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, Stoecklein Sophia
Department of Radiology University Hospital LMU Munich Munich Germany.
Department of Neuroradiology University Hospital LMU Munich Munich Germany.
Alzheimers Dement (Amst). 2024 Dec 11;16(4):e70037. doi: 10.1002/dad2.70037. eCollection 2024 Oct-Dec.
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.
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.
AI significantly improved diagnostic accuracy for AD (area under the curve -AI: 0.800, +AI: 0.926, < 0.05), with increased correct diagnoses ( < 0.01) and reduced errors ( < 0.03). BCR and RR showed notable performance gains (BCR: < 0.04; RR: < 0.02). For the diagnosis FTD, overall consensus ( < 0.01), BCNR ( < 0.02), and BCR ( < 0.05) recorded significantly more correct diagnoses.
AI-assisted volumetry improves diagnostic performance in differentiating AD and FTD, benefiting all reader groups, including BCNR.
Artificial intelligence (AI)-supported brain volumetry significantly improved the diagnostic accuracy for Alzheimer's disease (AD) and frontotemporal dementia (FTD), with notable performance gains across radiologists of varying expertise levels.The presented AI tool is readily clinically available and reduces brain volumetry processing time from 12 to 24 hours to under 5 minutes, with full integration into picture archiving and communication systems, streamlining the workflow and facilitating real-time clinical decision making.AI-supported rapid brain volumetry has the potential to improve early diagnosis and to improve patient management.
本研究评估了一种基于深度学习的人工智能（AI）系统的临床价值，该系统可通过自动脑叶分割以及年龄和性别调整后的百分位数比较来进行快速脑容量测定。
55名患者——17名患有阿尔茨海默病（AD），18名患有额颞叶痴呆（FTD），20名健康对照者——接受了头颅磁共振成像扫描。两名具备专业资格认证的神经放射科医生（BCNR）、两名具备专业资格认证的放射科医生（BCR）和三名放射科住院医师（RR）对扫描结果进行了两次评估：第一次在没有AI支持的情况下进行，第二次在AI辅助下进行。
AI显著提高了AD的诊断准确性（曲线下面积——无AI：0.800，有AI：0.926，<0.05），正确诊断数量增加（<0.01），错误数量减少（<0.03）。BCR和RR的表现有显著提升（BCR：<0.04；RR：<0.02）。对于FTD的诊断，总体一致性（<0.01）、BCNR（<0.02）和BCR（<0.05）记录的正确诊断明显更多。
AI辅助的容量测定提高了区分AD和FTD的诊断性能，使包括BCNR在内的所有读者群体都受益。
人工智能（AI）支持的脑容量测定显著提高了阿尔茨海默病（AD）和额颞叶痴呆（FTD）的诊断准确性，不同专业水平的放射科医生的表现都有显著提升。所展示的AI工具在临床上易于使用，将脑容量测定处理时间从12至24小时缩短至5分钟以内，并完全集成到图像存档与通信系统中，简化了工作流程，便于进行实时临床决策。AI支持的快速脑容量测定有潜力改善早期诊断并优化患者管理。
