Recently a Chinese media interviewed me and I talked about a few side projects I have done in the past. I talked about the Neuralrad Mammo Screening project and Neuralrad multiple brain mets SRS platform. More awareness on radiation therapy to the general public will greatly help the community and we believe Stereotactic Radiosurgery (SRS) will eventually replace majority of the whole brain radiation therapy (WBRT) in the next five years.
Super effort. I understand your reluctance to accept funding but if you ever change your mind on that be sure to publish it here on HN. If giving you more tools means more progress in this domain without the usual red tape then I'm all for giving you as much of a push as possible.
What's the best way to contact you? I've been fighting brain cancer for 7 years and work closely with a group of neuro-oncologists, researchers, non-profits, and investors in the space.
WBRT is pretty brutal. Am I right in thinking you are focusing on multiple site treatment/palliative treatment of metastatic presentations? High site count also or sticking to say < 5?
Where did you learn to program on distributed Nvidia GPUs? The article implied you were self taught and learning to do this is quite challenging for various reasons.
Not least, Nvidia's documentation is not the best resource to learn from. This seems like quite a lot of work to understand ML and write custom CUDA code to get this to work. Do you have any insight about how you taught yourself these things and what tools you use?
Imagine for a moment if FB and Google took all their developers and resources and applied it to solving cancer, how long do you think it would take to make a dent in the problem space? Or is there a hard limit stopping us from progressive like Moores law for scientific understanding.
Sir, We've all been hearing that AI will revolutionize medical diagnostics for a long time, seen startups come & go in this space but seeing your work impact lives on the ground has convinced me that the secret missing ingredient was a self-less human who can build an accessible(non-commercial) solution for the masses.
A decade ago I did a voluntary work on a simple app for oral cancer detection(questionnaire, data-entry) with an oncologist, Who used it to for survey in the tribal regions of India and he used to say how lack of early detection is the number one reason for so many deaths(many die without knowing that they had cancer).
He's now settled in Germany, But I would still pass this story to him & perhaps his colleagues in India could make use of it.
Hi. Some great projects. What's more commendable is your dedication towards your projects and seeing them through to end- to the point that they are actually useful. This is what I truly admire.
I have a question for you. What is the tech stack that you use?
And if it is not too much: What resources did you use to learn Deep Learning?
> Recently a Chinese media interviewed me and I talked about a few side projects I have done in the past.
I apologize if this has been asked and answered before, but do you speak Mandarin, or was the interview in English?
Asking out of curiosity if it’s the former, and if so, how difficult was it to learn whilst also working on this and other things? And are there any resources or tips you might share that you found helpful?
Great work. I'm inspired seeing others use their skills to work on something important. So many of the smartest, most well educated engineers of my generation have put their talents to use doing things that are of little value to society. Thank you for demonstrating to us what else is possible.
Unless it's more expensive than existing treatments the medical industry will close the circles around you excluding you.
That's why not one startup has hacked healthcare in America, not one. No breakaway successes making pharma cheaper. Like those incubators in Bangladesh, for premature babies not startups that is, those did OK. Some pill startups yes, but again that's an expensivification of medicine. If you can make medicine more expensive, they welcome you in!
Jim Clark tried this, he was on a roll after Silicon Graphics and Netscape. Huge roll about as strong as Elon Musk as a serial entrepreneur. Then he targeted healthcare and couldn't do shit, just couldn't get anything to happen. He literally talked about getting "rid of all the assholes" by which he meant insurance and doctors and hospitals and middlemen and pharma and all the other "assholes" of that nature in his own words, but leave "only one asshole in the middle--us [paraphrased]." It's in a book. That book also talks about guys going on airplanes and chasing goats off cliffs, saying "Some people do this."
Well the real structure of medicine isn't designed around the human body, it's designed around cornering the market. Market dominance. So of course it has this immune system against cost reduction and efficiencies--efficiencies especially--and you do know it lobbies, don't you? And can bribe the FDA like the Sacklers did? Or lobby the FDA, and then bribe underneath so when people see favoritism they think it's the over-the-counter placebo causing a placebo effect without suspecting an additional more potent under-the-table dosage of money. In case the administration has built up a tolerance to the over-the-counter stuff.
Super impressed. Amateurs can and do play their parts in science --- there are numerous discoveries made in astronomy, mathematics, and definitely in computer applied sciences that sprang from the minds of amateurs.
As a “professional” programmer, I’m humbled by your accomplishments. I really must find ways to contribute more to the world. It seems there’s a lot of opportunities in AI to do it.
