AmyloidPETNet: Classification of Amyloid Positivity in Brain PET Imaging Using End-to-End Deep Learning.

Journal: Radiology
PMID: 38860897

Abstract

Background Visual assessment of amyloid PET scans relies on the availability of radiologist expertise, whereas quantification of amyloid burden typically involves MRI for processing and analysis, which can be computationally expensive. Purpose To develop a deep learning model to classify minimally processed brain PET scans as amyloid positive or negative, evaluate its performance on independent data sets and different tracers, and compare it with human visual reads. Materials and Methods This retrospective study used 8476 PET scans (6722 patients) obtained from late 2004 to early 2023 that were analyzed across five different data sets. A deep learning model, AmyloidPETNet, was trained on 1538 scans from 766 patients, validated on 205 scans from 95 patients, and internally tested on 184 scans from 95 patients in the Alzheimer's Disease Neuroimaging Initiative (ADNI) fluorine 18 (F) florbetapir (FBP) data set. It was tested on ADNI scans using different tracers and scans from independent data sets. Scan amyloid positivity was based on mean cortical standardized uptake value ratio cutoffs. To compare with model performance, each scan from both the Centiloid Project and a subset of the Anti-Amyloid Treatment in Asymptomatic Alzheimer's Disease (A4) study were visually interpreted with a confidence level (low, intermediate, high) of amyloid positivity/negativity. The area under the receiver operating characteristic curve (AUC) and other performance metrics were calculated, and Cohen κ was used to measure physician-model agreement. Results The model achieved an AUC of 0.97 (95% CI: 0.95, 0.99) on test ADNI F-FBP scans, which generalized well to F-FBP scans from the Open Access Series of Imaging Studies (AUC, 0.95; 95% CI: 0.93, 0.97) and the A4 study (AUC, 0.98; 95% CI: 0.98, 0.98). Model performance was high when applied to data sets with different tracers (AUC ≥ 0.97). Other performance metrics provided converging evidence. Physician-model agreement ranged from fair (Cohen κ = 0.39; 95% CI: 0.16, 0.60) on a sample of mostly equivocal cases from the A4 study to almost perfect (Cohen κ = 0.93; 95% CI: 0.86, 1.0) on the Centiloid Project. Conclusion The developed model was capable of automatically and accurately classifying brain PET scans as amyloid positive or negative without relying on experienced readers or requiring structural MRI. Clinical trial registration no. NCT00106899 © RSNA, 2024 See also the editorial by Bryan and Forghani in this issue.

