Image processing in R for BMI calculation

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
12 messages Options
Reply | Threaded
Open this post in threaded view
|

Image processing in R for BMI calculation

PaulJr
Hello everyone,

Does anyone know about any package for image processing, for example, to
calculate body mass index pased on a picture, silouette or image.

Any guidance will be greatly appreciated.

Best regards,

Paul

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

Bert Gunter-2
1) doing a web search on:
"R package to calculate body mass index based on a picture, silhouette or
image"

did *not* bring up any R packages, but did provide what looked like
relevant links to other software and research/discussions. You can decide
whether or not this is useful "guidance" (if you have not already done
this).

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Sun, Feb 28, 2021 at 8:39 AM Paul Bernal <[hidden email]> wrote:

> Hello everyone,
>
> Does anyone know about any package for image processing, for example, to
> calculate body mass index pased on a picture, silouette or image.
>
> Any guidance will be greatly appreciated.
>
> Best regards,
>
> Paul
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

Jim Lemon-4
In reply to this post by PaulJr
Hi Paul,
The paper doesn't seem to mention R and the journal doesn't inspire
confidence, but the formulas provided give you a start:

https://www.researchgate.net/publication/280133090_Calculation_of_Body_Mass_Index_using_Image_Processing_Techniques

Jim

On Mon, Mar 1, 2021 at 3:39 AM Paul Bernal <[hidden email]> wrote:

>
> Hello everyone,
>
> Does anyone know about any package for image processing, for example, to
> calculate body mass index pased on a picture, silouette or image.
>
> Any guidance will be greatly appreciated.
>
> Best regards,
>
> Paul
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

bretschr
In reply to this post by PaulJr
Hello Paul Bernal,


(sorry, forgot to CC)

Re:

> Does anyone know about any package for image processing, for example, to
> calculate body mass index pased on a picture, silouette or image.



This sounds more like a job for the image analysis program NIH Image (the Java-version "ImageJ" being available for most platforms).
ImageJ was designed for the analysis of microscopic images of cells etcetera, and can count, mark and measure objects.
However, it works for 2D images unless jou have a stack of images.

For R there is a Package ‘EBImage’ for image manipulation and measuring that might also be interesting (but also 2D I guess).

Succes and
Best regards,


Franklin
-----------


Franklin Bretschneider
Dept of Biology
Utrecht University
[hidden email]
[hidden email]
Franklin Bretschneider
Dept of Biology
Utrecht University
[hidden email]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

aBBy Spurdle, ⍺XY
In reply to this post by PaulJr
Hi Paul,

If the background is relatively uniform:
Then a simple algorithm could be used, to distinguish foreground from
background points.
Essentially, returning a logical matrix.

Otherwise, I'm assuming that suitable pooling/convolution operations
could be used for this purpose.

Then you could estimate *relative* measures of height and mass from
the logical matrix.
(With more precise measures being possible, if you know the image scales).

There are a number of R packages for reading images.
Currently, I mainly use Simon Urbanek's package, "png".

I'm currently creating a package with support for pooling/convolution
operations, and related utility functions.
However, it's not ready yet.

Another option is Jeroen Ooms' package, "magick".


best,
B.


On Mon, Mar 1, 2021 at 5:39 AM Paul Bernal <[hidden email]> wrote:

>
> Hello everyone,
>
> Does anyone know about any package for image processing, for example, to
> calculate body mass index pased on a picture, silouette or image.
>
> Any guidance will be greatly appreciated.
>
> Best regards,
>
> Paul
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

Richard O'Keefe-2
In reply to this post by PaulJr
"Body Mass Index" is a rather bizarre thing:
body.mass.in.kg / height.in.m^2
I have never been able to find any biological
or physical meaning for this.  Yet clinicians
are solemnly advised to measure the weight to
the nearest 0.1kg and the height to the
nearest 0.1cm.

How do you propose to determine the weight from
a single image?  Even an R package cannot perform magic.


