Re: Digital imaging ethics as pertaining to the enhancement of microscopy images with artificial intelligence

Posted by Ralf Palmisano on
URL: http://confocal-microscopy-list.275.s1.nabble.com/Digital-imaging-ethics-as-pertaining-to-the-enhancement-of-microscopy-images-with-artificial-intellie-tp7588915p7588927.html

*****
To join, leave or search the confocal microscopy listserv, go to:
http://lists.umn.edu/cgi-bin/wa?A0=confocalmicroscopy
Post images on http://www.imgur.com and include the link in your posting.
*****

Hi Andreas,

I agree in the broader picture, but I do think that will be within my
estimated time of departure as a carbon based "intelligent" life form on
this planet... :-)
And in remembrance of Philip K. Dick:
"Everything in life is just for a while."

Cheers
Ralf

Am 19.11.2018 um 14:38 schrieb Andreas Bruckbauer:

> *****
> To join, leave or search the confocal microscopy listserv, go to:
> http://lists.umn.edu/cgi-bin/wa?A0=confocalmicroscopy
> Post images on http://www.imgur.com and include the link in your posting.
> *****
>
> Ralf, AI will one day be able to discover the “unknown” just as humans do, knowing their field, looking out for things which do not fit into the current theoretical framework, forming a new hypothesis, doing experiments and modifying the hypothesis.... the robot scientist is waiting to replace us, obviously there is long way to go
> http://aiweirdness.com/post/172894792687/when-algorithms-surprise-us
>
> Andreas
>
>
>
> Sent from my phone
>
>> On 19 Nov 2018, at 10:59, Ralf Palmisano OICE <[hidden email]> wrote:
>>
>> *****
>> To join, leave or search the confocal microscopy listserv, go to:
>> http://lists.umn.edu/cgi-bin/wa?A0=confocalmicroscopy
>> Post images on http://www.imgur.com and include the link in your posting.
>> *****
>>
>> Benjamin, thanks for pointing out all this which I fully agree with!
>>
>> One more from my side.
>> How can I ever trust AI if I am exploring terra incognita by imaging, which quite often is the case, that's why quite a few of us are doing imaging.
>> How could (whatever background) AI ever produce data that are not known yet. How could IT know what is unknown???
>>
>> Cheers Ralf
>>
>>> Am 18.11.2018 um 23:19 schrieb Benjamin Smith:
>>> *****
>>> To join, leave or search the confocal microscopy listserv, go to:
>>> http://lists.umn.edu/cgi-bin/wa?A0=confocalmicroscopy
>>> Post images on http://www.imgur.com and include the link in your posting.
>>> *****
>>>
>>> Here are my two cents, I think the simplest rubric for using an AI
>>> algorithm in science is, "Have I ever seen a paper where this was done by
>>> hand?"
>>>
>>> For example, tracking objects, identifying subsets of objects, counting
>>> objects are all the types of image processing tasks that have been done by
>>> hand, and therefore are excellent candidates for AI.  The reason these are
>>> valid is that a human can look at the data and immediately ascertain the
>>> result, but the challenge is in coming up with a computational algorithm
>>> that will robustly define the problem as clearly as we are seeing it.
>>> Whenever I teach people computational image processing, I always point out
>>> that there are certain tasks that are trivial for computers but are
>>> non-trivial for humans (convolutions, counting and measuring thousands of
>>> objects, measuring distances between all pairs of objects, etc.) and tasks
>>> that are often trivial for humans but non-trivial for computers (image
>>> segmentation in a complex feature space, tracking objects in a 2D image
>>> that can cross in 3D space, etc.), and therefore sometimes the best
>>> solution is to write an algorithm that lets the human do the things they
>>> are good at, and the computer does the rest.
>>>
>>> To me, the goal of AI in image processing is to replicate what we as
>>> researchers would have done anyway, just in a manner where the computer
>>> does it on its own.  For example, using a well designed convolutional
>>> neural network to learn to segment an image is an excellent application.
>>> You could find an segmentation algorithm by hand, tuning bandpass filters,
>>> trying different convolutions, adjusting both the magnitude and order of
>>> these parameters to get to some lowest energy state.  With convolutional
>>> neural networks, computers can effectively perform this exact same task,
>>> and even in relatively the same manner that we would have, allowing us to
>>> go do something else.  On top of that, they can search a much broader
>>> parameter space than anyone would ever want to do by hand, and therefore
>>> possibly come up with an even more robust algorithm than we could have.
