News for hackers. Stuff that matters.
Re:Breast cancer detection in mammography using deep learnin... by RcouF1uZ4gsC on Monday December 30, 2019 @07:15PM (#21917889)
Of the major specialties, it seems that radiology is the most in danger of significant disruption. First of all, it can be done remotely, so there is risk if the regulation is lightened that foreign radiologists will be allowed to read studies at much less cost. The other issue is that this is something that deep learning can rapidly progress in given there are already a plethora of labeled data sets. For example, every mammogram that is taken has already been labeled normal or abnormal.
Re:Breast cancer detection in mammography using deep learnin... by Gatsky on Monday December 30, 2019 @08:09PM (#21918186)
I don't know anywhere that has a surfeit of radiologists just sitting around chewing gum. The types of tools described in the paper will enter the market as radiologist assisting devices, if for no other reason that the regulatory burden for this is dramatically less than a total radiologist replacement. Their introduction will make radiologist's jobs easier, and improve scan throughput and reduce waiting times for results. This will free up radiologists to deal with more complex cases. But I doubt it will materially reduce the number of radiology jobs, at least in the next generation.
Re:Breast cancer detection in mammography using deep learnin... by divbzero on Monday December 30, 2019 @08:42PM (#21918317)
> The types of tools described in the paper will enter the market as radiologist assisting devices, if for no other reason that the regulatory burden for this is dramatically less than a total radiologist replacement.

100% agreed.

A significant dimension of the regulatory dynamics is accountability: Who will sign off on and ultimately be responsible for findings from radiologic studies?

Re:Breast cancer detection in mammography using deep learnin... by Gatsky on Monday December 30, 2019 @08:58PM (#21918392)
Yes, taking responsibility is primarily the function of a doctor. This is actually a very unique and rare thing. Everywhere else we see people minimising their responsibility to others, rather than actively taking it on board.

Ceding this responsibility to corporations is a terrible idea. After all, one of the things about a corporate entity is that there isn't really anyone responsible. The GFC and Boeing are recent perfect examples of this. Automating medicine will result in making healthcare more like trying to get tech support. Yes doctors are imperfect, they make mistakes, some definitely shouldn't be working, they are territorial and monopolistic etc etc, but when the system is working you walk into a room with another person who wants to listen to you and help you, and we shouldn't ever try to take that away.

Re:Breast cancer detection in mammography using deep learnin... by tcbawo on Monday December 30, 2019 @09:18PM (#21918475)
If you could reduce the cost by increasing the productivity of radiologists, we'll be doing lots more and be getting better outcomes. This should be a win-win.
Re:Breast cancer detection in mammography using deep learnin... by gbrown on Monday December 30, 2019 @10:26PM (#21918716)
I think there's a huge potential for patient benefit if this is done correctly, though I worry that we'll just create mostly adequate classifiers based on existing data.

I also think we need to watch out for the human-attention issues illustrated in almost self driving cars. If a radiologist gets used to the computer being right 9/10 times, they could miss the 10th which would usually have been caught.

Overall we need more CV/ML/AI (choose your acronym) in this space, but it definitely requires some care.

Re:Breast cancer detection in mammography using deep learnin... by m_ke on Monday December 30, 2019 @10:37PM (#21918754)
There's a ton of deep learning startups working in this space already. Hardest part for most of them is getting access to training data. Because of that we'll probably see most of the commercial innovation coming from China and other countries that don't care about privacy.

Doctors make mistakes all the time and people in the medical profession work odd hours so there's already a ton of room for errors. Having a machine check their work or provide a second opinion will help them a lot.

Having a system that can do the primary screening and prioritize patients before a radiologist is available will save a ton of lives.

Re:Breast cancer detection in mammography using deep learnin... by gbrown on Tuesday December 31, 2019 @11:28AM (#21922179)
Part of the problem is that inadequate training data may not be a barrier to successfully marketing and implementing these systems - the tech is sexy and people are rightly excited.

> Doctors make mistakes all the time and people in the medical profession work odd hours so there's already a ton of room for errors.

That's my point - this is the training data. Unless we're careful, we're just going to approximate what we're already doing.

