Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia

Rudolph, Jan ; Rueckel, Johannes; Döpfert, Jörg; Ling, Wen Xin; Opalka, Jens; Brem, Christian; Hesse, Nina; Ingenerf, Maria ; Koliogiannis, Vanessa; Solyanik, Olga; Hoppe, Boj F. ; Zimmermann, Hanna ; Flatz, Wilhelm; Forbrig, Robert ; Patzig, Maximilian; Rauchmann, Boris‐Stephan; Perneczky, Robert ; Peters, Oliver; Priller, Josef; Schneider, Anja; Fliessbach, Klaus; Hermann, Andreas; Wiltfang, Jens; Jessen, Frank; Düzel, Emrah; Buerger, Katharina ; Teipel, Stefan; Laske, Christoph; Synofzik, Matthis; Spottke, Annika; Ewers, Michael; Dechent, Peter; Haynes, John‐Dylan; Levin, Johannes ; Liebig, Thomas; Ricke, Jens; Ingrisch, Michael und Stoecklein, Sophia (2024): Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia. In: Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring, Bd. 16, Nr. 4, e70037

Abstract

Introduction

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.

Methods

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.

Results

AI significantly improved diagnostic accuracy for AD (area under the curve −AI: 0.800, +AI: 0.926, p < 0.05), with increased correct diagnoses (p < 0.01) and reduced errors (p < 0.03). BCR and RR showed notable performance gains (BCR: p < 0.04; RR: p < 0.02). For the diagnosis FTD, overall consensus (p < 0.01), BCNR (p < 0.02), and BCR (p < 0.05) recorded significantly more correct diagnoses.

Discussion

AI-assisted volumetry improves diagnostic performance in differentiating AD and FTD, benefiting all reader groups, including BCNR.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Medizin > Munich Cluster for Systems Neurology (SyNergy) ; Medizin > Institut für Schlaganfall- und Demenzforschung (ISD) ; Medizin > Klinikum der LMU München > Neurologische Klinik und Poliklinik mit Friedrich-Baur-Institut ; Medizin > Klinikum der LMU München > Klinik und Poliklinik für Radiologie
• Themengebiete: 600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin und Gesundheit
• ISSN: 2352-8729
• Sprache: Englisch
• DFG: Gefördert durch die Deutsche Forschungsgemeinschaft (DFG) - 390857198