You are here: Home » News-IANS » Health-Medicine
Business Standard

Google develops AR-powered microscope for real-time cancer detection

IANS  |  New York 

A team of researchers has developed a (ML) and (AR)-powered microscope that can help in real-time detection of and save millions of lives.

In the annual meeting of the American Association for Research (AACR) in Chicago, on Monday, described a prototype Microscope (ARM) platform that can help accelerate and democratise the adoption of for pathologists around the world.

The platform consists of a modified light microscope that enables and presentation of the results of algorithms directly into the field of view.

The ARM can be retrofitted into existing light microscopes around the world, using low-cost, readily-available components, and without the need for whole slide digital versions of the tissue being analysed.

"In principle, the ARM can provide a wide variety of visual feedback, including text, arrows, contours, heatmaps or animations, and is capable of running many types of algorithms aimed at solving different problems such as object detection, quantification or classification," Martin Stumpe, Technical Lead and Craig Mermel, Product Manager, Brain Team, wrote in a blog post.

Applications of deep learning to medical disciplines including ophthalmology, dermatology, radiology, and pathology have shown great promise.

"At Google, we have also published results showing that a convolutional is able to detect metastases in lymph nodes at a level of accuracy comparable to a trained pathologist," the post said.

However, because direct tissue visualization using a compound light microscope remains the predominant means by which a diagnoses illness, a critical barrier to the widespread adoption of deep learning in pathology is the dependence on having a digital representation of the microscopic tissue.

Modern computational components and deep learning models, such as those built upon "TensorFlow", will allow a wide range of pre-trained models to run on this platform.

The Google team configured ARM to run two different -- one that detects in lymph node specimens and another that detects in specimens.

While 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, the noted.

"We believe that the ARM has potential for a large impact on global health, particularly for the diagnosis of infectious diseases, including and malaria, in the developing countries," Google noted.



(This story has not been edited by Business Standard staff and is auto-generated from a syndicated feed.)

First Published: Tue, April 17 2018. 13:58 IST