Re:Breast cancer detection in mammography using deep learnin... by m_ke on Tuesday December 31, 2019 @09:00PM (#21926154)
These systems can be trained on more data than any doctor will see in their lifetime. This means that it can pick up on discrepancies between doctors and has room to outperform most doctors.

I'm working on a similar system but for dietaty feedback based on images and it's amazing to see the model outperform all of the dietitians because it's able to see how all of the coaches respond to similar items.

Re:Breast cancer detection in mammography using deep learnin... by jayd16 on Monday December 30, 2019 @10:03PM (#21918638)
Is this different than any other illness that became easily testable? Wouldn't this eventually move into something a technician would perform, like a blood test?
Re:Breast cancer detection in mammography using deep learnin... by braindeath on Monday December 30, 2019 @10:24PM (#21918712)
Technicians don’t interpret blood tests, and radiologists don’t perform most imaging procedures, so I don’t understand the comparison.
Re:Breast cancer detection in mammography using deep learnin... by jayd16 on Tuesday December 31, 2019 @12:04PM (#21922512)
Well my thinking is more that the results would be read by your GP and not a specialist.
Re:Breast cancer detection in mammography using deep learnin... by learc83 on Monday December 30, 2019 @10:23PM (#21918706)
Technicans perform blood tests but doctors are the ones that interpret the results.
Re:Breast cancer detection in mammography using deep learnin... by jayd16 on Tuesday December 31, 2019 @12:03PM (#21922506)
Right, but GPs can interpret the results and raise red flags as needed. My point is not every test needs a specialist.
Re:Breast cancer detection in mammography using deep learnin... by learc83 on Tuesday December 31, 2019 @01:09PM (#21923054)
The problem is that unlike a blood test, neural networks are not transparent at all. So when an imaging test comes back with "possible malignancy" with red circle around the highlighted area, a GP doesn't have the experience to agree or disagree with the result. So every time that happens the next step will be to send the image to a specialist.

And in the case where the machine learning algorithms don't find anything suspicious, the GP again won't have the training or experience to confirm those results. Now if the person was otherwise healthy and this was just a screening that might be enough, but if the GP was suspicious enough to order the test in the first place, it won't be.

What will probably happens is that this kind of technology increases productivity for radiologists, and maybe increases the number of screenings done on healthy people. But it's not going to reduce the demand for radiologists.

Basically the problem is that to be able to interpret the output of a neural network you need to be an expert. What we need is AI that can present a fully formed argument that is easy for a non expert to follow and validate, but we are nowhere near that in most cases.

Re:Breast cancer detection in mammography using deep learnin... by mikece on Monday December 30, 2019 @07:18PM (#21917914)
It's also an area where a scan from a year ago can be re-processed based on new research and find something that wasn't detected on the first processing run -- and still be found years earlier than current methods. Lots of promise here. As for disrupting the field, practicing radiology will become a rare job for humans but the demand for basic research in radiology will likely go through the roof so that the AI can be properly improved and expanded.
Re:Breast cancer detection in mammography using deep learnin... by drageth on Monday December 30, 2019 @10:36PM (#21918750)
Most of the people that have been saying this for years have no idea how hospitals or health care in general functions. This includes the internal politics of a hospital, politics of the health care system as a whole and patterns of medical care/practice. As a surgeon, I can assure you that Radiology is not going anywhere. If anything, ML/DL will augment and improve radiology outcomes by assisting radiologists but there is no way as of yet where any type of AI can perform the role of a radiologist- that is, take a radiologic study, correlate that with an often past medical/surgical history of a patient and provide valuable insight into what's going on with the patient. I'm not a pessimist about this at all. ML/DL will absolutely improve outcomes if implemented properly; however, radiologists are going to be augmented, not replaced. They are after all physicians.
Re:Breast cancer detection in mammography using deep learnin... by m_ke on Monday December 30, 2019 @10:46PM (#21918792)
That's how all sensible machine learning systems are deployed, as assistive tools with a human in the loop so that they can improve with usage.

This stuff will be used to do initial screening to prioritize cases and provide an initial analysis for the radiologist to confirm. Once they're deployed it won't be too long before they're as good as the top practitioners.