On Mon, 1 Mar 2021 at 05:39, Paul Bernal <[hidden email]> wrote:

> Hello everyone,
>
> Does anyone know about any package for image processing, for example, to
> calculate body mass index pased on a picture, silouette or image.
>
> Any guidance will be greatly appreciated.
>
> Best regards,
>
> Paul
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

R help mailing list-2
In reply to this post by PaulJr
"Body Mass Index" is a rather bizarre thing:body.mass.in.kg / height.in.m^2I have never been able to find any biologicalor physical meaning for this.  Yet cliniciansare solemnly advised to measure the weight tothe nearest 0.1kg and the height to thenearest 0.1cm.How do you propose to determine the weight froma single image?  Even an R package cannot perform magic.On Mon, 1 Mar 2021 at 05:39, Paul Bernal <[hidden email]> <mailto:[hidden email]> wrote:

> Hello everyone,Does anyone know about any package for image processing, for example, tocalculate body mass index pased on a picture, silouette or image.Any guidance will be greatly appreciated.Best regards,Paul
>

A quick search with the terms "BMI flawed" produces an enormous list of hits pointing out the problems with BMI as an index.  Here's one from a dozen or so years ago:

https://www.npr.org/templates/story/story.php?storyId=106268439

And a quote from that piece:

"The BMI was introduced in the early 19th century by a Belgian named Lambert Adolphe Jacques Quetelet. He was a mathematician, not a physician. He produced the formula to give a quick and easy way to measure the degree of obesity of the general population to assist the government in allocating resources. In other words, it is a 200-year-old hack."
As an index of obesity in individuals, BMI has some glaring flaws.



- T. Arthur Milne

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

Jim Lemon-4
In reply to this post by Richard O'Keefe-2
I must agree with the criticism of BMI as a diagnostic index. It is
easy to tell if a person is - ahem - wide and not very high with a
single glance. These elementary parameters can easily be deduced from
an image of said person. However, it does not convey that essential
ratio of muscle to - ahem - adipose tissue that is the stated reason
for its prominence. I suggest an older, but more valid, index that was
used in the identification of witches. Simply tie the person's hands
behind their back and throw him or her into the deep end of the pool.
Time to drowning is the response variable and I am certain that those
now chastised for their adipose tissue will vastly prefer it.

Jim

On Mon, Mar 1, 2021 at 10:24 PM Richard O'Keefe <[hidden email]> wrote:

>
> "Body Mass Index" is a rather bizarre thing:
> body.mass.in.kg / height.in.m^2
> I have never been able to find any biological
> or physical meaning for this.  Yet clinicians
> are solemnly advised to measure the weight to
> the nearest 0.1kg and the height to the
> nearest 0.1cm.
>
> How do you propose to determine the weight from
> a single image?  Even an R package cannot perform magic.
>
>
> On Mon, 1 Mar 2021 at 05:39, Paul Bernal <[hidden email]> wrote:
>
> > Hello everyone,
> >
> > Does anyone know about any package for image processing, for example, to
> > calculate body mass index pased on a picture, silouette or image.
> >
> > Any guidance will be greatly appreciated.
> >
> > Best regards,
> >
> > Paul
> >
> >         [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> > http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> >
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

Sorkin, John
Colleagues,

BMI has is failures, but it has demonstrated utility. BMI predicts multiple outcome measures including cardiovascular disease and mortality. Don't through out a useful metric because it is not the perfect metric.

As to why BMI is computed as weight/height^2, it can be shown that dividing height by the square of weight decreases the correlation between weight and height. The optimum exponent (i.e. the power that most effectively minimizes the correlation between weight and height) is not the same in men and women and it differs by race. In general an exponent of 2.0 is best for men; for women an exponent of 2.2 is a bit better than 2.0.

In any event, don't let the perfect get in the way of the good.

John


John David Sorkin M.D., Ph.D.
Professor of Medicine
Chief, Biostatistics and Informatics
University of Maryland School of Medicine Division of Gerontology and Geriatric Medicine
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524
(Phone) 410-605-7119
(Fax) 410-605-7913 (Please call phone number above prior to faxing)



________________________________________
From: R-help <[hidden email]> on behalf of Jim Lemon <[hidden email]>
Sent: Monday, March 1, 2021 4:23 PM
To: Richard O'Keefe; r-help mailing list
Subject: Re: [R] Image processing in R for BMI calculation

I must agree with the criticism of BMI as a diagnostic index. It is
easy to tell if a person is - ahem - wide and not very high with a
single glance. These elementary parameters can easily be deduced from
an image of said person. However, it does not convey that essential
ratio of muscle to - ahem - adipose tissue that is the stated reason
for its prominence. I suggest an older, but more valid, index that was
used in the identification of witches. Simply tie the person's hands
behind their back and throw him or her into the deep end of the pool.
Time to drowning is the response variable and I am certain that those
now chastised for their adipose tissue will vastly prefer it.

