Related Experiment Video
Updated: Aug 6, 2026
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Automated Midline Shift Quantification on Noncontrast CT Across Intracranial Pathologies: A Multicenter Validation
Ish A Talati1, Sarah J Snyder1, Hafez D Haerian1
1From the Department of Radiology (I.A.T., J.J.H.), Stanford University School of Medicine, CA; Temple Medical School (S.J.S.), Philadelphia, PA; Department of Radiology (H.D.H.), Carle Foundation Hospital, Urbana, IL; Department of Radiology (J.M.H.), University of Colorado Medical School, Aurora, CO and Boulder Statistics (K.C.), Boulder, CO.
Automated software Rapid MLS accurately quantifies midline shift (MLS) on non-contrast CT scans, comparable to expert neuroradiologists. This tool offers rapid and reproducible measurements for acute neuroimaging.
Area of Science:
- Neurology
- Radiology
- Medical Imaging
Background:
- Midline shift (MLS) is a critical indicator of intracranial pathology, potentially leading to fatal brain herniation.
- Manual MLS measurement on non-contrast CT (NCCT) is time-consuming and prone to inter-rater variability.
- Automated tools are needed for efficient and reliable MLS quantification.
Purpose of the Study:
- To evaluate the performance of Rapid MLS, an automated software tool for MLS quantification on NCCT.
- To compare the accuracy of automated MLS measurements with manual measurements by expert neuroradiologists.
Main Methods:
- Retrospective multicenter cohort study involving 153 adult patients with intracranial pathology and MLS.
- NCCT images were analyzed, with MLS manually measured by three independent neuroradiologists to establish a gold standard.
- Automated MLS measurements from Rapid MLS were compared to the gold standard using non-inferiority analysis (mean absolute error) and regression/Bland-Altman analyses.
Main Results:
- Rapid MLS demonstrated a mean absolute error (MAE) of 0.8 mm, which was non-inferior to the expert neuroradiologists' average pairwise MAE of 0.9 mm (p<0.0001).
- Passing-Bablok regression showed close agreement, with a small mean difference of 0.2 mm observed in Bland-Altman analysis.
- The software showed comparable accuracy to experts, though it tended to underestimate MLS values above 10 mm.
Conclusions:
- Automated MLS measurement using Rapid MLS on NCCT is accurate and comparable to expert neuroradiologists.
- Rapid MLS shows potential as an adjunct tool for rapid and reproducible MLS quantification in acute neuroimaging workflows.
- This technology can aid in faster clinical decision-making for patients with intracranial pathologies.