It will be a long time before they completely replace radiologists in America but we'll probably see them on autopilot in third world countries where there's a shortage of doctors and data privacy laws are not as stringent. I've met a Chinese guy doing medicine in the states who claimed to have access to all medical data for a bunch of hospitals back in China.

Re:Breast cancer detection in mammography using deep learnin... by bearjaws on Tuesday December 31, 2019 @10:26AM (#21921571)
Sure the politics of health systems will slow down implementation. However, I have seen many times in my career where technology has made peoples job titles more "scarce" as the efficiency gains of new medical software have decreased the time needed for people to do that job.

Radiologists are likely to see a lower demand as a result of these technologies and will either A) Spend more time on complicated cases or B) Be let go. Nobody is saying ALL radiologists are going to be out a job. Look at dosimetry as a recent example of how software improved, and the time to contour per patient decreased, causing many health systems to shrink their dosimetrist staff or offload the responsibilities to the physician office.

This isn't the first time technology has been applied to healthcare, change will come slowly and eventually people will have to find new fields to work within healthcare.

Re:Breast cancer detection in mammography using deep learnin... by heavyset_go on Monday December 30, 2019 @09:02PM (#21918409)
This is like suggesting that intelligent autocomplete will put office workers out of work.
Re:Breast cancer detection in mammography using deep learnin... by avocado4 on Monday December 30, 2019 @08:39PM (#21918307)
It's not politically easy to push legislation that increases competition for MDs.

They've been successfully pushing back against scope of practice changes for RAs, PAs, ANPs, PTs and other midlevels, let alone allowing foreign doctors in without an expensive residency medallion. And on the data side, hospitals are doing all they can to make sure that is as locked down in their silos as possible, because all these AI papers have been posing a fundamental threat to their bottom line (Medicare and employer reimbursement for physician and related services).

Basically every single decision-making regulatory body on state and Federal levels is full of MDs, with inherent conflict of interest.

Now new FDA chief is an old-school MD again, and his first order of business was to call a conference studying the potential dangers AI can pose to patient safety.

Re:Breast cancer detection in mammography using deep learnin... by dragonwriter on Monday December 30, 2019 @08:46PM (#21918339)
> They've been successfully pushing back against scope of practice changes for RAs, PAs, ANPs, PTs and other midlevels,

As such changes continue to be signed into law, I assume you mean, overall, unsuccessfully doing so.

Re:Breast cancer detection in mammography using deep learnin... by nitwit005 on Monday December 30, 2019 @10:42PM (#21918776)
> given there are already a plethora of labeled data sets

I had some coworkers who went to RSNA this year. The AI companies are still desperate for data. There was direct discussion of the disappointment in AI in more than one talk.

It'll happen, but like anything else it'll take a lot longer than people were predicting.

Re:Breast cancer detection in mammography using deep learnin... by aswanson on Monday December 30, 2019 @07:30PM (#21917994)
Talk to some lawyers. Not happening anytime soon.
Re:Breast cancer detection in mammography using deep learnin... by chance_state on Monday December 30, 2019 @07:34PM (#21918018)
Care to elaborate?
Re:Breast cancer detection in mammography using deep learnin... by chongli on Monday December 30, 2019 @07:42PM (#21918065)
False positives are a major source of morbidity in cancer treatment. Biopsies and unnecessary major surgeries are a big problem.
Re:Breast cancer detection in mammography using deep learnin... by jcims on Monday December 30, 2019 @09:54PM (#21918613)
Are you aware of any studies in this regard? I can't find anything conclusive, just handwavy assertions like this[0]:

If the NNS for a screening test is 5,000, those who advocate screening must make the ethical argument that the large benefits to 1 individual justify the sum of the harms to which 4,999 people are exposed. Whether this holds up to moral scrutiny depends on the nature of the harms.

The problem that I think the medical community misses is that the unwashed masses are generally completely unable to access procedures that aren't recommended by a doctor. So in the above assertion, that someone 'advocating for screening' must take on the ethical burden of harms coming from that screening, in my estimation, is complete and utter bullshit. What I would prefer to see is that screening comes with patient education so they understand the potential risks and inaccuracies and then let 'er rip. If something goes south, it's on them.