Jim

On Mon, Mar 1, 2021 at 10:24 PM Richard O'Keefe <[hidden email]> wrote:

>
> "Body Mass Index" is a rather bizarre thing:
> body.mass.in.kg / height.in.m^2
> I have never been able to find any biological
> or physical meaning for this.  Yet clinicians
> are solemnly advised to measure the weight to
> the nearest 0.1kg and the height to the
> nearest 0.1cm.
>
> How do you propose to determine the weight from
> a single image?  Even an R package cannot perform magic.
>
>
> On Mon, 1 Mar 2021 at 05:39, Paul Bernal <[hidden email]> wrote:
>
> > Hello everyone,
> >
> > Does anyone know about any package for image processing, for example, to
> > calculate body mass index pased on a picture, silouette or image.
> >
> > Any guidance will be greatly appreciated.
> >
> > Best regards,
> >
> > Paul
> >
> >         [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> > https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-help&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432633266%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=h%2FZ9zAI4aad5GEtvB1H9BoN4bxRYnATV%2Fds7r8D2s04%3D&amp;reserved=0
> > PLEASE do read the posting guide
> > https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.r-project.org%2Fposting-guide.html&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432633266%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=2IvMsdifWeGaAyBNT%2F7695rmNX6O1Pb3G90%2FlrpU0KA%3D&amp;reserved=0
> > and provide commented, minimal, self-contained, reproducible code.
> >
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-help&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432633266%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=h%2FZ9zAI4aad5GEtvB1H9BoN4bxRYnATV%2Fds7r8D2s04%3D&amp;reserved=0
> PLEASE do read the posting guide https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.r-project.org%2Fposting-guide.html&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432643223%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=Ht2zAvvZpRhQ%2FKwjJXEbPreJd2RleNgzjD%2FhdbXhQc0%3D&amp;reserved=0
> and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-help&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432643223%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=6hUDWapuTlwnbSWTupkoiE6b9%2FyYxZIxjkJitJRZNiE%3D&amp;reserved=0
PLEASE do read the posting guide https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.r-project.org%2Fposting-guide.html&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432643223%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=Ht2zAvvZpRhQ%2FKwjJXEbPreJd2RleNgzjD%2FhdbXhQc0%3D&amp;reserved=0
and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

aBBy Spurdle, ⍺XY
I can't help but feel that a discussion on the merit of BMI is a
digression, from the OP's question.
In addition, to being of no relevance to "R Programming".

In relation to Richard's technical comments:
As per my previous post, it is possible to get *relative" measures.
(Assuming the images are not on a standardized scale, which they could be).

In relation to Jim's anatomical comments:
An improved algorithm could evaluate a subject's body type.
In addition to factoring in gender, ethnic characteristics and age.

In any case, I don't see why image-based classification is any less
worthwhile than conclusions based on timeseries plots and
scatterplots...

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

Bert Gunter-2
In reply to this post by Sorkin, John
This discussion is completely offr topic here. Please take it elsewhere.

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Mon, Mar 1, 2021 at 1:42 PM Sorkin, John <[hidden email]>
wrote:

