One whole-body MRI could replace multiple cancer scans • Hacker News Board

Re: One whole-body MRI could replace multiple cancer scans

#201

Post by choppaface » Tue, May 21, 2019, 7:00 AM UTC

Friend of mine recently got diagnosed with cancer. Has over a dozen golf-ball sized tumors in his brain, bones, lungs, liver, etc. After 6 months of nagging pain and pneumonia they finally did a small MRI and saw something odd. Then they did a full-body MRI and it was very very obvious.

Taking an image can help catch things? No shit Sherlock! I don't care if doctors can't agree imaging diagnoses sometimes. Time to get better at doing that. Computers can help. Yes there's a helium shortage, but since when does healthcare get short-changed?

Aside: there's at least one company looking to make whole-body imaging more available: https://q.bio/ The founder is a little crazy, but a good kind of crazy.

Re: One whole-body MRI could replace multiple cancer scans

#202

Post by blub » Tue, May 21, 2019, 7:23 AM UTC

jedberg wrote: post #111

I've had this idea floating in my head for a while. Provide free annual full body MRIs to people, including being read by a radiologist, which they can take to anyone they want (doctor, lawyer, whatever). In exchange, they agree to send the org a copy of all their past and future medical records. The records are anonymized and tied to the MRIs. The MRIs and medical data is then pumped through machine learning algorit…

That's not a charity, it's the good ole model of paying with data.

You might as well show ads to the patients while they're in the machine and evaluate their brainwaves to see which they like best.

Re: One whole-body MRI could replace multiple cancer scans

#203

Post by jlpom » Tue, May 21, 2019, 7:30 AM UTC

ohithereyou wrote: post #187

jlpom wrote: post #136

MRI are generaly considered safe but my personnal experience contradict this. I passed a 3T brain MRI (with gadolinium injection for angiography) ~80 days ago and my life has been seriously painful since then. I have experienced hypertension (often >170 of systole, seem unrelated but never had high tension of my life and like the rest of theses issues it appeared exactly after the MRI), sleep issues, head difficultie…

Make sure you report this to both your GP and to the company that makes the machine. All major MRI machine makers watch for adverse reactions like hawks, and if there's any way that your experience is an adverse reaction to either the contrast or the scan they are going to want the details to prevent it from happening to somebody else.

Thanks for the advice, I will send an email to GE.

Re: One whole-body MRI could replace multiple cancer scans

#204

Post by D_Alex » Tue, May 21, 2019, 7:41 AM UTC

mattkrause wrote: post #173

Someone wrote: post #163

Earlier quoted context omitted.

”Determining whether something is (non) malignant isn't trivial. It often requires a more invasive test (e.g., biopsy, exploratory surgery)” Not necessarily, waiting can in many cases tell you whether something is malignant. If we had, say, a century of monthly full-body MRIs of a million persons, together with their history and cause of death, the technology to align those scans across time, and the technology to an…

Two reasons I think this is not the way to go: First, the cost would be insane. A century of monthly MRIs is 1200 scans per person, or 1.2B scans to finish your hypothetical dataset. We pay about $US 550/hr for scanner time, using a research scanner that's subsidized (i.e., we're just covering costs, not making a profit). The article doesn't say how long the scan is. You can burn as much scanner time as you want chas…

> You can burn as much scanner time as you want chasing resolution/quality, but an hour seems reasonable.

Out of curiosity, what determines the speed of the MRI scan? Are massive improvements theoretically possible?

Re: One whole-body MRI could replace multiple cancer scans

#205

Post by agent008t » Tue, May 21, 2019, 8:24 AM UTC

mattkrause wrote: post #166

koboll wrote: post #140

Earlier quoted context omitted.

It's nice that you think those are costs worth remaining ignorant over. However, when the ignorance is about things that literally might kill me, my personal opinion is that it's worth it.

The word 'cost' seems to be confusing things. Both options have risks and both options can kill you. Namely: A) Doing nothing may allow a problem to fester until it either kills you or becomes detectable with standard treatments. However, you have no exposure whatsoever to side effects, infections, or medical errors for the things that are missed. B) Doing whole-body MRI 'fishing expeditions' decreases the risk of mi…

Speaking of blood tests - where does the uncertainty come in there? Is the measuring equipment noisy, so they might detect some marker when it is actually not present? Or is it that you can actually have a high concentration of whatever they are looking for in your blood but it somehow just be normal for you because you are an outlier?

I tend to think it is the former but can anyone clarify?

Re: One whole-body MRI could replace multiple cancer scans

#206

Post by D_Alex » Tue, May 21, 2019, 8:26 AM UTC

abakker wrote: post #122

concernedstats wrote: post #95

Earlier quoted context omitted.

I think their statement is more general than what you're making it out to be. The goal of receiving better and more data puts pressure to have better imaging technology.

I think there are perverse incentives at work, too. If running the MRI machine cost $100, people would do it. If it can bill insurance $100k, and then any follow up might cost $500k, there is a rational aversion to doing it as it might make the _system_ less good for everyone if insurance cracked down on exploratory imaging as a billable thing (obviously, they already do this to some extent). Better technology is unl…

>If running the MRI machine cost $100, people would do it.

There are different kinds of MRIs, but the actual direct costs for running an MRI without preparatory procedures is around $100 (preparatory dye injection may be another $50 cost). Marginal costs are lower still.

Re: One whole-body MRI could replace multiple cancer scans

#207

Post by D_Alex » Tue, May 21, 2019, 8:27 AM UTC

briandear wrote: post #192

mattkrause wrote: post #173

Earlier quoted context omitted.

