Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia
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 disea...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-10-01
|
| Series: | Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/dad2.70037 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850059569560027136 |
|---|---|
| author | Jan Rudolph Johannes Rueckel Jörg Döpfert Wen Xin Ling Jens Opalka Christian Brem Nina Hesse Maria Ingenerf Vanessa Koliogiannis Olga Solyanik Boj F. Hoppe Hanna Zimmermann Wilhelm Flatz Robert Forbrig Maximilian Patzig Boris‐Stephan Rauchmann Robert Perneczky Oliver Peters Josef Priller Anja Schneider Klaus Fliessbach Andreas Hermann Jens Wiltfang Frank Jessen Emrah Düzel Katharina Buerger Stefan Teipel Christoph Laske Matthis Synofzik Annika Spottke Michael Ewers Peter Dechent John‐Dylan Haynes Johannes Levin Thomas Liebig Jens Ricke Michael Ingrisch Sophia Stoecklein |
| author_facet | Jan Rudolph Johannes Rueckel Jörg Döpfert Wen Xin Ling Jens Opalka Christian Brem Nina Hesse Maria Ingenerf Vanessa Koliogiannis Olga Solyanik Boj F. Hoppe Hanna Zimmermann Wilhelm Flatz Robert Forbrig Maximilian Patzig Boris‐Stephan Rauchmann Robert Perneczky Oliver Peters Josef Priller Anja Schneider Klaus Fliessbach Andreas Hermann Jens Wiltfang Frank Jessen Emrah Düzel Katharina Buerger Stefan Teipel Christoph Laske Matthis Synofzik Annika Spottke Michael Ewers Peter Dechent John‐Dylan Haynes Johannes Levin Thomas Liebig Jens Ricke Michael Ingrisch Sophia Stoecklein |
| author_sort | Jan Rudolph |
| collection | DOAJ |
| description | 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. Highlights 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. |
| format | Article |
| id | doaj-art-0c50654dddbd4ff789cf0212ae53597c |
| institution | DOAJ |
| issn | 2352-8729 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring |
| spelling | doaj-art-0c50654dddbd4ff789cf0212ae53597c2025-08-20T02:50:51ZengWileyAlzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring2352-87292024-10-01164n/an/a10.1002/dad2.70037Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementiaJan Rudolph0Johannes Rueckel1Jörg Döpfert2Wen Xin Ling3Jens Opalka4Christian Brem5Nina Hesse6Maria Ingenerf7Vanessa Koliogiannis8Olga Solyanik9Boj F. Hoppe10Hanna Zimmermann11Wilhelm Flatz12Robert Forbrig13Maximilian Patzig14Boris‐Stephan Rauchmann15Robert Perneczky16Oliver Peters17Josef Priller18Anja Schneider19Klaus Fliessbach20Andreas Hermann21Jens Wiltfang22Frank Jessen23Emrah Düzel24Katharina Buerger25Stefan Teipel26Christoph Laske27Matthis Synofzik28Annika Spottke29Michael Ewers30Peter Dechent31John‐Dylan Haynes32Johannes Levin33Thomas Liebig34Jens Ricke35Michael Ingrisch36Sophia Stoecklein37Department of Radiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDevelopment Department Mediaire GmbH Berlin GermanyDevelopment Department Mediaire GmbH Berlin GermanyMedical Department Mediaire GmbH Berlin GermanyDepartment of Neuroradiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Neuroradiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Neuroradiology University Hospital LMU Munich Munich GermanyDepartment of Neuroradiology University Hospital LMU Munich Munich GermanyDepartment of Neuroradiology University Hospital LMU Munich Munich GermanyGerman Center for Neurodegenerative Diseases (DZNE) Munich Munich GermanyGerman Center for Neurodegenerative Diseases (DZNE) Berlin Berlin GermanyGerman Center for Neurodegenerative Diseases (DZNE) Berlin Berlin GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Rostock/Greifswald Rostock GermanyGerman Center for Neurodegenerative Diseases (DZNE) Goettingen Goettingen GermanyDepartment of Psychiatry and Psychotherapy Klinikum rechts der Isar Technical University Munich Munich GermanyGerman Center for Neurodegenerative Diseases (DZNE) Magdeburg Magdeburg GermanyGerman Center for Neurodegenerative Diseases (DZNE) Munich Munich GermanyGerman Center for Neurodegenerative Diseases (DZNE) Rostock Rostock GermanyGerman Center for Neurodegenerative Diseases (DZNE) Tuebingen Tuebingen GermanyGerman Center for Neurodegenerative Diseases (DZNE) Tuebingen Tuebingen GermanyGerman Center for Neurodegenerative Diseases (DZNE) Bonn Bonn GermanyGerman Center for Neurodegenerative Diseases (DZNE) Munich Munich GermanyMR‐Research in Neurosciences, Department of Cognitive Neurology Georg‐August‐University Goettingen Goettingen GermanyBernstein Center for Computational Neuroscience Charité‐Universitätsmedizin Berlin GermanyGerman Center for Neurodegenerative Diseases (DZNE) Munich Munich GermanyDepartment of Neuroradiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyDepartment of Radiology University Hospital LMU Munich Munich GermanyAbstract 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. Highlights 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.https://doi.org/10.1002/dad2.70037Alzheimer's diseaseartificial intelligencebrain volumetryclinical cohortsfrontotemporal dementia |
| spellingShingle | Jan Rudolph Johannes Rueckel Jörg Döpfert Wen Xin Ling Jens Opalka Christian Brem Nina Hesse Maria Ingenerf Vanessa Koliogiannis Olga Solyanik Boj F. Hoppe Hanna Zimmermann Wilhelm Flatz Robert Forbrig Maximilian Patzig Boris‐Stephan Rauchmann Robert Perneczky Oliver Peters Josef Priller Anja Schneider Klaus Fliessbach Andreas Hermann Jens Wiltfang Frank Jessen Emrah Düzel Katharina Buerger Stefan Teipel Christoph Laske Matthis Synofzik Annika Spottke Michael Ewers Peter Dechent John‐Dylan Haynes Johannes Levin Thomas Liebig Jens Ricke Michael Ingrisch Sophia Stoecklein Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring Alzheimer's disease artificial intelligence brain volumetry clinical cohorts frontotemporal dementia |
| title | Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia |
| title_full | Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia |
| title_fullStr | Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia |
| title_full_unstemmed | Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia |
| title_short | Artificial intelligence–based rapid brain volumetry substantially improves differential diagnosis in dementia |
| title_sort | artificial intelligence based rapid brain volumetry substantially improves differential diagnosis in dementia |
| topic | Alzheimer's disease artificial intelligence brain volumetry clinical cohorts frontotemporal dementia |
| url | https://doi.org/10.1002/dad2.70037 |
| work_keys_str_mv | AT janrudolph artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT johannesrueckel artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT jorgdopfert artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT wenxinling artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT jensopalka artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT christianbrem artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT ninahesse artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT mariaingenerf artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT vanessakoliogiannis artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT olgasolyanik artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT bojfhoppe artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT hannazimmermann artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT wilhelmflatz artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT robertforbrig artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT maximilianpatzig artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT borisstephanrauchmann artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT robertperneczky artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT oliverpeters artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT josefpriller artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT anjaschneider artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT klausfliessbach artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT andreashermann artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT jenswiltfang artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT frankjessen artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT emrahduzel artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT katharinabuerger artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT stefanteipel artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT christophlaske artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT matthissynofzik artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT annikaspottke artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT michaelewers artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT peterdechent artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT johndylanhaynes artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT johanneslevin artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT thomasliebig artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT jensricke artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT michaelingrisch artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia AT sophiastoecklein artificialintelligencebasedrapidbrainvolumetrysubstantiallyimprovesdifferentialdiagnosisindementia |