> Colleagues,
>
> BMI has is failures, but it has demonstrated utility. BMI predicts
> multiple outcome measures including cardiovascular disease and mortality.
> Don't through out a useful metric because it is not the perfect metric.
>
> As to why BMI is computed as weight/height^2, it can be shown that
> dividing height by the square of weight decreases the correlation between
> weight and height. The optimum exponent (i.e. the power that most
> effectively minimizes the correlation between weight and height) is not the
> same in men and women and it differs by race. In general an exponent of 2.0
> is best for men; for women an exponent of 2.2 is a bit better than 2.0.
>
> In any event, don't let the perfect get in the way of the good.
>
> John
>
>
> John David Sorkin M.D., Ph.D.
> Professor of Medicine
> Chief, Biostatistics and Informatics
> University of Maryland School of Medicine Division of Gerontology and
> Geriatric Medicine
> Baltimore VA Medical Center
> 10 North Greene Street
> GRECC (BT/18/GR)
> Baltimore, MD 21201-1524
> (Phone) 410-605-7119
> (Fax) 410-605-7913 (Please call phone number above prior to faxing)
>
>
>
> ________________________________________
> From: R-help <[hidden email]> on behalf of Jim Lemon <
> [hidden email]>
> Sent: Monday, March 1, 2021 4:23 PM
> To: Richard O'Keefe; r-help mailing list
> Subject: Re: [R] Image processing in R for BMI calculation
>
> I must agree with the criticism of BMI as a diagnostic index. It is
> easy to tell if a person is - ahem - wide and not very high with a
> single glance. These elementary parameters can easily be deduced from
> an image of said person. However, it does not convey that essential
> ratio of muscle to - ahem - adipose tissue that is the stated reason
> for its prominence. I suggest an older, but more valid, index that was
> used in the identification of witches. Simply tie the person's hands
> behind their back and throw him or her into the deep end of the pool.
> Time to drowning is the response variable and I am certain that those
> now chastised for their adipose tissue will vastly prefer it.
>
> Jim
>
> On Mon, Mar 1, 2021 at 10:24 PM Richard O'Keefe <[hidden email]> wrote:
> >
> > "Body Mass Index" is a rather bizarre thing:
> > body.mass.in.kg / height.in.m^2
> > I have never been able to find any biological
> > or physical meaning for this.  Yet clinicians
> > are solemnly advised to measure the weight to
> > the nearest 0.1kg and the height to the
> > nearest 0.1cm.
> >
> > How do you propose to determine the weight from
> > a single image?  Even an R package cannot perform magic.
> >
> >
> > On Mon, 1 Mar 2021 at 05:39, Paul Bernal <[hidden email]> wrote:
> >
> > > Hello everyone,
> > >
> > > Does anyone know about any package for image processing, for example,
> to
> > > calculate body mass index pased on a picture, silouette or image.
> > >
> > > Any guidance will be greatly appreciated.
> > >
> > > Best regards,
> > >
> > > Paul
> > >
> > >         [[alternative HTML version deleted]]
> > >
> > > ______________________________________________
> > > [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> > >
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-help&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432633266%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=h%2FZ9zAI4aad5GEtvB1H9BoN4bxRYnATV%2Fds7r8D2s04%3D&amp;reserved=0
> > > PLEASE do read the posting guide
> > >
> https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.r-project.org%2Fposting-guide.html&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432633266%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=2IvMsdifWeGaAyBNT%2F7695rmNX6O1Pb3G90%2FlrpU0KA%3D&amp;reserved=0
> > > and provide commented, minimal, self-contained, reproducible code.
> > >
> >
> >         [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> >
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-help&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432633266%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=h%2FZ9zAI4aad5GEtvB1H9BoN4bxRYnATV%2Fds7r8D2s04%3D&amp;reserved=0
> > PLEASE do read the posting guide
> https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.r-project.org%2Fposting-guide.html&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432643223%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=Ht2zAvvZpRhQ%2FKwjJXEbPreJd2RleNgzjD%2FhdbXhQc0%3D&amp;reserved=0
> > and provide commented, minimal, self-contained, reproducible code.
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
>
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-help&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432643223%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=6hUDWapuTlwnbSWTupkoiE6b9%2FyYxZIxjkJitJRZNiE%3D&amp;reserved=0
> PLEASE do read the posting guide
> https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.r-project.org%2Fposting-guide.html&amp;data=04%7C01%7CJSorkin%40som.umaryland.edu%7C58f4e3f9226c4ac456cf08d8dcf8532e%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502306432643223%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=Ht2zAvvZpRhQ%2FKwjJXEbPreJd2RleNgzjD%2FhdbXhQc0%3D&amp;reserved=0
> and provide commented, minimal, self-contained, reproducible code.
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Image processing in R for BMI calculation

Sorkin, John
In reply to this post by Sorkin, John
Heinz,

I can't tell you how much I appreciated your email. I firmly believe that the rules and norms of the R-help mailing list need to be respected and followed. Nevertheless, I feared that if the comments were left unquestioned people who are not familiar with BMI, its strengths weakness, and its history, might assume from the comments that the metric is worthless, and that all studies that have used it are by extension worthless. It is for this reason, and because I thought it important the people understand that the exponent of 2 in the denominator is not a arbitrary value, but rather a value with a reason that I replied.

