Deep learning (DL) methods have in recent years yielded impressive results in medical imaging, with the potential to function as clinical aid to radiologists. However, DL models in medical imaging are often trained on public research cohorts with images acquired with a single scanner or with strict protocol harmonization, which is not representative of a clinical setting. The aim of this study was to investigate how well a DL model performs in unseen clinical datasets-collected with different scanners, protocols and disease populations-and whether more heterogeneous training data improves generalization. In total, 3117 MRI scans of brains from multiple dementia research cohorts and memory clinics, that had been visually rated by a neuroradiologist according to Scheltens' scale of medial temporal atrophy (MTA), were included in this study. By training multiple versions of a convolutional neural network on different subsets of this data to predict MTA ratings, we assessed the impact of including images from a wider distribution during training had on performance in external memory clinic data. Our results showed that our model generalized well to datasets acquired with similar protocols as the training data, but substantially worse in clinical cohorts with visibly different tissue contrasts in the images. This implies that future DL studies investigating performance in out-of-distribution (OOD) MRI data need to assess multiple external cohorts for reliable results. Further, by including data from a wider range of scanners and protocols the performance improved in OOD data, which suggests that more heterogeneous training data makes the model generalize better. To conclude, this is the most comprehensive study to date investigating the domain shift in deep learning on MRI data, and we advocate rigorous evaluation of DL models on clinical data prior to being certified for deployment.

1st Department of Neurology Medical Faculty St Anne's Hospital and CEITEC Masaryk University Brno Czech Republic

3rd Department of Neurology Memory and Dementia Unit Aristotle University of Thessaloniki Thessaloniki Greece

Centre for Age Related Medicine Stavanger University Hospital Stavanger Norway; Institute of Psychiatry Psychology and Neuroscience King's College London London UK

Centre for Age Related Medicine Stavanger University Hospital Stavanger Norway; Stavanger Medical Imaging Laboratory Department of Radiology Stavanger University Hospital Stavanger Norway; Department of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway

Day Hospital of Geriatrics Memory Resource and Research Centre ICONE Strasbourg France

Department of Clinical Neuroscience Karolinska Institutet Stockholm Sweden; Department of Radiology Karolinska University Hospital Stockholm Sweden

Department of Neurology University Medical Centre Ljubljana Medical faculty University of Ljubljana Slovenia

Department of Neuroscience Imaging and Clinical Sciences and CESI University G d'Annunzio of Chieti Pescara Chieti Italy

Department of Neuroscience University of Genoa and Neurology Clinics Polyclinic San Martino Hospital Genoa Italy

Department of Neuroscience University of Padua Padua and Fondazione Ospedale San Camillo Venezia Venice Italy

Department of Psychiatry Warneford Hospital University of Oxford Oxford UK

Division of Clinical Geriatrics Department of Neurobiology Care Sciences and Society Karolinska Institutet Stockholm Sweden

Division of Clinical Geriatrics Department of Neurobiology Care Sciences and Society Karolinska Institutet Stockholm Sweden; Department of Neuroimaging Centre for Neuroimaging Sciences Institute of Psychiatry Psychology and Neuroscience King's College London London UK

Institute of Clinical Medicine Neurology University of Eastern Finland Finland; Neurocenter Neurology Kuopio University Hospital Kuopio Finland

Institute of Gerontology and Geriatrics University of Perugia Perugia Italy

Institute of Neuroscience Newcastle University Newcastle upon Tyne UK

Landspitali University Hospital Reykjavik Iceland

Medical University of Lodz Lodz Poland

Memory Clinic Department of Neurology Charles University 2nd Faculty of Medicine and Motol University Hospital Prague Czech Republic

Movement Disorders Unit Neurology Department Sant Pau Hospital Barcelona Spain; Institut d'Investigacions Biomédiques Sant Pau Barcelona Spain

Neurology Unit Department of Clinical and Experimental Sciences University of Brescia Brescia Italy

NIHR Biomedical Research Centre for Mental Health London UK; NIHR Biomedical Research Unit for Dementia London UK; Department of Neuroimaging Centre for Neuroimaging Sciences Institute of Psychiatry Psychology and Neuroscience King's College London London UK

UMR INSERM 1027 gerontopole CHU University of Toulouse France

References provided by Crossref.org

Federated learning enables big data for rare cancer boundary detection