Authors

  • Shuyang Fan
    From the Department of Bioengineering, Rice University, Houston, Tex (S. Fan); Department of Radiology (S. Fan, M.R.P., P.X., S.M.H., J.J.L., S. Flores, P.L., B.G., C.A.R., D.S.M., A.N., T.L.S.B., A.S.), Charles F. and Joanne Knight Alzheimer Disease Research Center (B.G., B.M.A., R.B., J.C.M., T.L.S.B.), Department of Neurology (C.A.R., B.M.A., R.J.B., J.C.M.), and Institute for Informatics, Data Science and Biostatistics (A.S.), Washington University School of Medicine, 660 S Euclid Ave, Campus Box 8132, St Louis, MO 63110; Duke-NUS Medical School, Singapore (S. Fan); Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, Mo (S.C., A.S.); Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Canada (A.N.); and Tracy Family SILQ Center for Neurodegenerative Biology, St Louis, Mo (R.J.B.).
  • Maria Rosana Ponisio
    From the Department of Bioengineering, Rice University, Houston, Tex (S. Fan); Department of Radiology (S. Fan, M.R.P., P.X., S.M.H., J.J.L., S. Flores, P.L., B.G., C.A.R., D.S.M., A.N., T.L.S.B., A.S.), Charles F. and Joanne Knight Alzheimer Disease Research Center (B.G., B.M.A., R.B., J.C.M., T.L.S.B.), Department of Neurology (C.A.R., B.M.A., R.J.B., J.C.M.), and Institute for Informatics, Data Science and Biostatistics (A.S.), Washington University School of Medicine, 660 S Euclid Ave, Campus Box 8132, St Louis, MO 63110; Duke-NUS Medical School, Singapore (S. Fan); Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, Mo (S.C., A.S.); Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Canada (A.N.); and Tracy Family SILQ Center for Neurodegenerative Biology, St Louis, Mo (R.J.B.).
  • Pan Xiao
    Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, No. 1 Youyi Road, Yuzhong District, Chongqing, 400016, China.
  • Sung Min Ha
    From the Department of Bioengineering, Rice University, Houston, Tex (S. Fan); Department of Radiology (S. Fan, M.R.P., P.X., S.M.H., J.J.L., S. Flores, P.L., B.G., C.A.R., D.S.M., A.N., T.L.S.B., A.S.), Charles F. and Joanne Knight Alzheimer Disease Research Center (B.G., B.M.A., R.B., J.C.M., T.L.S.B.), Department of Neurology (C.A.R., B.M.A., R.J.B., J.C.M.), and Institute for Informatics, Data Science and Biostatistics (A.S.), Washington University School of Medicine, 660 S Euclid Ave, Campus Box 8132, St Louis, MO 63110; Duke-NUS Medical School, Singapore (S. Fan); Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, Mo (S.C., A.S.); Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Canada (A.N.); and Tracy Family SILQ Center for Neurodegenerative Biology, St Louis, Mo (R.J.B.).
  • Satrajit Chakrabarty
    Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, MO.
  • John J Lee
    Echocardiography Laboratory Mount Sinai Heart InstituteMount Sinai Medical Center Miami Beach FL.
  • Shaney Flores
    Washington University in St. Louis, St. Louis, Missouri, USA.
  • Pamela LaMontagne
    Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO, USA.
  • Brian Gordon
    From the Department of Bioengineering, Rice University, Houston, Tex (S. Fan); Department of Radiology (S. Fan, M.R.P., P.X., S.M.H., J.J.L., S. Flores, P.L., B.G., C.A.R., D.S.M., A.N., T.L.S.B., A.S.), Charles F. and Joanne Knight Alzheimer Disease Research Center (B.G., B.M.A., R.B., J.C.M., T.L.S.B.), Department of Neurology (C.A.R., B.M.A., R.J.B., J.C.M.), and Institute for Informatics, Data Science and Biostatistics (A.S.), Washington University School of Medicine, 660 S Euclid Ave, Campus Box 8132, St Louis, MO 63110; Duke-NUS Medical School, Singapore (S. Fan); Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, Mo (S.C., A.S.); Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Canada (A.N.); and Tracy Family SILQ Center for Neurodegenerative Biology, St Louis, Mo (R.J.B.).
  • Cyrus A Raji
    From the Department of Bioengineering, Rice University, Houston, Tex (S. Fan); Department of Radiology (S. Fan, M.R.P., P.X., S.M.H., J.J.L., S. Flores, P.L., B.G., C.A.R., D.S.M., A.N., T.L.S.B., A.S.), Charles F. and Joanne Knight Alzheimer Disease Research Center (B.G., B.M.A., R.B., J.C.M., T.L.S.B.), Department of Neurology (C.A.R., B.M.A., R.J.B., J.C.M.), and Institute for Informatics, Data Science and Biostatistics (A.S.), Washington University School of Medicine, 660 S Euclid Ave, Campus Box 8132, St Louis, MO 63110; Duke-NUS Medical School, Singapore (S. Fan); Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, Mo (S.C., A.S.); Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Canada (A.N.); and Tracy Family SILQ Center for Neurodegenerative Biology, St Louis, Mo (R.J.B.).
  • Daniel S Marcus
    Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO, USA.
  • Arash Nazeri
    From the Department of Bioengineering, Rice University, Houston, Tex (S. Fan); Department of Radiology (S. Fan, M.R.P., P.X., S.M.H., J.J.L., S. Flores, P.L., B.G., C.A.R., D.S.M., A.N., T.L.S.B., A.S.), Charles F. and Joanne Knight Alzheimer Disease Research Center (B.G., B.M.A., R.B., J.C.M., T.L.S.B.), Department of Neurology (C.A.R., B.M.A., R.J.B., J.C.M.), and Institute for Informatics, Data Science and Biostatistics (A.S.), Washington University School of Medicine, 660 S Euclid Ave, Campus Box 8132, St Louis, MO 63110; Duke-NUS Medical School, Singapore (S. Fan); Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, Mo (S.C., A.S.); Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Canada (A.N.); and Tracy Family SILQ Center for Neurodegenerative Biology, St Louis, Mo (R.J.B.).
  • Beau M Ances
    Department of Radiology, Washington University in St. Louis, School of Medicine, 510 S. Kingshighway, MC 8131, Saint Louis, MO 63110, USA; Knight Alzheimer's Disease Research Center, Washington University in St. Louis, School of Medicine, 510 S. Kingshighway, MC 8131, Saint Louis, MO 63110, USA; Department of Neurology, Washington University in St. Louis, School of Medicine, 510 S. Kingshighway, MC 8131, Saint Louis, MO 63110, USA.
  • Randall J Bateman
    Knight Alzheimer's Disease Research Center, Washington University in St. Louis, St. Louis, Missouri, USA.
  • John C Morris
    Knight Alzheimer Disease Research Center, Washington University in St. Louis, St. Louis, MO, USA.
  • Tammie L S Benzinger
    Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO, USA.
  • Aristeidis Sotiras
    Department of Radiology and Institute of Informatics, Washington University in St. Luis, St. Luis, MO63110, USA.

Keywords

External Resources

Popular Topics
Recent Journals