Related Experiment Video
Updated: Nov 25, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
A Multiscale Deep Learning Method for Quantitative Visualization of Traumatic Hemoperitoneum at CT: Assessment of
David Dreizin1, Yuyin Zhou1, Shuhao Fu1
1Section of Trauma and Emergency Radiology, R. Adams Cowley Shock Trauma Center (D.D.) and Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland Medical Center, University of Maryland, 22 S Greene St, Baltimore, MD 21201 (G.L., K.C., E.S., Z.W., T.C.); and Department of Computer Science, Computational Cognition Vision and Learning, Johns Hopkins University, Baltimore, Md (Y.Z., S.F., Y.W., A.L.Y.).
Purpose:
To evaluate the feasibility of a multiscale deep learning algorithm for quantitative visualization and measurement of traumatic hemoperitoneum and to compare diagnostic performance for relevant outcomes with categorical estimation.
Materials And Methods:
This retrospective, single-institution study included 130 patients (mean age, 38 years; interquartile range, 25-50 years; 79 men) with traumatic hemoperitoneum who underwent CT of the abdomen and pelvis at trauma admission between January 2016 and April 2019. Labeled cases were separated into five combinations of training (80%) and test (20%) sets, and fivefold cross-validation was performed. Dice similarity coefficients (DSCs) were compared with those from a three-dimensional (3D) U-Net and a coarse-to-fine deep learning method. Areas under the receiver operating characteristic curve (AUCs) for a composite outcome, including hemostatic intervention, transfusion, and in-hospital mortality, were compared with consensus categorical assessment by two radiologists. An optimal cutoff was derived by using a radial basis function-based support vector machine.
Results:
Mean DSC for the multiscale algorithm was 0.61 ± 0.15 (standard deviation) compared with 0.32 ± 0.16 for the 3D U-Net method and 0.52 ± 0.17 for the coarse-to-fine method (P < .0001). Correlation and agreement between automated and manual volumes were excellent (Pearson r = 0.97, intraclass correlation coefficient = 0.93). The algorithm produced intuitive and explainable visual results. AUCs for automated volume measurement and categorical estimation were 0.86 and 0.77, respectively (P = .004). An optimal cutoff of 278.9 mL yielded accuracy of 84%, sensitivity of 82%, specificity of 93%, positive predictive value of 86%, and negative predictive value of 83%.
Conclusion:
A multiscale deep learning method for traumatic hemoperitoneum quantitative visualization had improved diagnostic performance for predicting hemorrhage-control interventions and mortality compared with subjective volume estimation. Supplemental material is available for this article. © RSNA, 2020.
