Baby Octopus playing with a diver!

This AI-driven microscope from Google could help detect cancer in future

Google showcased its prototype Augmented Reality Microscope (ARM) platform with a new modified light microscope that can detect breast cancer metastases as well as prostate cancer.

Google showcased its prototype Augmented Reality Microscope (ARM) platform with a new modified light microscope that can detect breast cancer metastases as well as prostate cancer.

Google showcased its prototype Augmented Reality Microscope (ARM) platform with a new modified light microscope that can detect breast cancer metastases as well as prostate cancer. The microscope, powered by Artificial Intelligence (AI) and machine learning algorithms enables real-time analysis. It displays the results directly into the field 0f view, unlike traditional analog microscopes that are need users to view the sample through the eyepiece. The magnifications can be between 4-40x and the result is displayed by outlining detected tumor regions with a green contour.

The prototype was showcased during a talk delivered at the Annual Meeting of the American Association for Cancer Research (AACR), with an accompanying paper “An Augmented Reality Microscope for Real-time Automated Detection of Cancer” which is currently under review. The move is aimed at accelerating the adoption of deep learning tools for pathologists globally. Google’s ARM platform can be retrofitted into existing light microscopes as well, which requires low-cost components. The microscope offers several visual feedback, thanks to machine learning algorithms. This includes text, arrows, contours, heatmaps, or animations.

“While both cancer models were originally trained on images from a whole slide scanner with a significantly different optical configuration, the models performed remarkably well on the ARM with no additional re-training,” reads a Google blog post. “Of course, light microscopes have proven useful in many industries other than pathology, and we believe the ARM can be adapted for a broad range of applications across healthcare, life sciences research, and material science,” the post added.