Google this week presented initial data from a prototype augmented reality microscope platform it’s developing for advanced cancer detection, according to a research blog post from the tech giant. The platform consists of a modified light microscope for real-time image analysis and presents analysis from a machine-learning algorithm directly into the users field of view, Google said.

Google said the platform could be retrofitted into existing light microscopes generally used in hospitals and clinics using low-cost, readily-available components without the need for digital versions of the scopes. The system can provide a number of visual overlays, including text, arrows, contours, heat maps and animations, Google said, and is capable of running multiple algorithms intended to improve detection, quantification or classification. In its prototype, Google said it configured the system to run two cancer detection algorithms – one intended to detect breast cancer metastases in lymph node specimens and one intended to detect cancer in prostatectomy specimens.

The prototype system overlays an outline around detected tumor regions with a green contour to help draw the pathologists’ attention without obscuring the tumor cell appearance, Google said. Project researchers said that the device performed remarkably well on the augmented-reality system, with the lymph node metastasis models achieving an area-under-the-curve of 0.98 and the prostate cancer model achieving an AUC of 0.96 for cancer detection.

We believe that the ARM has potential for a large impact on global health, particularly for the diagnosis of infectious diseases, including tuberculosis and malaria, in developing countries. Furthermore, even in hospitals that will adopt a digital pathology workflow in the near future, ARM could be used in combination with the digital workflow where scanners still face major challenges or where rapid turnaround is required (e.g. cytology, fluorescent imaging, or intra-operative frozen sections). 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. We’re excited to continue to explore how the ARM can help accelerate the adoption of machine learning for positive impact around the world, Google technical lead Martin Stumpe and brain team member Craig Mermel wrote in a blog post.

Earlier this month, the American Medical Association said it is partnering with Google to launch the AMS Healthcare Interoperability and Innovation Challenge designed to support mobile health technology that improves monitoring and care in the management of chronic diseases. – MassDevice

10 Diagnostic Imaging Trends for 2018



Digital version