EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

Advancing osteoporosis opportunistic screening: multicenter validation of a deep learning algorithm using abdominal CT scans

Augusto Sarquis Serpa, Marcelo Straus Takahashi, Eduardo Moreno Júdice de Mattos Farina, Sean Bennett, Nishith Khandwala, Melissa Major, Jack Paparian, Fernanda Garozzo Velloni, Steven Rothenberg, Leonardo Kayat Bittencourt, Ross Warren Filice, John Mongan und 1 weitere

Abdominal Radiology · 2025

DOI: 10.1007/s00261-025-05213-2 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Abdominal Radiology, 2025. Verfasst von Augusto Sarquis Serpa und 12 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Diagnóstico por Imagem, Federal University of São Paulo, São Paulo, Brazil. augusto.esd5@gmail.com. Hauptthemen laut MEDLINE: Osteoporosis, Tomography, X-Ray Computed, Deep Learning, Radiography, Abdominal. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: To develop and do multicenter validation on an algorithm that screens for osteoporosis from abdominal CTs. METHODS: This is a diagnostic accuracy study with retrospective data from January 2022 to July 2022 consisting of two steps: a segmentation step of the lumbar vertebral bodies, involving outpatient non-contrast abdominal CTs from Diagnósticos da América S/A (Dasa), and a multicenter validation step incorporating data from four additional institutions. The segmentation employed a 2D UNet with a ResNet34 backbone. We determined the Pearson correlation coefficient (r) between the mean of the slices' mean attenuations (MSMA) on CT scans against the bone mineral density (BMD) on recent DEXA scans, calculated AUCs and performance metrics for osteoporosis prediction, including 95% confidence intervals, and evaluated calibration plots. RESULTS: The multicenter validation included 504 participants (median age, 66 years, interquartile range 56-72; 388 women). A linear regression analysis showed an r of 0.62 (95% CI, 0.56-0.67) between MSMA (HU) and BMD (g/cm2). The AUCs (95% CI) for distinguishing between normal and osteoporosis were 0.96 (0.89, 1.0) for the internal dataset and 0.82 (0.74, 0.89) for the external dataset, and the performance metrics (95% CI), for a globally optimized threshold of 202.6 HU, were 100% sensitivity (44, 100) and 91% specificity (84, 95) for internal data and 79% sensitivity (61, 90) and 81% specificity (76, 84) for external sites. MSMA was independently associated with osteoporosis on a mixed-effects logistic regression analysis. The model showed good calibration, with Brier score of 0.054. CONCLUSION: We developed and performed a multicenter validation of a DL model for osteoporosis prediction on CT.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OsteoporosisTomography, X-Ray ComputedDeep LearningRadiography, AbdominalHumansFemaleMiddle AgedRetrospective StudiesAgedMaleAlgorithmsBone DensityLumbar VertebraeAbsorptiometry, PhotonMass Screening

Stichwörter der Autor:innen

Computed tomographyDeep learningLumbar spineOpportunistic screeningOsteoporosis

Autor:innen und Institutionen

  • Departamento de Diagnóstico por Imagem, Federal University of São Paulo, São Paulo, Brazil. augusto.esd5@gmail.com.
  • Instituto de Radiologia, Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil. augusto.esd5@gmail.com.
  • Bunkerhill Health, San Francisco, USA. augusto.esd5@gmail.com.
  • Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, USA.
  • Departamento de Diagnóstico por Imagem, Federal University of São Paulo, São Paulo, Brazil.
  • Dasa, São Paulo, Brazil.

Zitieren

APA

Sarquis Serpa, A., Straus Takahashi, M., Júdice de Mattos Farina, E. M., Bennett, S., Khandwala, N., Major, M., Paparian, J., Garozzo Velloni, F., Rothenberg, S., Kayat Bittencourt, L., Filice, R. W., Mongan, J., & Campos Kitamura, F. (2025). Advancing osteoporosis opportunistic screening: multicenter validation of a deep learning algorithm using abdominal CT scans. Abdominal Radiology. https://doi.org/10.1007/s00261-025-05213-2

Vancouver

Sarquis Serpa A, Straus Takahashi M, Júdice de Mattos Farina EM, Bennett S, Khandwala N, Major M, et al. Advancing osteoporosis opportunistic screening: multicenter validation of a deep learning algorithm using abdominal CT scans. Abdominal Radiology. 2025. doi:10.1007/s00261-025-05213-2

BibTeX
@article{SarquisSerpa2025,
  author = {Sarquis Serpa, Augusto and Straus Takahashi, Marcelo and Júdice de Mattos Farina, Eduardo Moreno and Bennett, Sean and Khandwala, Nishith and Major, Melissa and Paparian, Jack and Garozzo Velloni, Fernanda and Rothenberg, Steven and Kayat Bittencourt, Leonardo and Filice, Ross Warren and Mongan, John and Campos Kitamura, Felipe},
  title = {Advancing osteoporosis opportunistic screening: multicenter validation of a deep learning algorithm using abdominal CT scans},
  journal = {Abdominal Radiology},
  year = {2025},
  doi = {10.1007/s00261-025-05213-2}
}
Kostenlos starten →