Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs.

Autor:	Jones RM; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Sharma A; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Hotchkiss R; Hospital for Special Surgery, 523 East 72nd St, New York, NY 10021 USA., Sperling JW; Mayo Clinic, 200 1st St SW, Rochester, MN 55905 USA., Hamburger J; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Ledig C; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., O'Toole R; University of Maryland Medical System, R Adams Cowley Shock Trauma Center, 22 South Greene Street, Baltimore, MD 21201 USA., Gardner M; Stanford University, 450 Broadway St, Redwood City, CA 94063 USA., Venkatesh S; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Roberts MM; Hospital for Special Surgery, 523 East 72nd St, New York, NY 10021 USA., Sauvestre R; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Shatkhin M; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Gupta A; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Chopra S; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Kumaravel M; The University of Texas Medical School at Houston, 6431 Fannin Street, Houston, TX 77030 USA., Daluiski A; Hospital for Special Surgery, 523 East 72nd St, New York, NY 10021 USA., Plogger W; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA., Nascone J; University of Maryland Medical System, 22 South Greene Street, Baltimore, MD 21201 USA., Potter HG; Hospital for Special Surgery, 523 East 72nd St, New York, NY 10021 USA., Lindsey RV; Imagen Technologies, Inc., 151 West 26th Street, Suite 1001, New York, NY 10001 USA.
Jazyk:	angličtina
Zdroj:	NPJ digital medicine [NPJ Digit Med] 2020 Oct 30; Vol. 3, pp. 144. Date of Electronic Publication: 2020 Oct 30 (Print Publication: 2020).
DOI:	10.1038/s41746-020-00352-w
Abstrakt:	Missed fractures are the most common diagnostic error in emergency departments and can lead to treatment delays and long-term disability. Here we show through a multi-site study that a deep-learning system can accurately identify fractures throughout the adult musculoskeletal system. This approach may have the potential to reduce future diagnostic errors in radiograph interpretation. Competing Interests: Competing interestsThe authors declare the following financial competing interest: financial support for the research was provided by Imagen Technologies, Inc. R.V.L., J.H., R.M.J., S.V., A.S., R.S., M.S., A.G., S.C., W.P., and C.L. are employees of Imagen Technologies, Inc. All authors are shareholders at Imagen Technologies, Inc. The authors declare that there are no non-financial competing interests. (© The Author(s) 2020.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu