Classification of negative and positive 18 F-florbetapir brain PET studies in subjective cognitive decline patients usin
- PDF / 1,060,378 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 2 Downloads / 173 Views
ORIGINAL ARTICLE
Classification of negative and positive 18F-florbetapir brain PET studies in subjective cognitive decline patients using a convolutional neural network Bart Marius de Vries 1 & Sandeep S. V. Golla 1 & Jarith Ebenau 2 & Sander C. J. Verfaillie 2 & Tessa Timmers 2 & Fiona Heeman 1 & Matthijs C. F. Cysouw 1 & Bart N. M. van Berckel 1,2 & Wiesje M. van der Flier 2,3 & Maqsood Yaqub 1 & Ronald Boellaard 1 & Alzheimer’s Disease Neuroimaging Initiative Received: 8 May 2020 / Accepted: 18 August 2020 # The Author(s) 2020
Abstract Purpose Visual reading of 18F-florbetapir positron emission tomography (PET) scans is used in the diagnostic process of patients with cognitive disorders for assessment of amyloid-ß (Aß) depositions. However, this can be time-consuming, and difficult in case of borderline amyloid pathology. Computer-aided pattern recognition can be helpful in this process but needs to be validated. The aim of this work was to develop, train, validate and test a convolutional neural network (CNN) for discriminating between Aß negative and positive 18F-florbetapir PET scans in patients with subjective cognitive decline (SCD). Methods 18F-florbetapir PET images were acquired and visually assessed. The SCD cohort consisted of 133 patients from the SCIENCe cohort and 22 patients from the ADNI database. From the SCIENCe cohort, standardized uptake value ratio (SUVR) images were computed. From the ADNI database, SUVR images were extracted. 2D CNNs (axial, coronal and sagittal) were built to capture features of the scans. The SCIENCe scans were randomly divided into training and validation set (5-fold crossvalidation), and the ADNI scans were used as test set. Performance was evaluated based on average accuracy, sensitivity and specificity from the cross-validation. Next, the best performing CNN was evaluated on the test set. Results The sagittal 2D-CNN classified the SCIENCe scans with the highest average accuracy of 99% ± 2 (SD), sensitivity of 97% ± 7 and specificity of 100%. The ADNI scans were classified with a 95% accuracy, 100% sensitivity and 92.3% specificity. Conclusion The 2D-CNN algorithm can classify Aß negative and positive 18F-florbetapir PET scans with high performance in SCD patients.
Key points QUESTION: Can a convolutional neural network accurately classify 18Fflorbetapir PET brain scans in a SCD patient cohort? PERTINENT FINDINGS: In this cohort study we observed high performance for classification of 18F-florbetapir PET brain scans using a CNN. IMPLICATIONS FOR PATIENT CARE: Deep-learning-based PET 18 F-florbetapir classification could be helpful in situations where there is lack of time and experienced readers. This article is part of the Topical Collection on Neurology * Ronald Boellaard [email protected] Bart Marius de Vries [email protected] 1
Department of Radiology and Nuclear Medicine, Amsterdam UMC, Vrije Universiteit Amsterdam, De Boelelaan, 1117 1081, HV Amsterdam, The Netherlands
2
Alzheimer Center and department of Neurology, Amsterdam UMC, Vrije U
Data Loading...
