Email
Password
Remember meForgot password?
    Log in with Twitter

article imageGoogle microscope uses AI and AR for cancer detection

By Tim Sandle     May 13, 2018 in Science
Google has launched a new product from its health arm. This is a microscope that uses artificial intelligence and augmented reality to assist with the detection of certain types of cancer in real-time.
At present the microscope exits as a prototype, pending further trials. Tests to date show the advantages of the technology for cancer detection. The augmented reality microscope platform is a type of light microscope that has undergone extensive modifications. The platform enables real-time image analysis.
These real-time data are analysed using machine learning algorithms. This process is designed to help medical professionals in cancer detection, with the deep learning tools assisting pathologists with critical decision making.
The current method for assessing tissue for cancer is through the use of a conventional light microscope (a compound optical microscope). This brings with it occasional failings due to human error. One reason for the complexity is berceuse there are more than 300 distinct varieties of tumors, each with a characteristic biology.
The augmented reality microscope developed by Google can be can be retrofitted onto many existing light microscopes. In addition, Google state that the required components are low-cost and readily-available. The technology does not require whole slide digital versions of the tissue being analyzed.
Commenting on the technology, Google states: “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 researchers go on to say: “As in a traditional analog microscope, the user views the sample through the eyepiece. A machine learning algorithm projects its output back into the optical path in real-time. This digital projection is visually superimposed on the original (analog) image of the specimen to assist the viewer in localizing or quantifying features of interest."
In terms of how the technology works, Google has issued a video:
The new technology offers a range of visual feedback options, including text, arrows, contours, heatmaps, and animations. Two machine learning algorithms have been developed to date: one for breast cancer and the other for prostate cancer.
More about Microscope, Cancer, Google, Artificial intelligence
More news from