AI Can Diagnose Prostate Cancer As Well As a Pathologist (sciencebusiness.net) 58
An anonymous reader quotes a report from Science Business: Chinese researchers have developed an artificial intelligence system which can diagnose cancerous prostate samples as accurately as any pathologist, holding out the possibility of streamlining and eliminating variation in the process of cancer diagnosis. The system may also help overcome shortages of trained pathologists and in the longer term lead to automated or partially-automated prostate diagnosis. Confirmation of a prostate cancer diagnosis normally requires a biopsy sample to be examined by a pathologist. Now the Chinese AI system has shown similar levels of accuracy to pathologists and can also accurately classify the level of malignancy of the cancer, eliminating the variability which can creep into human diagnoses. [Hongqian Guo, who led the research group] took 918 prostate samples from 283 patients and ran these through the AI system, with the software gradually learning and improving diagnosis. The pathology images were subdivided into 40,000 smaller samples of which 30,000 were used to train the software while the remaining 10,000 were used to test accuracy. The results showed an accurate diagnosis in 99.38 per cent of cases, using a human pathologist as a gold standard. Guo said that means the AI system is as accurate as a pathologist. The research was presented at the 33rd European Association of Urology Congress in Copenhagen.
Sure it can, (Score:2)
Re: (Score:2)
The computer then looks back over work and looks at a new medical sample.
A human expert with decades of experience at a teaching hospital who has written books would have done all the work.
A human also has the skill to know when to seek other experts with decades of experience around them to consult with.
The other aspect to worry about is what to do with the result.
A result cant just be sent out withou
Re: (Score:1)
Who is Al? I am really confused here.
Re: Sure it can, (Score:3, Informative)
How pathology works (Score:3)
5. The diagnosis is made. For this until now you need a specialized pathologist with many years of experience and very expensive training to look at the photos and give you his opinion of whether this is cancer he's looking at in the photos or not. Or apparently now you can use a computer program to check out the photos and give you an almost equally accurate opinion.
It's not really like that when you get into the details. My wife is a pathologist. First off anatomic pathologists [wikipedia.org] do not look at photos as a general proposition. They look at slides under a microscope for the most part. There are some pathology imaging systems but they are not in widespread use currently for both cost and technical reasons. It turns out to be technically challenging and expensive in many cases to make an image of every slide with sufficient detail to be useful - it's cheaper and more
Re: (Score:2)
Re: (Score:3, Funny)
My nurse scowled at me when I laughed when she told me to jack off a sample for her. I started to stroke the cup and she looked like she was going to smack me. It good being from Brasil. Americans have no sense of humor.
Yeah.. dental nurses can be like that.
Re: (Score:2)
Come on man, I swear AI works! I have only met compatible mates since I use AI driven dating sites.
Butt...butt... (Score:2)
I'm not sure I'm ok with a robot examining me like that. I prefer the awkward wriggling fingers of a real human, and the incredibly strained communication before and after.
Some things do require a human touch.
Like my prostrate.
Lemmiwinks (Score:1)
I prefer a more natural approach to the prostate exam.
Re: (Score:2)
Re: (Score:1)
Yes, but cars don't go up the butt. This will save millions of homophobes from being penetrated by another man.
Welp! someones out of a job (Score:2)
As Well As a Pathologist (Score:2)
Re: (Score:2)
I thought Pathologist another illness...
Re:As Well As a Pathologist (Score:4, Informative)
I am very skeptical whether we have any idea who is a good pathologist and who is a bad one. What is the Truth Table we use to figure out whether a particular pathologist is good?
There is strong circumstantial evidence that American doctors significantly overtreat suspected cancers. You know what happens when you as an oncologist treat as cancer something that is not dangerous? Your survival rate goes up! And the patient, who has suffers enormous physical and psychological damage during the year or so of controlled poisoning (chemo) enters into the throngs of The Cult of Cancer Survivors, who will testify about his or her brush with death and how we need more aggressive cancer screenings so that cancer survival rates can continue to go up.
Re: (Score:3)
I am very skeptical whether we have any idea who is a good pathologist and who is a bad one.
It is hard to evaluate doctors. Kaiser (a big American health company) tried to evaluate their doctors by patient outcome. It didn't work because the best doctors tended to have the worst record of good outcomes. Why? Because, since they were the best, they were often assigned the worst-case patients.
Re: (Score:2)
Re: (Score:2)
Evaluating doctors based on patient outcome for different patients is almost certainly not going to work well unless you can control for an enormous number of factors. Doctor evaluations should be based on patients getting a diagnosis from multiple doctors and then comparing those diagnosis and eventual outcomes. It wouldn't be rocket science, but it would incur the cost of multiple doctors providing care to the same patient.
Re: (Score:3)
I am very skeptical whether we have any idea who is a good pathologist and who is a bad one
From TFS "The results showed an accurate diagnosis in 99.38 per cent of cases". Only a (very) good pathologist would reach such a high %, thus "as well as a pathologist" should be "better than a pathologist".
Re: (Score:2)
Accuracy of diagnosis. In case of a pathologist, this isn't about curing people. It's about being correct in one's diagnosis of potentially having specific kinds of cancer. You're confusing oncologist, the doctor who actually works on cancer treatment with pathologist, the people who's only job is to analyse the sample in front of him for pathological elements that shouldn't be there in healthy sample.