In the UK the NHS don't do screening for breast cancer for under 50s because it's believed that it would do more harm than good by leading to unnecessary treatment for cancers that would never have actually caused any harm, and even where no treatment is carried out it causes great distress. Though there are arguments that the age cut off is too high, and should be set at 40.
The above is with regard to a well-funded and regulated screening program that presumably has much better precision/recall than this website. I wonder what the cut off age is for this website before the diagnoses cause more harm than good? 60? 70?
This is getting lots of upvotes because it's confirmation bias for the large segment of HN readers who believe that problems would easily be solved by a small number of brilliant technologists, if only it weren't for governments and big organisations with all their rules and regulations.
A lot of people, including myself, don’t believe that central health authorities have the right to make that call.
Moreover, I personally don’t have confidence in their ability to make those kinds of decisions, and I believe the abysmal performance of the NHS supports my view.
This is absurd logic. If the next step for a test like is a procedure with a lot of risk, change the next step.
We need to be able to work in a world with frequent, imperfect, low cost diagnostic tools. Cancer is almost completely survivable if caught early enough. So working to figure out early detection is effectively the "cure" for cancer we have been looking for.
I'm always surprised with the "just close your eyes" attitude of medical policies. I mean, this way we essentially choose when to get women misdiagnosed? Isn't the solution to get a better idea of how common it is for non-cancerous masses to appear and adjust the risk predictions? Or to actually improve the diagnostic methods?
1) I just downloaded the "The Mammographic Image Analysis Society database of digital mammograms" [0] and ran it against the tool [1] image by image. Results below, code here [2]:
true_pos 36
true_neg 207
false_pos 63
false_neg 16
total 322
2) How is it true when the site [1] says "We will not store your data on our server. Please don't worry about any privacy issues." when you can find all analyzed mammograms under the "static" directory?
Thank you for your efforts for validation and I appreciate that. There is a script running in the background to auto clean the files in static folder every day.
This is very cool work. I'm a radiologist, I also work on developing ML/AI based systems for cancer detection and characterization. Literally just took a break for a few minutes from creating some labels and saw this as the top HN post!
I think in some ways making the model available online can be good, but in other ways could be harmful too. Very complicated topic.
What peer review or regulatory approval process has this been through? Seems pretty irresponsible -- there are many notorious pitfalls encountered with ML for medical imaging. You shouldn't play with people's lives.
ETH will soon move from PoW to PoS (let's not debate the timeline or if it is a good idea). This will put about 32 million GPUs worth of compute and millions of CPUs searching for something else to do (or just flood the market with used equipment).
I have been searching, for years, for alternative workloads for these GPUs beyond just PoW mining and password cracking. Many of them are on systems with tiny cpus, little memory, little disk, little networking so the options are heavily limited. AI/ML/Rendering/Gaming actually make bad use cases.
If anyone has thoughts on this, I'd appreciate hearing them. Let it all die is certainly an option, but it also seems just as wasteful as keeping it going. Maybe we can find a better use case, like somehow curing cancer...
If anyone ever needs an example of how crypto is doing harm to the world: "Due to crypto mining, GPUs were in severe shortage and very over-priced on eBay"
The over-valuation of crypto is a two-fold negative impact on society: a massive brain-drain sucking talented engineers who would otherwise be solving real problems, and the opportunity cost of GPUs burning electricity to run unintentional ponzi schemes instead of training deep learning models.
* The free AI breast cancer detection website took coolwulf about three months of spare time, sometime he had to sleep in his office to get things done, before the site finally went live in 2018
* The website also gained a lot of attention from the industry, during which many domestic and foreign medical institutions, such as Fudan University Hospital, expressed their gratitude to him by email and were willing to provide financial and technical support
* Afterwards, he and Weiguo Lu, now a tenured professor at University of Texas Southwest Medical Center, founded two software companies targeting the radiotherapy and started working on product development for cancer radiotherapy and artificial intelligence technologies
* But in 2022, he returned with an even more important "brain cancer project"
* coolwulf (Hao Jiang) (right) He told us that his parents are not medical professionals, and his interest in programming was fostered from a young age
* A reliable AI for tumor detection can enable a large number of patients who cannot seek adequate medical diagnosis in time to know the condition earlier or provide a secondary opinion
* He said that he’s not sure actually how many people have used it because the data is not saved on the server due to patient privacy concerns
It's an interesting subject, with a long history; I think many of the biggest challenges are not technical.
