Abstract
Preparing radiology examinations for interpretation requires prefetching relevant prior examinations and implementing hanging protocols to optimally display the examination along with comparisons. Body part is a critical piece of information to facilitate both prefetching and hanging protocols, but body part information encoded using the Digital Imaging and Communications in Medicine (DICOM) standard is widely variable, error-prone, not granular enough, or missing altogether. This results in inappropriate examinations being prefetched or relevant examinations left behind; hanging protocol optimization suffers as well. Modern artificial intelligence (AI) techniques, particularly when harnessing federated deep learning techniques, allow for highly accurate automatic detection of body part based on the image data within a radiological examination; this allows for much more reliable implementation of this categorization and workflow. Additionally, new avenues to further optimize examination viewing such as dynamic hanging protocol and image display can be implemented using these techniques.
Similar content being viewed by others
Availability of Data and Material
The source data contains PHI and is not available for public consumption.
Code Availability
The underlying model has been submitted to the 2021 SIIM Annual Meeting for evaluation. If it is made publicly available, we will be happy to support that.
References
Moise A, Atkins MS. Workflow oriented hanging protocols for radiology workstation. Proc SPIE. 2002 (4685):189−99.
Richardson ML, Garwood ER, Lee Y, Li MD, Lo HS, Nagaraju A, Nguyen XV, Probyn L, Rajiah P, Sin J, Wasnik AP, Xu K. Noninterpretive uses of artificial intelligence in radiology. Acad Radiol. 2020: in press.
Lakhani P, Prater AB, Hutson RK, Andriole KP, Dreyer KJ, Morey J, Prevedello LM, Clark TJ, Geis JR, Itri JN, Hawkins CM. Machine learning in radiology: applications beyond image interpretation. J Am Coll Radiol. 2018 15:350−9.
Talati IA, Krishnan P, Filice RW. Developing deeper radiology exam insight to optimize MRI workflow and patient experience. J Digit Imaging. 2019 Jan;32:865−9.
Kahn CE, Carrino JA, Flynn MJ, Peck DJ, Horii SC. DICOM and radiology: past, present, and future. J Am Coll Radiol. 2007.
Gueld MO, Kohnen M, Keysers D, Schubert H, Wein BB, Bredno J, Lehmann TM. Quality of DICOM header information for image categorization. Proc SPIE. 2002 (4685):280−7.
Towbin AJ, Roth CJ, Petersilge CA, Garriott K, Buckwalter KA, Clunie DA. The importance of body part labeling to enable enterprise imaging: a HIMSS-SIIM enterprise imaging community collaborative white paper. J Digit Imaging. 2021 Feb (online).
Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, Milchenko M, Xu W, Marcus D, Colen RR, Bakas S. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Nature. 2020 Jul;10(12598).
Rieke N, Hancox J, Li W, Milletari F, Roth HR, Albarqouni S, Bakas S, Galter MN, Landman BA, Maier-Hein K, Ourselin S, Sheller M, Summers RM, Trask A, Xu D, Baust M, Cardoso MJ. The future of digital health with federated learning. NPJ Digit Med. 2020 Sep;3(119).
Yan, Zhan Y, Peng Z, Liao S, Shinagawa Y, Zhang S, Metaxas DN, Zhou XS. Multi-instance deep learning: discover discriminative local anatomies for bodypart recognition. IEEE Trans Med Imaging. 2016 May;35(5):1332−43.
Acknowledgements
We acknowledge the support of Nvidia Corporation with the donation of a Quadro P6000 via an academic GPU grant which was used for this research.
Funding
An Nvidia Quadro P6000 graphics card (estimated value $5000) was donated by Nvidia Corporation as part of a broad academic grant and was used for this work.
Author information
Authors and Affiliations
Contributions
Ross Filice participated in the design and implementation of the study and was the primary manuscript author. Anouk Stein participated in the design and implementation of the study and helped with the writing of the manuscript. Ian Pan developed the underlying infrastructure and deep learning architecture design. George Shih supervised the design and implementation. All authors reviewed the manuscript prior to submission.
Corresponding author
Ethics declarations
Ethics Approval
IRB exemption was obtained.
Consent to Participate
IRB exemption was obtained.
Consent for Publication
IRB exemption was obtained.
Conflict of Interest
Ross Filice, M.D. received an academic GPU grant from Nvidia Corporation which supported this work. Two authors (Anouk Stein, M.D. and George Shih, M.D., M.S.) serve as stakeholders and/or consultants for MD.ai.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Filice, R.W., Stein, A., Pan, I. et al. Federated Deep Learning to More Reliably Detect Body Part for Hanging Protocols, Relevant Priors, and Workflow Optimization. J Digit Imaging 35, 335–339 (2022). https://doi.org/10.1007/s10278-021-00547-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-021-00547-x