biostudies-literatureUnknown16(4)Rudolph J<h4>Introduction</h4>This study evaluates the clinical value of a deep learning-based artificial intelligence (AI) system that performs rapid brain volumetry with automatic lobe segmentation and age- and sex-adjusted percentile comparisons.<h4>Methods</h4>Fifty-five patients-17 with Alzheimer's disease (AD), 18 with frontotemporal dementia (FTD), and 20 healthy controls-underwent cranial magnetic resonance imaging scans. Two board-certified neuroradiologists (BCNR), two board-certified radiologists (BCR), and three radiology residents (RR) assessed the scans twice: first without AI support and then with AI assistance.<h4>Results</h4>AI significantly improved diagnostic accuracy for AD (area under the curve -AI: 0.800, +AI: 0.926, <i>p</i> < 0.05), with increased correct diagnoses (<i>p</i>Alzheimer's & dementia (Amsterdam, Netherlands)e70037https://www.ebi.ac.uk/biostudies/studies/S-EPMC11632536biostudies-literatureArtificial intelligence-based rapid brain volumetry substantially improves differential diagnosis in dementia.PMC11632536Duzel ESpottke AIngrisch MZimmermann HDopfert JOpalka JRauchmann BSHermann APerneczky RHesse NSolyanik OSchneider APatzig MForbrig RBuerger KHoppe BFSynofzik MPeters OPriller JLaske CDechent PRicke JEwers MHaynes JDKoliogiannis VJessen FLing WXWiltfang JTeipel SBrem CLevin JFliessbach KRudolph JFlatz WRueckel JIngenerf MLiebig TStoecklein SfalseArtificial intelligence-based rapid brain volumetry substantially improves differential diagnosis in dementia.<h4>Introduction</h4>This study evaluates the clinical value of a deep learning-based artificial intelligence (AI) system that performs rapid brain volumetry with automatic lobe segmentation and age- and sex-adjusted percentile comparisons.<h4>Methods</h4>Fifty-five patients-17 with Alzheimer's disease (AD), 18 with frontotemporal dementia (FTD), and 20 healthy controls-underwent cranial magnetic resonance imaging scans. Two board-certified neuroradiologists (BCNR), two board-certified radiologists (BCR), and three radiology residents (RR) assessed the scans twice: first without AI support and then with AI assistance.<h4>Results</h4>AI significantly improved diagnostic accuracy for AD (area under the curve -AI: 0.800, +AI: 0.926, <i>p</i> < 0.05), with increased correct diagnoses (<i>p</i>2024-01-01T00:00:00Z2024 Oct-Dec2025-04-04T01:21:12.342Z2025-04-04T01:21:12.342ZS-EPMC116325363966508710.1002/dad2.70037