The first commercially available AI/ML approach to breast cancer screening was available (US) in the late 90s. There have been many iterations and some improvements since, none of which really knock it out of the park but most clinical radiologists see the value. Perhaps the more interesting question then is why are people getting value out of uploading their own scans, i.e. why does their standard care path not already include this?
'Amateur' oughtn't be scare-quoted because it's not a slur, many of the finest programmers were amateurs for many years before they were old enough to be given a job in the profession.
As an AI/ML researcher who publishes in this area regularly, I will be using this as a case study for AI ethics classes. That this is allowed to go on is shocking.
> In 2018, a programmer named “coolwulf” started a thread about a website he had made. Users just need to upload their X-ray images, then they can let AI to carry out their own fast diagnosis of breast cancer disease.
Literally the worst fears that we have as a community is that people will recklessly apply ML to things like cancer screening on open websites and cause countless deaths, bankruptcies, needless procedures, etc. How many people went to this website, uploaded images, were told were ok and didn't follow up? How many were told they have cancer and insisted on procedures they didn't need?
The website is totally unaccountable. Totally unregulated. Totally without any of the most basic ethical standards in medicine. Without even the most basic human rights for patients. This is frankly disgusting.
In the US this would have been shut down by the FDA immediately.
We should not be celebrating this unethical "science" that doesn't meet even the most basic of scientific standards or ethical standards.
Admittedly I just skimmed the article but I feel like the title should be more - "This "amateur" medical...". His primary expertise is more physics/CS/programmer related than it is human biology/medicine.
> As for why he doesn't commercialize the website and collect some money, this question was also asked by us.
You don't get into open source development for the big bucks. It's sort of like asking someone who starts a soup kitchen why they don't open a restaurant.
I think it's worth noting how open source development spurs technical innovation in a way commercial development does not. If a company develops a proprietary technology, almost nobody will get access to the source or datasets, and so it can't then be reused and built upon to advance the state of the art. If it's open source, everyone can build on it and improve things. Sort of like how science needs to be public in order to develop more science.
But just as we need large investments to push science further, we should also have large investments in open source. We need to make access to these 50-GPU clusters easier for open source research, so a lone developer doesn't have to built it himself. Some meager funding for the actual development would be nice too... How many OSS researchers could we fund at $35K per?
Reading this article only makes me realise how crypto industry has crippled the progress independent researchers like this would badly need gpus for AI.
How many really useful, cool and meaningful projects are stuck because such authors can't find or afford gpus - as they are being used to calculate meaningless hashes instead :/
> In short, it is to let the AI help you "look at the film", and the accuracy rate is almost comparable to professional doctors, and it is completely free.
>> Furthermore, the accuracy of tumor identification has reached 90%.
How is this accuracy calculated? Further in the article it is noted that there is no patient data saved by the project:
>> He said that he’s not sure actually how many people have used it because the data is not saved on the server due to patient privacy concerns. But during that time, he received a lot of thank-you emails from patients, many of them from China.
Considering user privacy is laudable in my opinion, but I'm still curious to know how accuracy is known.
[+] [-] coolwulf|3 years ago|reply
Here is the link to the original article: https://www.toutiao.com/article/7094940100450107935/
[+] [-] jacquesm|3 years ago|reply
[+] [-] pen2l|3 years ago|reply
What a beacon of light and inspiration you are. Thanks for your work.
That said, I welcome you to publish your work so it can become even better after a formalized peer-review process.
[+] [-] jabrams2003|3 years ago|reply
I'd love to chat.
[+] [-] ska|3 years ago|reply
[+] [-] onetimeusename|3 years ago|reply
Not least, Nvidia's documentation is not the best resource to learn from. This seems like quite a lot of work to understand ML and write custom CUDA code to get this to work. Do you have any insight about how you taught yourself these things and what tools you use?
[+] [-] abfan1127|3 years ago|reply
[+] [-] sizzle|3 years ago|reply
[+] [-] Abishek_Muthian|3 years ago|reply
A decade ago I did a voluntary work on a simple app for oral cancer detection(questionnaire, data-entry) with an oncologist, Who used it to for survey in the tribal regions of India and he used to say how lack of early detection is the number one reason for so many deaths(many die without knowing that they had cancer).
He's now settled in Germany, But I would still pass this story to him & perhaps his colleagues in India could make use of it.
Thank you.
[+] [-] Simon_O_Rourke|3 years ago|reply
[+] [-] llaolleh|3 years ago|reply
[+] [-] rg111|3 years ago|reply
I have a question for you. What is the tech stack that you use?
