According to an accepted manuscript published in ARRS’s own journal American Journal of Radiology (AJRMore), the use of automated deep learning AI tools and weight-based volume thresholds may enable large-scale assessment of splenomegaly in CT examinations performed for any indication.
Note that historically, the standard splenic linear measurement, which was used as a surrogate for splenic volume, had suboptimal performance in detecting volume-based splenomegaly.
Weight-based volume thresholds showed the presence of splenomegaly in most patients undergoing pre-liver transplantation CT. ”
Perry J. Pickhart, M.D., corresponding study author, Department of Radiology, University of Wisconsin School of Medicine and Public Health
Pickhardt and colleagues AJRMore Accepted manuscripts included 8,901 patients (4,235 men, A screening sample of 4,666 individuals (mean age 56 years) was included.
A secondary cohort of 104 patients with end-stage liver disease (62 men, 42 women, mean age 56 years) underwent pre-transplantation CT from January 2011 to May 2013. The deep learning algorithm of Pickhardt et al. – formerly developed, trained and tested at the National Institutes of Health Clinical Center, was used for segmentation of the spleen to determine spleen volume, and two radiologists performed the segmentation. independently examined a subset of
Ultimately, this automated deep learning AI tool was utilized to calculate spleen volume from CT examinations of 8,853 primary outpatients. Moreover, spleen volume was most strongly associated with body weight among various patient factors.
“As far as we know” AJRMore The authors concluded, “This study represents the largest reported sample of patients undergoing splenic volume fractionation.”
sauce:
American Roentgen Ray Association
Reference magazines:
Perez, AA, other. (2023) Automated deep learning artificial intelligence tool for spleen segmentation in CT: Volume-based threshold definition for splenomegaly. American Journal of Radiology. doi.org/10.2214/AJR.23.29478.
