Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Nov;6(6):e240101.
doi: 10.1148/ryai.240101.

The RSNA Abdominal Traumatic Injury CT (RATIC) Dataset

Collaborators, Affiliations

The RSNA Abdominal Traumatic Injury CT (RATIC) Dataset

Jeffrey D Rudie et al. Radiol Artif Intell. 2024 Nov.

Abstract

Supplemental material is available for this article.

Keywords: CT; Kidney; Large Bowel; Liver; Small Bowel; Spleen; Trauma.

PubMed Disclaimer

Conflict of interest statement

Disclosures of conflicts of interest: J.D.R. Consulting fees from Cortechs.ai; payment from Sutton Pierce for expert testimony; member of the Radiological Society of North America (RSNA) AI Committee; associate editor for Radiology: Artificial Intelligence; Radiology: Artificial Intelligence trainee editorial board alum; stock or stock options in Cortechs.ai and Subtle Medical. H.M.L. No relevant relationships. R.L.B. Support for present manuscript from the RSNA; consulting fees from the RSNA; leadership or fiduciary role in the RSNA AI Committee and the American Statistical Association Statistical Consulting Section. S.J. No relevant relationships. L.M.P. RSNA AI Committee member; associate editor for Radiology: Artificial Intelligence. S.N. University of British Columbia Health Innovation Funding Investment Award and the Canadian Institutes for Health Research Pandemic Preparedness and Health Emergencies Research Priority Grant; royalties from FRCPC; consulting fees from Siemens and Amgen. B.S.M. No relevant relationships. A.E.F. Grants or contracts from the Medical Imaging and Data Resource Center; member of the RSNA board of directors. K.M. Mentor for RSNA 2024 Medical Student Grant to Miriam Chisholm (award: $3000, paid to author’s institution); principal investigator for RSNA Research Scholar Grant, 2022 to present (award: $150 000, paid to author’s institution); principal investigator for Duke Center of Artificial Intelligence in Radiology: SPARK award, 2021–2022 (award: 50% research technician support for 1 year, paid to author’s institution); support for attending meetings and/or travel from the Society of Abdominal Radiology DEI Professional Development Award, the American Association for Women in Radiology Dr. Shaffer RLI Leadership Summit Award, the North Carolina Radiological Society RLI Summit Stipend Award, the American Association for Women in Radiology: AAMC Leadership Seminar Award, and the Society of Abdominal Radiology: Travel Scholarship for Trainees; patent for “Methods for non-invasive cancer identification, classification, and grading: machine Learning models using mixed exam-, region-, and voxel-wise supervision” (patent no. US20230410301A1, filed November 5, 2021, and issued December 21, 2023); associate editor for Radiology: Artificial Intelligence; advisory panel member for Radiology: Artificial Intelligence trainee editorial board; co-chair of the RSNA Radiology Reimagined: AI, Innovation and Interoperability in Practice Demonstration; co-chair of the Society of Abdominal Radiology Informatics committee; Radiology: Artificial Intelligence trainee editorial board alum. G.S. Member of the MD.ai board of directors and the Society for Imaging Informatics in Medicine (SIIM) board of directors; shareholder in MD.ai. M.A.D. No relevant relationships. J.M. Grants or contracts from Siemens, paid to author’s institution; royalties from GE, made via author’s institution; payment from Gibson Dunn for expert testimony, (patent litigation expert witness); support for attending meetings from RSNA; chair of the RSNA AI Committee; stock or stock options in Annexon Biosciences; associate editor for Radiology: Artificial Intelligence. P.D.C. Grants or contracts from Novocure; consulting fees from Canon Medical Bayer; stock or stock options in Avicenna.ai (co-founder). F.H.B. No relevant relationships. S.H. No relevant relationships. M.L. No relevant relationships. T.R. No relevant relationships. J.P.G. Grants or contracts from the Interdisciplinary Center of Clinical Research Würzburg (Z-3BC/02); speaker honoraria from Siemens Healthineers. A.S.K. No relevant relationships. S.M. No relevant relationships. S.G.S. No relevant relationships. A.D.C. No relevant relationships. S.A. No relevant relationships. C.C.K. Consulting fees from Everfortune.AI. L.A. No relevant relationships. A.V.C. No relevant relationships. A.S. No relevant relationships. F.A.S.T. No relevant relationships. A.J. No relevant relationships. L.K.B. No relevant relationships. M. Brassil No relevant relationships. A.E.H. No relevant relationships. H.D. No relevant relationships. M. Becircic No relevant relationships. A.G.B. No relevant relationships. E.M.J.d.M.F. Consulting fees from MD.ai; speaker payment or honoraria from Sharing Progress in Cancer Care; member of the SIIM subcommittee for ML Education; Radiology: Artificial Intelligence trainee editorial board member. E.C. No relevant relationships.

Figures

Summary of the data curation and annotation process. * = bowel and
mesenteric injuries were reviewed by two annotators. DICOM = Digital Imaging and
Communications in Medicine.
Figure 1:
Summary of the data curation and annotation process. * = bowel and mesenteric injuries were reviewed by two annotators. DICOM = Digital Imaging and Communications in Medicine.
Example of abdominal organ segmentation, with each color representing
different organs. (A) Axial CT DICOM image demonstrates a splenic laceration
(arrow). (B) Image illustrates the segmentations for the liver (red), spleen
(green), left kidney (blue), and gastrointestinal tract (brown) in the axial
plane. (C) Image shows segmentation masks overlaying the corresponding CT image.
(D) Image shows segmentation masks overlaying the corresponding organs on a
reconstructed coronal CT DICOM image. DICOM = Digital Imaging and Communications
in Medicine.
Figure 2:
Example of abdominal organ segmentation, with each color representing different organs. (A) Axial CT DICOM image demonstrates a splenic laceration (arrow). (B) Image illustrates the segmentations for the liver (red), spleen (green), left kidney (blue), and gastrointestinal tract (brown) in the axial plane. (C) Image shows segmentation masks overlaying the corresponding CT image. (D) Image shows segmentation masks overlaying the corresponding organs on a reconstructed coronal CT DICOM image. DICOM = Digital Imaging and Communications in Medicine.

References

    1. Wiik Larsen J , Søreide K , Søreide JA , Tjosevik K , Kvaløy JT , Thorsen K . Epidemiology of abdominal trauma: An age- and sex-adjusted incidence analysis with mortality patterns . Injury 2022. ; 53 ( 10 ): 3130 – 3138 . - PubMed
    1. Soto JA , Anderson SW . Multidetector CT of blunt abdominal trauma . Radiology 2012. ; 265 ( 3 ): 678 – 693 . - PubMed
    1. Federle MP , Goldberg HI , Kaiser JA , Moss AA , Jeffrey RB Jr , Mall JC . Evaluation of abdominal trauma by computed tomography . Radiology 1981. ; 138 ( 3 ): 637 – 644 . - PubMed
    1. Kozar RA , Crandall M , Shanmuganathan K , et al. . Organ injury scaling 2018 update: Spleen, liver, and kidney . J Trauma Acute Care Surg 2018. ; 85 ( 6 ): 1119 – 1122 . - PubMed
    1. Dixe de Oliveira Santo I , Sailer A , Solomon N , et al. . Grading abdominal trauma: changes in and implications of the revised 2018 AAST-OIS for the Spleen, Liver, and Kidney . RadioGraphics 2023. ; 43 ( 9 ): e230040 . - PubMed

Publication types