This Is The End Of The Beginning Rather Than The Beginning Of The End.

This appeared a few days ago.

Google AI system beats doctors in detection tests for breast cancer

Hannah Kuchler

Jan 2, 2020 — 3.19pm

New York | Google Health has developed a system that can identify breast cancer more accurately than radiologists, in the latest sign that artificial intelligence could improve early detection of disease in images.

In a paper published in the scientific journal Nature, experts from Google Health, Alphabet’s DeepMind unit, and UK and US universities showed the AI model reduced both false positives, in which patients are wrongly told they have cancer, as well as false negatives, where the disease is present but not diagnosed.

Screening mammograms is known to be imperfect, failing to detect about one in five breast cancers, according to the American Cancer Society. More than half of all women are given a false positive every 10 years, causing anxiety and leading to unnecessary treatment, which was estimated in a 2015 study in the journal Health Affairs to cost the US more than $US4 billion ($5.7 billion) a year.

Dominic King, the UK lead for Google Health, said the results were “really exciting” and showed how AI could be used to help screen for cancers in earlier stages, when the disease is harder to detect accurately. The algorithm was trained and tested on de-identified images from almost 120,000 mammograms in the US and the UK.

DeepMind recently transferred control of its health division to parent company Google. Mustafa Suleyman, who oversaw the health team, is leaving DeepMind for a new job examining the opportunities and impacts of applied artificial intelligence at Google.

Lots more here:

https://www.afr.com/technology/google-ai-system-beats-doctors-in-detection-tests-for-breast-cancer-20200102-p53ocu

This is good news in terms of decreasing what is missed and reducing the false positives.

There are two issues that now need to be fully worked through – accepting that the AI actually works and is stable in its reliability.

First there needs to be a prospective studies and trials of the system, to confirm the algorithm performance.

Second we need to integrate the AI into the radiological work flow so maximum benefit is achieved with the least interference to traditional ways of working and relationships.

If this all proves up it really will be a step forward in clinical care, but we are not there quite yet. Practical and routine use of AI still has a way to go. Of course ongoing human involvement in decision making remains vital. It will be decades before un-supervised application of AI in clinical advanced applications will be sensible!

This view is rather confirmed by this from the U.S.

University tests AI-powered ‘radiology assistant’

The NYU School of Medicine’s technology enables radiologists to see images the way they currently see them, then, if they deem necessary, ask the AI for its opinion. Results to date are impressive.

By Bill Siwicki

January 03, 2020 12:12 PM

There are various known issues with screening mammography.

Probably the most important one is the fact that even though relatively few women actually develop breast cancer, many women are asked for additional imaging following screening mammography (such as diagnostic mammography, ultrasounds and MRI), which is a big cost both in terms of money spent and the stress it causes patients.

Putting AI to work in radiology

Dr. Krzysztof J. Geras, assistant professor, department of radiology, at the NYU School of Medicine, led an AI-powered effort to tackle this challenge.

“Our intention is to decrease this number of additional imaging, and AI is the means to achieve that,” he stated. “It also is known that a small fraction of cancers are missed by the radiologists during a screening mammography exam. We were also hoping that our AI tool would help catch these cases, which could potentially save lives.”

The name of the proposed technology is “ResNet-22.” It is a type of deep convolutional neural network. The way it works is by learning from a very large number of image/label pairs.
Lots more here:
https://www.healthcareitnews.com/news/university-tests-ai-powered-radiology-assistant

This is a very worthwhile deeper read on the topic.

https://www.afr.com/technology/how-do-machines-think-20191213-p53jvj

How do machines think?

We have built AI systems that can do everything from diagnose our illnesses to drive our cars. But how can we trust them if we don’t understand them?

David.