BlurryScope enables compact, cost-effective scanning microscopy for HER2 scoring using deep learning on blurry images
This provides a more affordable and portable solution for digital pathology in clinical settings, though it is incremental as it builds on existing scanning and deep learning methods.
The researchers tackled automated HER2 scoring in breast tissue sections by developing BlurryScope, a compact and cost-effective scanning microscope that uses deep learning on blurry images, achieving testing accuracies of 79.3% for 4-class and 89.7% for 2-class classification on a dataset of 284 patient cores.
We developed a rapid scanning optical microscope, termed "BlurryScope", that leverages continuous image acquisition and deep learning to provide a cost-effective and compact solution for automated inspection and analysis of tissue sections. This device offers comparable speed to commercial digital pathology scanners, but at a significantly lower price point and smaller size/weight. Using BlurryScope, we implemented automated classification of human epidermal growth factor receptor 2 (HER2) scores on motion-blurred images of immunohistochemically (IHC) stained breast tissue sections, achieving concordant results with those obtained from a high-end digital scanning microscope. Using a test set of 284 unique patient cores, we achieved testing accuracies of 79.3% and 89.7% for 4-class (0, 1+, 2+, 3+) and 2-class (0/1+, 2+/3+) HER2 classification, respectively. BlurryScope automates the entire workflow, from image scanning to stitching and cropping, as well as HER2 score classification.