Deep learning for Alzheimer's disease: Mapping large-scale histological tau protein for neuroimaging biomarker validation
Daniela Ushizima,
Yuheng Chen,
Maryana Alegro,
Dulce Ovando,
Rana Eser,
WingHung Lee,
Kinson Poon,
Anubhav Shankar,
Namrata Kantamneni,
Shruti Satrawada,
Edson Amaro Junior,
Helmut Heinsen,
Duygu Tosun,
Lea T. Grinberg
Affiliations
Daniela Ushizima
Bakar Institute for Computational Health Sciences, University of California San Francisco, CA, USA; Berkeley Institute for Data Science, University of California Berkeley, CA, USA; Lawrence Berkeley National Laboratory, Berkeley, CA, USA
Yuheng Chen
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Maryana Alegro
Bakar Institute for Computational Health Sciences, University of California San Francisco, CA, USA; Berkeley Institute for Data Science, University of California Berkeley, CA, USA; Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Dulce Ovando
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Rana Eser
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
WingHung Lee
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Kinson Poon
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Anubhav Shankar
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Namrata Kantamneni
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Shruti Satrawada
Department of Neurology, University of California San Francisco, San Francisco, CA, USA
Edson Amaro Junior
University of Sao Paulo Medical School, Sao Paulo, Brazil
Helmut Heinsen
University of Sao Paulo Medical School, Sao Paulo, Brazil; Julius-Maximilians University Würzburg, Würzburg, Germany
Duygu Tosun
Department of Radiology, University of California San Francisco, San Francisco, CA, USA; Veterans Affairs San Francisco, CA, USA
Lea T. Grinberg
Bakar Institute for Computational Health Sciences, University of California San Francisco, CA, USA; Department of Neurology, University of California San Francisco, San Francisco, CA, USA; University of Sao Paulo Medical School, Sao Paulo, Brazil; Department of Pathology, University of California San Francisco, San Francisco, CA, USA; Corresponding author at: 675 Nelson Rising Lane. PO Box 1207, San Francisco, CA, 94158, USA.
Abnormal tau inclusions are hallmarks of Alzheimer's disease and predictors of clinical decline. Several tau PET tracers are available for neurodegenerative disease research, opening avenues for molecular diagnosis in vivo. However, few have been approved for clinical use. Understanding the neurobiological basis of PET signal validation remains problematic because it requires a large-scale, voxel-to-voxel correlation between PET and (immuno) histological signals. Large dimensionality of whole human brains, tissue deformation impacting co-registration, and computing requirements to process terabytes of information preclude proper validation. We developed a computational pipeline to identify and segment particles of interest in billion-pixel digital pathology images to generate quantitative, 3D density maps. The proposed convolutional neural network for immunohistochemistry samples, IHCNet, is at the pipeline's core. We have successfully processed and immunostained over 500 slides from two whole human brains with three phospho-tau antibodies (AT100, AT8, and MC1), spanning several terabytes of images. Our artificial neural network estimated tau inclusion from brain images, which performs with ROC AUC of 0.87, 0.85, and 0.91 for AT100, AT8, and MC1, respectively. Introspection studies further assessed the ability of our trained model to learn tau-related features. We present an end-to-end pipeline to create terabytes-large 3D tau inclusion density maps co-registered to MRI as a means to facilitate validation of PET tracers.
