Slashdot Mirror
Google's DeepMind To Apply AI In Head and Neck Cancer Treatments (thestack.com)
An anonymous reader quotes a report from The Stack: Google's DeepMind team has partnered with British hospital doctors on an oral cancer program hoping to cut planning times for radiotherapy treatments. After recently announcing a partnership with London's Moorfields Eye Hospital to use its machine learning technologies to speed up the diagnoses of eye conditions, DeepMind has confirmed a new initiative at the University College London Hospitals (UCLH) NHS Foundation Trust. According to Google's artificial intelligence unit, cancer treatments including radiotherapy involve complicated design and planning, especially when they involve the head and neck. Treatments need to obliterate cancerous cells while avoiding any healthy surrounding cells, nerves, and organs. UCLH plans to work with DeepMind to explore whether machine learning can reduce planning time for these treatments, particularly for the image segmentation process which involves clinicians taking CT and MRI scans to build a detailed map of the areas to be treated. The report adds: "DeepMind algorithms will be set to work on an anonymized collection of 700 radiology scans from former oral cancer patients, learning from the historical data in order to draw its own conclusions without human support."
Google is follwing IBM Watson healthcare unit that started like 2 or 3 years ago. They are late in the game. Like they did with google home, a copy of amazon echo. Google copy and paste.
So they are saying Doctors are fallible and don't know what they are doing? Therefore Dr. Google is going to be diagnosing head and neck cancer from now on. I thought MD's were the authority on all things in the universe.
Some of the data sets used for facial detection and facial recognition number in the 10's or 100's of thousands of images. I wouldn't expect training on 700 scans to be particularly useful.
Charges for planning head and neck treatments are pretty substantial. Clicking a mouse and auto-contouring the different lymphatic regions and normal anatomy will earn that artificial intelligence a real revenue stream. Unless CMS decides that because the doctor didn't do it they will pay less.
So we are calling algorithms "AI" now? Cool.
Getting sick of how the word "Deep" is being plastered on everything. Like "Dark". It's become another bullshit marketing buzzword. Supposedly it means "a large system of neurons arranged in several hidden layers" but by that token you can call any program with nested subroutines "Deep". This is DEEP software bud. DEEP! I can't explain it to you because it's DEEP. Now break out the checkbook sucker, and I'll throw in this cyber cat brain too.
Radiation therapy physicist and image segmentation researcher here.
Generally speaking, there has been no revolutionary advance in segmentation algorithm design in the past 5-10 years. Most modern algorithms combine atlas-based segmentation (ABS), with either shape modeling and/or machine learning. By itself, machine learning alone is generally agreed to be less accurate than ABS alone. The data set described in the article (700 patients) is certainly adequate for ABS and shape modeling. It may not be adequate for a pure learning algorithm, but I reserve final judgement on that.
There are a few strange things in the article. (1) A standard head and neck case probably does not require four hours to create a manual segmentation. An hour is closer to correct. Therefore, they have already achieved their goal. (2) An important reason why a complex head and neck case takes longer is to define the therapy target. It is unlikely that simply adding processing power will make this easier. (3) I didn't see any description of what algorithm(s) they will evaluate, nor who will be in charge of algorithm development.