Interpretable classification of Alzheimer’s disease pathologies with a convolutional neural network pipeline

By Ziqi Tang, Kangway V. Chuang, Charles Decarli, Lee‐way Jin, L. Beckett, Michael J. Keiser, Brittany N. Dugger. 2018

214 citations recorded by the source corpus.

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 that identifies 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 annotate > 70,000 plaque candidates from 43 whole slide images (WSIs) to train and evaluate convolutional neural networks. Networks achieve 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 visualize morphology distributions at high resolution. Resulting network-derived amyloid beta (Aβ)-burden scores correlate well with established semi-quantitative scores on a 30-WSI blinded hold-out. Finally, saliency mapping demonstrates that networks learn patterns agreeing with accepted pathologic features. This scalable means to augment a neuropathologist’s ability suggests a route to neuropathologic deep phenotyping. Convolutional neural networks have been applied to various areas of medical imaging and histology. Here the authors develop an automated approach using interpretable neural networks to determine Alzheimer’s disease plaque and cerebral amyloid angiopathy burden in post-mortem human brain tissue.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tao Lei
2. Asoke Kumar Nandi
3. Cuntai Guan
4. Yong Wan
5. Risheng Wang
6. Xiaogang Du
7. Hongying Meng
8. Erico Tjoa

In Biomedical Engineering

1. Cuntai Guan
2. Erico Tjoa

In Computer Vision and Pattern Recognition

1. Tao Lei
2. Asoke Kumar Nandi
3. Cuntai Guan
4. Yong Wan
5. Risheng Wang
6. Xiaogang Du
7. Hongying Meng
8. Erico Tjoa

Citations in the corpus

• A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “Reference [67] uses Guided Grad-CAM and feature occlusion, providing complementary heatmaps for the classification of Alzheimer’s disease pathologies.”
• Medical Image Segmentation Using Deep Learning: A Survey (2020, background): “Therefore, the research on the interpretability of deep learning for medical image segmentation [114-117] will be a popular direction in future.”