>>> Therefore, if it will likely be faster to build a training dataset than to
>>> try and explore the entire parameter space needed to segment an image, AI
>>> is a good candidate for these tasks.
>>>
>>> Using the same rubric I mentioned at the start, I have never seen a paper
>>> where someone showed an artist a bunch of high resolution images, and then
>>> asked them to draw high resolution interpretations of low resolution
>>> images, and then publishing meaningful conclusions from this (for example,
>>> scientific conclusions should not be drawn from artistic renderings of
>>> exoplanets).  The reason we don't do this is that the task is premised on
>>> the assumption that the low resolution images have the same feature space
>>> as the high resolution ones.  Therefore, the only case where the assumption
>>> that the artist's renderings are correct are if our low resolution images
>>> have the same information as the high resolution ones, meaning the low res
>>> images are completely redundant and useless in the sense that they offer no
>>> additional information.
>>>
>>> Along these lines, asking a neural network to draw in features in images
>>> based on previous images is not science, because you are forcing the
>>> assumption that all the data matches the hypothesis.  Google's DeepDream is
>>> an excellent case of this, where depending on what the algorithm was
>>> trained on, it will then put those features into any other image.  This is
>>> a great video explaining the impact of using different network layers in
>>> image reconstruction: https://www.youtube.com/watch?v=BsSmBPmPeYQ
>>>
>>> Therefore, if you use a neural network in image reconstruction, what you
>>> are really doing is having a computer or artist to draw a high resolution
>>> version of your image that matches your hypothesis.  While this is
>>> inherently not science (as you are changing the data to match your
>>> hypothesis, rather than the other way around), this type of image
>>> reconstruction still has a place in medical science.  For example, a human
>>> body does have a well defined and constrained feature space.  As such, if
>>> you took a low-res CT scan of a human, reconstruction that image based on a
>>> training set of a human would create a meaningful image that could guide
>>> diagnoses, and allow for significantly lower X-ray exposure to the
>>> patient.  Therefore, while AI image reconstruction in science appears to be
>>> a case of circular logic, in medicine it can have very meaningful
>>> applications.
>>>
>>> Just my own to cents, and looking forward to hearing other people's
>>> insights,
>>>     Ben Smith
>>>
>>> On Sun, Nov 18, 2018 at 3:55 AM Andreas Bruckbauer <
>>> [hidden email]> wrote:
>>>
>>>> *****
>>>> To join, leave or search the confocal microscopy listserv, go to:
>>>> http://lists.umn.edu/cgi-bin/wa?A0=confocalmicroscopy
>>>> Post images on http://www.imgur.com and include the link in your posting.
>>>> *****
>>>>
>>>> Thanks John for bringing us up-to date on image processing, these are
>>>> indeed very important developments. I think there will be great changes
>>>> coming over the next years driven by the AI revolution in image and video
>>>> processing. But the fundamental limit should is that one cannot increase
>>>> the information content of an image beyond what was originally recorded. Of
>>>> course the missing information can be replaced by knowledge derived from
>>>> other images. But then the new AI algorithms will have similar flaws as
>>>> human perception (optical illusions). Science should be about measuring
>>>> accurately instead of guessing.
>>>> My criticism of current publications and promotional videos in image
>>>> processing using AI is that they show the cases when the algorithms
>>>> actually work well (which might be most of the time), the important
>>>> question is when do they fail and produce the wrong results? With the fast
>>>> development in the field, today's problems are often solved a few days
>>>> later with a new generation of the algorithm, so detecting flaws in these
>>>> algorithms is an ungrateful task. But I think it is important and we will
>>>> need to come up with very good quality control standards to accept these
>>>> results for medical imaging or scientific publications.
>>>> A few years ago I was very excited about using compressed sensing in
>>>> microscopy to "break the Nyquist barrier", but after looking into this in
>>>> more detail, I came to the conclusion that this only works well when images
>>>> are already heavily oversampled like in normal photography (more megapixels
>>>> sell better). When microscopy data is taken at the resolution limit there
>>>> is not much room for further compression. I would expect the same for
