Reverse-engineering the diagnostic process: An indirect finding-driven deep learning model for pelvic active bleeding detection on CT that achieves specialist-level performance and surpasses residents - a multicenter study.

Okada N, Inoue S, Hirano Y, Liu C, Mitarai S, Honda S, Sato K, Hiraki S, Ichinose Y, Takita H, Ueda D, Matsuzawa Y, Yamamoto G, Fujimi S, Kuroda T

Open source

DOI
10.1016/j.injury.2026.113713
Published
2026 Sep 9
Container
Injury
Publisher
Not recorded
Open access
no

Credibility signals

limited evidence Score 43/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1016/j.injury.2026.113713,
  title = {Reverse-engineering the diagnostic process: An indirect finding-driven deep learning model for pelvic active bleeding detection on CT that achieves specialist-level performance and surpasses residents - a multicenter study.},
  author = {Okada N and Inoue S and Hirano Y and Liu C and Mitarai S and Honda S and Sato K and Hiraki S and Ichinose Y and Takita H and Ueda D and Matsuzawa Y and Yamamoto G and Fujimi S and Kuroda T},
  year = {2026},
  journal = {Injury},
  doi = {10.1016/j.injury.2026.113713},
  url = {https://doi.org/10.1016/j.injury.2026.113713}
}

RIS

TY  - JOUR
TI  - Reverse-engineering the diagnostic process: An indirect finding-driven deep learning model for pelvic active bleeding detection on CT that achieves specialist-level performance and surpasses residents - a multicenter study.
AU  - Okada N
AU  - Inoue S
AU  - Hirano Y
AU  - Liu C
AU  - Mitarai S
AU  - Honda S
AU  - Sato K
AU  - Hiraki S
AU  - Ichinose Y
AU  - Takita H
AU  - Ueda D
AU  - Matsuzawa Y
AU  - Yamamoto G
AU  - Fujimi S
AU  - Kuroda T
PY  - 2026
JO  - Injury
DO  - 10.1016/j.injury.2026.113713
UR  - https://doi.org/10.1016/j.injury.2026.113713
ER  - 

APA

N, O., S, I., Y, H., C, L., S, M., S, H., K, S., S, H., Y, I., H, T., D, U., Y, M., G, Y., S, F., & T, K. (2026). Reverse-engineering the diagnostic process: An indirect finding-driven deep learning model for pelvic active bleeding detection on CT that achieves specialist-level performance and surpasses residents - a multicenter study.. Injury. https://doi.org/10.1016/j.injury.2026.113713

Source records