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

Abstract

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.

Age-group determination of living individuals using first molar images based on artificial intelligence

“…Furthermore, important features for tooth-wise prediction were highlighted through Grad-CAM visualization. Grad-CAM can produce a coarse localization map highlighting the important regions in an image that aids prediction and wherein the algorithm is focused on 37 . In our CNN model, CNNs learn from various other regions, including a lowered occlusal surface due to tooth attrition, decreased alveolar bone level, and increased interdental space, however, usually from the pulp of the tooth, depending on the shape and location of the first molar when classifying the age group.…”

Radiomics and Machine Learning in Oral Healthcare

“…Recent studies have demonstrated that CNNs may increase diagnostic accuracy or prediction of various diseases, such as cardiovascular diseases, metabolic bone diseases, neurological diseases, ophthalmological diseases, infectious NTHL1 diseases, as well as several benign and malignant tumors . One of the most promising applications of CNNs is analyzing radiological images.…”

“…These imaging features may aid in the early detection of malignant or many bone diseases. They can also be used to predict treatment response to therapies, including oncotherapy, and to estimate functional parameters . The combination of these imaging features with other clinical and genetic data may improve the capacity of detecting and predicting diagnosis and outcomes.…”

Improved automatic detection of herpesvirus secondary envelopment stages in electron microscopy by augmenting training data with synthetic labelled images generated by a generative adversarial network

“…Nowadays, deep learning techniques, particularly convolutional neural networks (CNNs), are the most common way to perform automatic object detection. They have already achieved remarkable success in many computer vision related tasks, such as image classification, object detection and semantic segmentation (LeCun, Bengio, & Hinton, 2015; Szegedy, Vanhoucke, Ioffe, Shlens, & Wojna, 2015; Tang et al, 2019). The biggest advantage of CNNs is that they automatically extract and learn high‐level features from the input data, thereby eliminating the need for complicated feature extraction that requires a high level of domain expertise (Tajbakhsh et al, 2016).…”