[0] https://www.ncbi.nlm.nih.gov/books/NBK223933/

Re:Breast cancer detection in mammography using deep learnin... by DanBC on Tuesday December 31, 2019 @04:58AM (#21919994)
Here's an easy to read introduction to over-testing and over-diagnosis. This isn't talking about false postives. It's talking about harm caused by actual positives. https://ebm.bmj.com/content/23/1/1

Gerd Gigerenzer has done a lot of work on this, so his books are useful. Reckoning With Risk or Risk Savvy are good.

> What I would prefer to see is that screening comes with patient education so they understand the potential risks and inaccuracies and then let 'er rip. If something goes south, it's on them.

Informed choice should already be built into all healthcare systems because it's a feature of international human rights laws and patients are usually allowed to decline to have a test done. And there's usually a doctor somewhere who'll perform an unnecessary test if you're prepared to pay.

Communicating risk is difficult.

We know that merely giving people information and letting them take full responsibility won't work. We know it won't work because we already study whether people understand the risks of testing and treatment, and we find a disturbingly large number of people don't, and that includes the HCPs recommending the testing and treatments.

Most people struggle with this question: "A machine has been invented to scan a population for a disease. The machine is good but not perfect. If you have the disease there is a 90% chance it will return positive. If you do not have the disease there is a 1% chance it will return positive. About 1% of the population have the disease. Mr Smith is tested, and the test comes back positive. What's the chance Mr Smith actually has the disease?"

But the problem of lack of numeracy is more severe: only 20% - 25% of people understand that 0.1% is 1 in 1,000. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3310025/

People do not understand the difference between "absolute" vs "relative" risk increases, so we see newspapers reporting "100% increase in risk from eating X" when the numbers are an increase from 1:100,000 to 2:100,000 deaths.

https://bestpractice.bmj.com/info/toolkit/practise-ebm/under...

https://www.eufic.org/en/understanding-science/article/absol...

Re:Breast cancer detection in mammography using deep learnin... by nopinsight on Monday December 30, 2019 @08:06PM (#21918175)
What if human doctors double check results for false positives? They will help prevent unnecessary procedures. The algorithms would still allow scans to be read more efficiently since negative results for low-risk patients can be mostly automated away.
Re:Breast cancer detection in mammography using deep learnin... by chongli on Monday December 30, 2019 @08:14PM (#21918201)
If a human radiologist is double-checking all of the results (for both false positives and false negatives) then it's not so much a disruptive technology, it's another tool in the radiologist's tool belt at that point.
Re:Breast cancer detection in mammography using deep learnin... by m_ke on Monday December 30, 2019 @09:43PM (#21918568)
Radiologists get second opinions all the time. I've seen radiology projects where the radiologists gave a different reading almost 40% of the time. (example of this: https://pubs.rsna.org/doi/full/10.1148/radiol.2018171557).

In some cases they also spend a lot of time annotating and measuring small areas of the images and having a model generate suggestions for them would save a ton of time.

Re:Breast cancer detection in mammography using deep learnin... by jrumbut on Monday December 30, 2019 @09:17PM (#21918473)
You say that like it's a bad thing!

I don't think taking the human all the way out of the loop is a great idea given the state of models we've seen to date (in medicine, anyway).

I think a better direction would be looking at how to make these systems more complementary with human operators, surfacing interesting features or distant connections humans tend to miss and guarding against the big errors anyone might make staring at grayscale images on the night shift.

Re:Breast cancer detection in mammography using deep learnin... by nopinsight on Monday December 30, 2019 @09:24PM (#21918492)
As in my last sentence, even just mostly automating the cases with negative results for low-risk patients would improve throughout and efficiency quite a bit.

Yes, I agree it should be another, yet increasingly important tool for a while. Perhaps not until a near-AGI is invented that machines can completely automate away doctor jobs.

Re:Breast cancer detection in mammography using deep learnin... by jlisam13 on Monday December 30, 2019 @09:01PM (#21918405)
how about less radiologists required to double check? I would consider that as disruptive.