UCSF

Neuropathologists assess vast brain areas to identify diverse and subtly-differentiated morphologies. Standard semi-quantitative scoring approaches, however, are coarse-grained and lack precise neuroanatomic localization. We report a proof-of-concept deep learning pipeline identifying specific neuropathologies—amyloid plaques and cerebral amyloid angiopathy—in immunohistochemically-stained archival slides. Using automated segmentation of stained objects and a cloud-based interface, we annotated >70,000 plaque candidates from 43 whole slide images (WSIs) to train and evaluate convolutional neural networks. Networks achieved strong plaque classification on a 10-WSI hold-out set (0.993 and 0.743 areas under the receiver operating characteristic and precision recall curve, respectively). Prediction confidence maps visualized morphology distributions for WSIs at high resolution. Resulting plaque-burden scores correlated well with established semi-quantitative scores on a 30-WSI blinded hold-out. Finally, saliency mapping demonstrated that networks learned patterns agreeing with accepted pathologic features. This scalable means to augment a neuropathologist’s ability may suggest a route to neuropathologic deep phenotyping.