Google Software Detects Cancer More Accurately Than Doctors

///Google Software Detects Cancer More Accurately Than Doctors

Google published a scientific article which explains how it has managed to identify cancer through artificial intelligence more accurately than physicians experienced in the field of pathology. The company is using a version of its intelligent image recognition system originally developed for its standalone car design.

A “raw” or pristine version of the same system used in cars has been trained to identify cancer in high-resolution images of the patient’s body. Without any personalization, the system has already achieved good results. However, a customization that made the software analyze each pixel broadly and also with reduced zoom greatly improved the performance of the machine.

After further customization, including network training to examine images at different magnifications, in much the same way a pathologist works, Google shows that it is possible to train a model that compares or exceeds the performance of a physician who has not had the time limit to examine the same images.


At present, the company’s artificial intelligence can identify any type of cancer in digital images with 89% accuracy, when medical experts rate the accuracy of 73% by analyzing the same content without any time limit.

Replace doctors?

While performing better than doctors, Google’s system will not replace their work. The idea is for the software to do a preliminary analysis and apply markings to suspect points, giving directions to where the doctors need to look and work.

After that, the professional is the one who will validate this information and evaluate all the findings of the system, which should make it more and more precise.

By |2017-03-04T17:06:01+00:00March 4th, 2017|Health & Food, Lifestyle|4 Comments


  1. Deep Kumar September 9, 2017 at 5:14 pm - Reply

    73%-89% accuracy.It’s a huge difference man.Google can make everything possible.I salute the progress… Google!!!
    Just Keep it up.

  2. Prottoy September 18, 2017 at 2:33 pm - Reply

    In real life AI is ‘any’ program that mimics human behavior, often to do a task, without human intervention. – This is a broad definition, but it is also a factual one. That coffee machine on the counter that brews coffee in the morning as long as it has water and beans, is AI.  Traffic lights that switch based on cars on a weight sensor, or light  beams at night, AI. Most AI is simple and not very becoming of a movie. I do not agree. AI denotes intelligence. A coffee maker has none, nore do any of those other systems mentioned. This machine might qualify since it came up with signs we haven’t yet. It gathered information and made decisions about new possibilities. But the rest of the items are just coded to heat water and put it into a spout sized to drip water through a bean at a specific pace. Traffic lights work off timers and/or signals from the street run through the most basic if/then/else type checks. There isn’t any intelligence there.

  3. Anthony October 20, 2017 at 4:47 am - Reply

    I think the reliable automation of diagnosis to the point that it could replace an actual physician is still in the science fiction/digital technology realm, and will remain there for some time yet.  However, in clinical technologies and automation I learned that we can make a tremendous progress by automating measurements (diagnostic tests) that one needs to make to come up with an accurate diagnosis.  If we focus on not replacing physician, but rather on making his/her job easier by providing more precise/accurate measurements, faster and with fewer false-positives and false-negatives, then the “automated diagnosis” is not so futuristic anymore.  The problem is that practically all clinical diagnostic tests are unreliable, some more so, some less.  Even many genetic tests leave a wide “grey area”, and many commonly used test have high rate of false-positives and -negatives.  The problem frequently stems from high biologic variability intra-subject, inter-subject, due to external factors and due to the method of measuring of this biologic signal.   In addition, computer technologies can be used to take much more data into account per subject than was previously possible.  The increased amount of data can both increase the precision, and provide new insight into the disease/condition.  In conclusion, the computer science community can impact the healthcare and diagnostics by focusing on making better measurements, rather than trying to replace what is actually working very well – the intellect and experience of highly trained and dedicated professionals.

  4. Omwancha Daniel Ogeto November 9, 2017 at 5:52 pm - Reply

    Very interesting article. I am amazed at the kind of things digital technology has enabled men to do and the many innovative startups that have put their resources into making this possible. It is a fact that making the decision on whether or not a patient has cancer usually involves trained professionals meticulously scanning tissue samples over weeks and months. Metastasis detection is currently performed by pathologists reviewing large expanses of biological tissues over extended time periods. This process is labor intensive and error-prone. But in a busy hospital, there isn’t always time to find such a perfect human to review your results. In any case, it turns out to be quite difficult to interpret the results of many common tests, regardless of the level of interest in the outcome. What does this mean for medicine? Well, there have long been studies showing that computers are better at basic correlation finding, and that you might well be better served by having an AI doc to listen to you list your woes. But such robot-docs have always been limited in their ability to interpret test results. Sure, an AI might be able to order an X-Ray, and a nurse might be able to administer the X-Ray, but certainly we’ll always need a doctor to read and interpret the X-Ray?

Leave A Comment