>>>> neural network approaches, works well when you have a lot of pixels and the
>>>> information content is not so high or accuracy is not so important.
>>>> So the question is what is actually necessary for a given experiment? If
>>>> one wants to track some cells in a fluorescence time laps movie, maybe
>>>> noisy (low exposure) jpeg compressed data combined with the latest AI
>>>> algorithm trained on this problem is better than the perfect exposure
>>>> needed for current segmentation methods and raw data recording, as in the
>>>> latter case the cells might be killed a short time after the experiment
>>>> started by the higher light exposure.
>>>> best wishes
>>>> Andreas
>>>>
>>>>
>>>>
>>>> -----Original Message-----
>>>> From: John Oreopoulos <[hidden email]>
>>>> To: CONFOCALMICROSCOPY <[hidden email]>
>>>> Sent: Sat, 17 Nov 2018 2:33
>>>> Subject: Digital imaging ethics as pertaining to the enhancement of
>>>> microscopy images with artificial intelligence
>>>>
>>>> *****
>>>> To join, leave or search the confocal microscopy listserv, go to:
>>>> http://lists.umn.edu/cgi-bin/wa?A0=confocalmicroscopy
>>>> Post images on http://www.imgur.com and include the link in your posting.
>>>> *****
>>>>
>>>> Earlier today a few people (including myself) brought up Doug Cromey's
>>>> excellent treatise on digital imaging ethics in a related thread that dealt
>>>> with training new microscope users within a research setting. Lately I've
>>>> been hearing a lot about applications of machine learning and artificial
>>>> intelligence to "improve", "de-noise", or "fix" images (microscopy or
>>>> otherwise), extracting new information from low-resolution images, and even
>>>> creating new 3D views of samples with very little information. Here is just
>>>> one such example from Nvidia and MIT:
>>>>
>>>>
>>>> https://news.developer.nvidia.com/ai-can-now-fix-your-grainy-photos-by-only-looking-at-grainy-photos/
>>>>
>>>> https://www.youtube.com/watch?time_continue=84&v=pp7HdI0-MIo
>>>>
>>>> It's clear that the microscopy world will eventually come to a head with
>>>> this technology. I think I've seen a few research articles on this topic
>>>> now, and this month's issue of Nature Methods has a paper on this topic too:
>>>>
>>>> https://www.nature.com/articles/s41592-018-0194-9
>>>>
>>>> I've been wondering if and how Cromey's guide for digital imaging ethics
>>>> should be altered when it comes to AI-assisted microscope imaging. Should
>>>> it be allowed/accepted? Other readings of mine on AI show that machine
>>>> learning algorithms can produce biased results if the training datasets are
>>>> incomplete in some way, and the very nature of machine learning makes it
>>>> difficult to understand why it produced a certain result, since the deep
>>>> learning neural networks that are used to generate the results are
>>>> essentially black boxes that can't easily be probed. But on the other hand,
>>>> I'm constantly blown away by what I've seen so far online for other various
>>>> applications of AI (facial recognition, translation, etc.).
>>>>
>>>> I also just finished a good read about AI from the perspective of
>>>> economics:
>>>>
>>>> https://www.predictionmachines.ai/
>>>>
>>>> https://youtu.be/5G0PbwtiMJk
>>>>
>>>> The basic message of this book is that AI makes prediction cheap. When
>>>> something is cheap, we use more of it. Other processes that complement
>>>> prediction, like judgement (by a human or otherwise) becomes more valuable.
>>>> It's easy to see how the lessons of this book could be re-framed for
>>>> imaging science.
>>>>
>>>> Curious to know the community's opinion on this matter. I used to laugh at
>>>> the following video, but now I'm not laughing:
>>>>
>>>> https://www.youtube.com/watch?v=LhF_56SxrGk
>>>>
>>>> John Oreopoulos
>>>>
>> --
>> Ralf Palmisano
>> Head - Optical Imaging Centre Erlangen
>>
>> Fellow Royal Microscopical Society
>> Member Royal Society of Medicine
>>
>> Speaker Scientific Advisory Board "German Society for Microscopy and Image Analysis"
>> Board of Directors Core Technologies for Life Science
>>
>> Hartmannstr. 14
>> 91052 Erlangen, Germany
>>
>> +49-9131-85-64300 (Office)
>> +49-9131-85-64301 (Secretary)
>> +49-9131-85-64302 (Fax)
>>
>> www.oice.uni-erlangen.de

--
Ralf Palmisano
Head - Optical Imaging Centre Erlangen

Fellow Royal Microscopical Society
Member Royal Society of Medicine

Speaker Scientific Advisory Board "German Society for Microscopy and Image Analysis"
Board of Directors Core Technologies for Life Science

Hartmannstr. 14
91052 Erlangen, Germany

+49-9131-85-64300 (Office)
+49-9131-85-64301 (Secretary)
+49-9131-85-64302 (Fax)

www.oice.uni-erlangen.de