And if it is not too much: What resources did you use to learn Deep Learning?
[+] [-] koprulusector|3 years ago|reply
I apologize if this has been asked and answered before, but do you speak Mandarin, or was the interview in English?
Asking out of curiosity if it’s the former, and if so, how difficult was it to learn whilst also working on this and other things? And are there any resources or tips you might share that you found helpful?
[+] [-] adultSwim|3 years ago|reply
[+] [-] FpUser|3 years ago|reply
[+] [-] daniel-cussen|3 years ago|reply
That's why not one startup has hacked healthcare in America, not one. No breakaway successes making pharma cheaper. Like those incubators in Bangladesh, for premature babies not startups that is, those did OK. Some pill startups yes, but again that's an expensivification of medicine. If you can make medicine more expensive, they welcome you in!
Jim Clark tried this, he was on a roll after Silicon Graphics and Netscape. Huge roll about as strong as Elon Musk as a serial entrepreneur. Then he targeted healthcare and couldn't do shit, just couldn't get anything to happen. He literally talked about getting "rid of all the assholes" by which he meant insurance and doctors and hospitals and middlemen and pharma and all the other "assholes" of that nature in his own words, but leave "only one asshole in the middle--us [paraphrased]." It's in a book. That book also talks about guys going on airplanes and chasing goats off cliffs, saying "Some people do this."
Well the real structure of medicine isn't designed around the human body, it's designed around cornering the market. Market dominance. So of course it has this immune system against cost reduction and efficiencies--efficiencies especially--and you do know it lobbies, don't you? And can bribe the FDA like the Sacklers did? Or lobby the FDA, and then bribe underneath so when people see favoritism they think it's the over-the-counter placebo causing a placebo effect without suspecting an additional more potent under-the-table dosage of money. In case the administration has built up a tolerance to the over-the-counter stuff.
[+] [-] mamborambo|3 years ago|reply
[+] [-] dclowd9901|3 years ago|reply
[+] [-] iaw|3 years ago|reply
[+] [-] sdo72|3 years ago|reply
[+] [-] rawgabbit|3 years ago|reply
[+] [-] nkzd|3 years ago|reply
[+] [-] hehepran|3 years ago|reply
[+] [-] rob_c|3 years ago|reply
[+] [-] Billsen|3 years ago|reply
[+] [-] sylware|3 years ago|reply
[+] [-] redeyedtreefrog|3 years ago|reply
The above is with regard to a well-funded and regulated screening program that presumably has much better precision/recall than this website. I wonder what the cut off age is for this website before the diagnoses cause more harm than good? 60? 70?
This is getting lots of upvotes because it's confirmation bias for the large segment of HN readers who believe that problems would easily be solved by a small number of brilliant technologists, if only it weren't for governments and big organisations with all their rules and regulations.
[+] [-] laingc|3 years ago|reply
Moreover, I personally don’t have confidence in their ability to make those kinds of decisions, and I believe the abysmal performance of the NHS supports my view.
[+] [-] mchusma|3 years ago|reply
We need to be able to work in a world with frequent, imperfect, low cost diagnostic tools. Cancer is almost completely survivable if caught early enough. So working to figure out early detection is effectively the "cure" for cancer we have been looking for.
[+] [-] mateo1|3 years ago|reply
[+] [-] adamredwoods|3 years ago|reply
Anecdotally, I know (directly and indirectly) many, many women who had breast cancer before 50 years of age.
[+] [-] gregsadetsky|3 years ago|reply
http://mammo.neuralrad.com:5300/static/mamo.jpg
http://mammo.neuralrad.com:5300/static/mammo.jpg
(trying file names at random)
[0] https://www.repository.cam.ac.uk/handle/1810/250394
[1] http://mammo.neuralrad.com:5300/upload
[2] https://github.com/gregsadetsky/mias-check
[+] [-] coolwulf|3 years ago|reply
[+] [-] themantalope|3 years ago|reply
I think in some ways making the model available online can be good, but in other ways could be harmful too. Very complicated topic.
恭喜coolwulf， 祝你继续成功。
[+] [-] tfgg|3 years ago|reply
[+] [-] latchkey|3 years ago|reply
I have been searching, for years, for alternative workloads for these GPUs beyond just PoW mining and password cracking. Many of them are on systems with tiny cpus, little memory, little disk, little networking so the options are heavily limited. AI/ML/Rendering/Gaming actually make bad use cases.