Two reasons I think this is not the way to go: First, the cost would be insane. A century of monthly MRIs is 1200 scans per person, or 1.2B scans to finish your hypothetical dataset. We pay about $US 550/hr for scanner time, using a research scanner that's subsidized (i.e., we're just covering costs, not making a profit). The article doesn't say how long the scan is. You can burn as much scanner time as you want chas…

At that scale, scans wouldn’t cost $550 per hour. “Because it’s too expensive,” seems like a great opportunity for some clever startup to figure out a way to make it less expensive. Computers used to take up entire rooms. Flying across the country used to be insanely expensive. Cell phones used to cost a ton of money per minute. Reducing the cost of scanning, or developing entirely new scanning tech isn’t science fic…

$98/scan in Japan.

https://www.pbs.org/wgbh/pages/frontline/sickaroundtheworld/...

Re: One whole-body MRI could replace multiple cancer scans

#208

Post by npunt » Tue, May 21, 2019, 9:19 AM UTC

D_Alex wrote: post #204

mattkrause wrote: post #173

Earlier quoted context omitted.

Two reasons I think this is not the way to go: First, the cost would be insane. A century of monthly MRIs is 1200 scans per person, or 1.2B scans to finish your hypothetical dataset. We pay about $US 550/hr for scanner time, using a research scanner that's subsidized (i.e., we're just covering costs, not making a profit). The article doesn't say how long the scan is. You can burn as much scanner time as you want chas…

> You can burn as much scanner time as you want chasing resolution/quality, but an hour seems reasonable. Out of curiosity, what determines the speed of the MRI scan? Are massive improvements theoretically possible?

ML & better imaging algorithms should help a lot. Times could be reduced from 45min to 15min [1]. Scanning a beating heart can be reduced from 4min+ to 25sec [2]. Also ML can aid in comparing past images to current ones [3], which would give you quick insights into what changed.

Two ideas for time reduction I haven't seen discussed but perhaps might also help:

1. Don't scan at the same resolution across the whole body each time. Instead, focus on anomalous places that you wanted to monitor from the first high-res scan, or places that look anomalous in low res in the latest scan. Then dial up the resolution in those areas.

2. If better imaging algorithms existed that could account for very slight movements of the body (ala the heartbeat one above), perhaps prep time could be reduced by changing the physical layout of the scanner itself. The whole process of lying down and getting your head or whatever mounted in their plastic frame, then lifting the gurney and slowly sliding it into the machine.. it's all very slow.

Instead of laying down, what if you could just walk in and be upright and get scanned relatively quickly - basically a slightly longer but similar experience to a chest X-ray. There's upright MRIs right now but they're not very high res (0.7tesla instead of 1-3), very few exist, and I'm sure they still take some time to complete scans and have lots of error correction extra scans to correct for patient movement.

However, even with less time in scanner, there's a lot of fixed time cost of scheduling and patient prep (remove all metal things, wear this gown and these ear plugs, please don't freak out its really claustrophobic patient messaging), as well as still needing technicians.

I'm just a patient who's gotten some MRIs but it definitely feels like there's ways to cut the time down significantly.

[1] http://news.mit.edu/2011/better-mri-algorithm-1101

[2] https://phys.org/news/2017-10-technology-mri-scan.html

[3] http://news.mit.edu/2018/faster-analysis-of-medical-images-0...

Re: One whole-body MRI could replace multiple cancer scans

#209

Post by jedberg » Tue, May 21, 2019, 9:30 AM UTC

blub wrote: post #202

jedberg wrote: post #111

I've had this idea floating in my head for a while. Provide free annual full body MRIs to people, including being read by a radiologist, which they can take to anyone they want (doctor, lawyer, whatever). In exchange, they agree to send the org a copy of all their past and future medical records. The records are anonymized and tied to the MRIs. The MRIs and medical data is then pumped through machine learning algorit…

That's not a charity, it's the good ole model of paying with data. You might as well show ads to the patients while they're in the machine and evaluate their brainwaves to see which they like best.

Except no profit would be made on data. All the findings would be given away for free. So we'd need donations to pay for the machine, its upkeep, and the staff to run it.

So not really anything like the pay with data model.

Re: One whole-body MRI could replace multiple cancer scans

#210

Post by yyyyip » Tue, May 21, 2019, 10:17 AM UTC

whatshisface wrote: post #35

nknealk wrote: post #13

Many doctors hate full body scans. Every individual has a handful of anomalies which are almost always benign. They show up on full body scans and chasing them down comes with cost and patient risk. I have a hard time with reporting like this that doesn't quantify cost of biopsy on false-positives as well as cost of complications from examining false-positives. Source: worked in clinical research for 2 years.

Why can't a doctor see an anomaly and decide not to chase it down based on the same reasoning that they use to not scan for it? Is there some pointless legal trap related to malpractice where the only allowable "don't operate" decision happens when the doctor decides what to test for?

We had a medical student who had her abdomen scanned as part of teaching. They found a cystic looking thing on her pancreas. She ended up getting it excised - it was benign and would've never caused problems, but she had multiple complications and 2 months in hospital as a result of the surgery.

I think Doctors (I am one) definitely err on the side of overtreating in those uncertain situations. Just like politicians, it feels more caring to act than to not act.

If you MRI 1000 people and leave the vague results in the hands of a bunch of physicians, they will tend to be interventional. This will lead to a spate of overtreatment.

Ways around this would be to consent patients for watchful waiting in the case of uncertain lesions. Even so, telling people they have weird looking lumps that you're not going to treat will cause serious anxiety.