn
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
- Perlman School of Medicine, University of Pennsylvania, Philadelphia, USA
| | - Hersh Sagreiya
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
- Perlman School of Medicine, University of Pennsylvania, Philadelphia, USA
| | - Walter Witschey
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
- Perlman School of Medicine, University of Pennsylvania, Philadelphia, USA
| |
Collapse
|
2
|
Huebbe P, Bilke S, Rueter J, Schloesser A, Campbel G, Glüer CC, Lucius R, Röcken C, Tholey A, Rimbach G. Human APOE4 Protects High-Fat and High-Sucrose Diet Fed Targeted Replacement Mice against Fatty Liver Disease Compared to APOE3. Aging Dis 2024; 15:259-281. [PMID: 37450924 PMCID: PMC10796091 DOI: 10.14336/ad.2023.0530] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Accepted: 05/30/2023] [Indexed: 07/18/2023] Open
Abstract
Recent genome- and exome-wide association studies suggest that the human APOE ε4 allele protects against non-alcoholic fatty liver disease (NAFLD), while ε3 promotes hepatic steatosis and steatohepatitis. The present study aimed at examining the APOE genotype-dependent development of fatty liver disease and its underlying mechanisms in a targeted replacement mouse model. Male mice expressing the human APOE3 or APOE4 protein isoforms on a C57BL/6J background and unmodified C57BL/6J mice were chronically fed a high-fat and high-sucrose diet to induce obesity. After 7 months, body weight gain was more pronounced in human APOE than endogenous APOE expressing mice with elevated plasma biomarkers suggesting aggravated metabolic dysfunction. APOE3 mice exhibited the highest liver weights and, compared to APOE4, massive hepatic steatosis. An untargeted quantitative proteome analysis of the liver identified a high number of proteins differentially abundant in APOE3 versus APOE4 mice. The majority of the higher abundant proteins in APOE3 mice could be grouped to inflammation and damage-associated response, and lipid storage, amongst others. Results of the targeted qRT-PCR and Western blot analyses contribute to the overall finding that APOE3 as opposed to APOE4 promotes hepatic steatosis, inflammatory- and damage-associated response signaling and fibrosis in the liver of obese mice. Our experimental data substantiate the observation of an increased NAFLD-risk associated with the human APOEε3 allele, while APOEε4 appears protective. The underlying mechanisms of the protection possibly involve a higher capacity of nonectopic lipid deposition in subcutaneous adipose tissue and lower hepatic pathogen recognition in the APOE4 mice.
Collapse
Affiliation(s)
- Patricia Huebbe
- Institute of Human Nutrition and Food Science, Kiel University, D-24118 Kiel, Germany.
| | - Stephanie Bilke
- Institute of Experimental Medicine, Proteomics & Bioanalytics, Kiel University, D-24105 Kiel, Germany.
| | - Johanna Rueter
- Institute of Human Nutrition and Food Science, Kiel University, D-24118 Kiel, Germany.
| | - Anke Schloesser
- Institute of Human Nutrition and Food Science, Kiel University, D-24118 Kiel, Germany.
| | - Graeme Campbel
- Section Biomedical Imaging, Department of Radiology and Neuroradiology, Kiel University, D-24118 Kiel, Germany.
| | - Claus-C. Glüer
- Section Biomedical Imaging, Department of Radiology and Neuroradiology, Kiel University, D-24118 Kiel, Germany.
| | - Ralph Lucius
- Anatomical Institute, Kiel University, D-24118 Kiel, Germany.
| | - Christoph Röcken
- Department of Pathology, Kiel University and University Hospital Schleswig-Holstein, Campus Kiel, D-24105 Kiel, Germany.
| | - Andreas Tholey
- Institute of Experimental Medicine, Proteomics & Bioanalytics, Kiel University, D-24105 Kiel, Germany.
| | - Gerald Rimbach
- Institute of Human Nutrition and Food Science, Kiel University, D-24118 Kiel, Germany.
| |
Collapse
|
3
|
Qadri S, Yki-Järvinen H. The quest for the missing links in fatty liver genetics: Deep learning to the rescue! Cell Rep Med 2022; 3:100862. [PMID: 36543096 PMCID: PMC9798017 DOI: 10.1016/j.xcrm.2022.100862] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
Park, MacLean, et al. conduct an exome-wide association study of liver fat content in the Penn Medicine BioBank.1 By leveraging machine learning-assisted analysis of clinical CT scans to quantify steatosis, they uncover previously undescribed liver fat-associated genetic variants.
Collapse
Affiliation(s)
- Sami Qadri
- University of Helsinki and Helsinki University Hospital, Helsinki, Finland,Minerva Foundation Institute for Medical Research, Helsinki, Finland
| | - Hannele Yki-Järvinen
- University of Helsinki and Helsinki University Hospital, Helsinki, Finland,Minerva Foundation Institute for Medical Research, Helsinki, Finland,Corresponding author
| |
Collapse
|