You take one sample, split it in two, get a doctor you want to test analyse one sample, get other analysed
Evaluating percent of correct diagnoses (Score:2)
Accuracy of diagnosis. In case of a pathologist, this isn't about curing people. It's about being correct in one's diagnosis of potentially having specific kinds of cancer.
Careful there. The "correct" diagnosis is only found out by the disease process evolving. What pathologists are trying to find is the diagnosis that meets the standard of care based on the available evidence. Pathologists are essentially being asked to gaze into the future and guess how a disease process will progress. They never have enough information to be right 100% of the time. Its a little like predicting the weather in that regard. So you evaluate pathologist performance by their accuracy in re
Re: (Score:2)
You are confusing oncologist with pathologist. Pathologists study existing samples for existing conditions. I.e. signs of tumours, which if found are analysed to find out if tumour is benign or malignant.
Oncologist is the one that "gazes into the future" to figure out the optimal treatment.
One is the doctor who's job is solely to analyse the sample for existing conditions. Other is the doctor that formulates the diagnosis based on, among other things, pathologist's report and then formulate the treatment pl
Pathology is not just sampling (Score:2)
You are confusing oncologist with pathologist. Pathologists study existing samples for existing conditions.
I'm married to a pathologist and I've worked in and around pathology labs. I assure you that there is no confusion here about what they do. You on the other hand are not actually well informed about what pathologists actually do as evidenced by your comments.
Oncologist is the one that "gazes into the future" to figure out the optimal treatment.
All doctors have to make guesses based on probabilities. The reason we have specialists like pathologists is that medicine is a team activity and you need multiple experts to get the diagnosis in many cases. It's no different than ER doctor calling
Re: (Score:2)
Your entire early tirade can be summed up as "it's not 100% certain, therefore they have to guess".
I have news for you. Even in engineering analysis, where you know every bolt and every weld, and where you have access to detailed plans, troubleshooting is still not 100%. Medical profession is ultimately engineering for a body that you cannot just shut down and disassemble, and must treat while it's functioning. It's fairly obvious that it's never going to be 100%. Nor does this interact with my argument in
Evaluating pathologist performance (Score:2)
I am very skeptical whether we have any idea who is a good pathologist and who is a bad one.
We do. Pathologists tend to have their work checked a lot (plus it's an accreditation requirement) so other pathologists tend to have a pretty good idea who is good and who isn't. (I know this because my wife is a pathologist) There also is a lot of clinical outcome data out there so it's pretty easy to correlate that to accuracy in diagnosis in pathology. Also if you want to know who is a good clinician the best person to ask is often a pathologist because they get to see the clinicians work. If you
Re: (Score:2)
Thank you, for an informative reply.
I still do not understand how you know that overtreatment is not occurring. You can detect anomalous numbers deaths that are the result of significant undertreatment. How do you know treatment is too aggressive?
A woman with a tiny lump is rushed under the knife -- lump and nearby lymph nodes are removed. She is immediate given chemo. She does not die of cancer in one year or five years. Maybe that lump was not very dangerous in the first place?
Have there actually bee
Certainty (Score:2)
I still do not understand how you know that overtreatment is not occurring.
In some cases it certainly is occurring. Sometimes this is appropriate and many others it is not. But it's a more nuanced problem than you might realize.
How do you know treatment is too aggressive?
Several ways but primarily you can compare the pathology to the treatment. If you start seeing treatment disproportionate to expectations for a given diagnosis then you have evidence that over treatment (and by extension over billing) is occurring. This is essentially a statistical evaluation. Also you or the doctor can solicit second (or third) opinio
Butt Bot (Score:1)
not sure I like the sound of that
Re: (Score:1)
Um, it's a joke.
Okay, attempted joke.
Fine, failed joke. Happy!?
Re: (Score:2)
.
Given peer review, and
AI driven, robotic assisted prostate exams (Score:2, Informative)
Please pull down your pants and bend over. You have twenty seconds to comply [youtu.be]
Accuracy? (Score:2)
I wish summaries would include FP and FN rates,
Determination of cancer from images is hardly new - we were showing excellent FP and FN rates for breast cancer in research we were doing ~15 years ago. It's nice to see another useful application, though.
In terms of the use of subdivision of samples, I'd like to see evidence of a clustering of those samples, to ensure there is not hidden information. Given it's peer reviewed, I assume that will have been done.
Re: (Score:2)
The long standing advice for men under 70 not to even screen for prostate cancer which , no surprise , seems to be changing again https://edition.cnn.com/2017/0... [cnn.com]
My father is 92 and recently started treatment for prostate cancer. His urologist says that if you biopsy every man at that age, over 90% will be positive for prostate cancer, but few will actually die from it. What matters is how aggressive it is (the so called Gleason score - https://en.wikipedia.org/wiki/... [wikipedia.org] ) as it only becomes dangerous when it starts to spread to other organs. This appears to be what the article says AI can determine as well as a pathologist.
PSA testing is not a good way to detect
I pathologist a new disease? (Score:3)
I did not know that pathologist was a disease, must be one of these new psychiatric conditions that keep popping every now and than. Anyway I'm happy that an AI can diagnose that.
Also, looking forward to see the automated "you got cancer" email, written by an underpaid Indian contractor.
Re: (Score:1)