Back to all papers

Automatic coarse-to-fine AC-PC localization on CT using registration-guided 3D-UNets.

July 21, 2026pubmed logopapers

Authors

Kadaba Sridhar S,Eastman A,Wilson P,Mishra S,Broadbent C,Truwit C,Kuang R,Samadani U

Affiliations (6)

  • Department of Bioinformatics and Computational Biology, University of Minnesota, Minneapolis, MN, United States.
  • Neurotrauma Research Lab, Center for Veterans Research and Education, Minneapolis, MN, United States.
  • Department of Radiation Oncology, University of Minnesota, Minneapolis, MN, United States.
  • Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, United States.
  • Department of Radiology, University of Minnesota, Minneapolis, MN, United States.
  • Division of Neurosurgery, Department of Surgery, Minneapolis Veterans Affairs Health Care System, Minneapolis, MN, United States.

Abstract

Automatically localizing the Anterior Commissure (AC) and Posterior Commissure (PC) is foundational for CT-based algorithmic disease screening, yet robust computational methods for this on CT remain lacking. We developed a registration-guided 3D-UNet framework for CT-based AC-PC localization, demonstrating its utility in computing ventriculomegaly features for Normal Pressure Hydrocephalus (NPH) detection. Framework development and evaluation were on an internal cohort of scans from patients with NPH, Alzheimer's disease, post-traumatic volume loss, and headache (Veterans Affairs [VA]-Cohort, <i>n</i> = 427). External validation was on separate datasets (VA-ExtCohort, University of California, Santa Barbara [UCSB]-ExtCohort). AC-PC reference standard definition, model development, and evaluation were on 1 mm<sup>3</sup>-resampled scans. On 1-mm<sup>3</sup> resampled scans, test-set AC-PC mean radial errors (MREs) were 1.64/1.49 mm on the VA-Cohort, 2.42/1.79 mm on the VA-ExtCohort (<i>n</i> = 40), and 2.31/1.93 mm on the UCSB-ExtCohort (<i>n</i> = 43). Notably, the upper limits of the 95% confidence intervals (CIs) for localization errors across all cohorts were well below 3.2 mm; we empirically determined this to be a clinically relevant threshold beyond which the discriminative power of AC-PC-referenced ventriculomegaly features degrades. Ventriculomegaly features assessed using our framework's predictions successfully distinguished NPH from Alzheimer's disease, post-traumatic volume loss, and headache on a chart-verified VA-Cohort subset (<i>n</i> = 238) with a test-set Area Under the Receiver Operating Characteristic Curve (AUC) of 0.95, closely matching the performance of features assessed using manual AC-PC localization. The proposed registration-guided 3D-UNet framework accurately and automatically localizes the AC-PC on CT despite varied structural degeneration, enabling standardized radiological feature computation. This approach can augment neurodegenerative disease screening on CT, the primary modality for elderly patients evaluated for falls and altered mentation.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.