Deep learning CT volumetry for idiopathic normal pressure hydrocephalus reaches AUC 0.97–0.99

Deep learning computed tomography (CT) volumetry distinguished idiopathic normal pressure hydrocephalus (iNPH) from controls with area under the curve 0.97 (95% confidence interval 0.94–1.00) externally and 0.99 (0.98–1.00) in Uppsala.

• Automated and manual CT ventricular cerebrospinal fluid volumes correlated strongly (rho 0.91, p<0.001) in iNPH patients.
• Training used 734 paired CT/MRI healthy-control datasets and 62 iNPH CT scans; external validation included 11 patients from Rostock and 30 from UAB.
• The CT volumetric measures performed comparably to gold-standard neuroradiology assessments, including cases with intraventricular shunt catheters.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.