If anyone has thoughts on this, I'd appreciate hearing them. Let it all die is certainly an option, but it also seems just as wasteful as keeping it going. Maybe we can find a better use case, like somehow curing cancer...
[+] [-] chrischen|3 years ago|reply
The over-valuation of crypto is a two-fold negative impact on society: a massive brain-drain sucking talented engineers who would otherwise be solving real problems, and the opportunity cost of GPUs burning electricity to run unintentional ponzi schemes instead of training deep learning models.
[+] [-] westcort|3 years ago|reply
* The free AI breast cancer detection website took coolwulf about three months of spare time, sometime he had to sleep in his office to get things done, before the site finally went live in 2018
* The website also gained a lot of attention from the industry, during which many domestic and foreign medical institutions, such as Fudan University Hospital, expressed their gratitude to him by email and were willing to provide financial and technical support
* Afterwards, he and Weiguo Lu, now a tenured professor at University of Texas Southwest Medical Center, founded two software companies targeting the radiotherapy and started working on product development for cancer radiotherapy and artificial intelligence technologies
* But in 2022, he returned with an even more important "brain cancer project"
* coolwulf (Hao Jiang) (right) He told us that his parents are not medical professionals, and his interest in programming was fostered from a young age
* A reliable AI for tumor detection can enable a large number of patients who cannot seek adequate medical diagnosis in time to know the condition earlier or provide a secondary opinion
* He said that he’s not sure actually how many people have used it because the data is not saved on the server due to patient privacy concerns
Link to the technology: http://mammo.neuralrad.com:5300/
[+] [-] ska|3 years ago|reply
The first commercially available AI/ML approach to breast cancer screening was available (US) in the late 90s. There have been many iterations and some improvements since, none of which really knock it out of the park but most clinical radiologists see the value. Perhaps the more interesting question then is why are people getting value out of uploading their own scans, i.e. why does their standard care path not already include this?
[+] [-] OJFord|3 years ago|reply
[+] [-] light_hue_1|3 years ago|reply
> In 2018, a programmer named “coolwulf” started a thread about a website he had made. Users just need to upload their X-ray images, then they can let AI to carry out their own fast diagnosis of breast cancer disease.
Literally the worst fears that we have as a community is that people will recklessly apply ML to things like cancer screening on open websites and cause countless deaths, bankruptcies, needless procedures, etc. How many people went to this website, uploaded images, were told were ok and didn't follow up? How many were told they have cancer and insisted on procedures they didn't need?
The website is totally unaccountable. Totally unregulated. Totally without any of the most basic ethical standards in medicine. Without even the most basic human rights for patients. This is frankly disgusting.
In the US this would have been shut down by the FDA immediately.
We should not be celebrating this unethical "science" that doesn't meet even the most basic of scientific standards or ethical standards.
I can't believe this is getting upvoted here.
[+] [-] somethoughts|3 years ago|reply
[+] [-] notfed|3 years ago|reply
[+] [-] 0xbadcafebee|3 years ago|reply
You don't get into open source development for the big bucks. It's sort of like asking someone who starts a soup kitchen why they don't open a restaurant.
I think it's worth noting how open source development spurs technical innovation in a way commercial development does not. If a company develops a proprietary technology, almost nobody will get access to the source or datasets, and so it can't then be reused and built upon to advance the state of the art. If it's open source, everyone can build on it and improve things. Sort of like how science needs to be public in order to develop more science.
But just as we need large investments to push science further, we should also have large investments in open source. We need to make access to these 50-GPU clusters easier for open source research, so a lone developer doesn't have to built it himself. Some meager funding for the actual development would be nice too... How many OSS researchers could we fund at $35K per?
[+] [-] jonplackett|3 years ago|reply
Seems like 1/10 wrong would be bad, how does that compare with a doctor doing it?
[+] [-] ChicagoBoy11|3 years ago|reply
[+] [-] ghoomketu|3 years ago|reply
How many really useful, cool and meaningful projects are stuck because such authors can't find or afford gpus - as they are being used to calculate meaningless hashes instead :/
[+] [-] vmception|3 years ago|reply
In the US, the issue is getting the Xray
[+] [-] YeGoblynQueenne|3 years ago|reply
How is this accuracy calculated? Further in the article it is noted that there is no patient data saved by the project:
>> He said that he’s not sure actually how many people have used it because the data is not saved on the server due to patient privacy concerns. But during that time, he received a lot of thank-you emails from patients, many of them from China.
Considering user privacy is laudable in my opinion, but I'm still curious to know how accuracy is known.
[+] [-] Hitton|3 years ago|reply