I hope that the larger list community will forgive the liberty I have taken with the listerver's norms. I also hope that none of the people who were part of the email chain were personally offended by my comments.

John




John David Sorkin M.D., Ph.D.
Professor of Medicine
Chief, Biostatistics and Informatics
University of Maryland School of Medicine Division of Gerontology and Geriatric Medicine
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524
(Phone) 410-605-7119
(Fax) 410-605-7913 (Please call phone number above prior to faxing)



________________________________________
From: Heinz Tuechler <[hidden email]>
Sent: Monday, March 1, 2021 6:26 PM
To: Sorkin, John; Jim Lemon; Richard O'Keefe; T. A. Milne via R-help; Abby Spurdle
Subject: Re: [R] Image processing in R for BMI calculation

Dear All,

since Bert Gunter correctly stated that the discussion is off topic, I
answer to you only.
In my view John and Abby made very reasonable comments, while
particularly the link
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.npr.org%2Ftemplates%2Fstory%2Fstory.php%3FstoryId%3D106268439&amp;data=04%7C01%7Cjsorkin%40som.umaryland.edu%7Cd5d29291516a4b5c84d408d8dd096c00%7C717009a620de461a88940312a395cac9%7C0%7C0%7C637502379829397742%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=MKCnjEzFyRmCrO6Efxo0s%2BTJ4cV%2B3m1FPy61MPwptE8%3D&amp;reserved=0
mentioned in the note of T. Arthur Milne seems remarkably superficial -
maybe it's just a joke?

Some examples:
"Moreover, it ignores waist size, which is a clear indicator of obesity
level." Without reference to hip?

"Because the majority of people today (and in Quetelet's time) lead
fairly sedentary lives ..." 200 years ago?

"Because the BMI is a single number between 1 and 100 (like a
percentage) ..." Try to imagine a BMI of 1, or of 100. The BMI will be
between 1 and 100, but 1 to 100 will not be its range.

"It suggests there are distinct categories of underweight, ideal,
overweight and obese, with sharp boundaries that hinge on a decimal
place." Why should categories be implied by the BMI itself?

"It is embarrassing for one of the most scientifically, technologically
and medicinally advanced nations in the world ..." That's true, at least
for my eyes. When I visited the USA, I had the impression that in many
cases you don't need a measure at all.

best regards,

Heinz

Sorkin, John wrote/hat geschrieben on/am 01.03.2021 22:42:

> Colleagues,
>
> BMI has is failures, but it has demonstrated utility. BMI predicts multiple outcome measures including cardiovascular disease and mortality. Don't through out a useful metric because it is not the perfect metric.
>
> As to why BMI is computed as weight/height^2, it can be shown that dividing height by the square of weight decreases the correlation between weight and height. The optimum exponent (i.e. the power that most effectively minimizes the correlation between weight and height) is not the same in men and women and it differs by race. In general an exponent of 2.0 is best for men; for women an exponent of 2.2 is a bit better than 2.0.
>
> In any event, don't let the perfect get in the way of the good.
>
> John
>
>
> John David Sorkin M.D., Ph.D.
> Professor of Medicine
> Chief, Biostatistics and Informatics
> University of Maryland School of Medicine Division of Gerontology and Geriatric Medicine
> Baltimore VA Medical Center
> 10 North Greene Street
> GRECC (BT/18/GR)
> Baltimore, MD 21201-1524
> (Phone) 410-605-7119
> (Fax) 410-605-7913 (Please call phone number above prior to faxing)
>
>
>
> ________________________________________
> From: R-help <[hidden email]> on behalf of Jim Lemon <[hidden email]>
> Sent: Monday, March 1, 2021 4:23 PM
> To: Richard O'Keefe; r-help mailing list
> Subject: Re: [R] Image processing in R for BMI calculation
>
> I must agree with the criticism of BMI as a diagnostic index. It is
> easy to tell if a person is - ahem - wide and not very high with a
> single glance. These elementary parameters can easily be deduced from
> an image of said person. However, it does not convey that essential
> ratio of muscle to - ahem - adipose tissue that is the stated reason
> for its prominence. I suggest an older, but more valid, index that was
> used in the identification of witches. Simply tie the person's hands
> behind their back and throw him or her into the deep end of the pool.
> Time to drowning is the response variable and I am certain that those
> now chastised for their adipose tissue will vastly prefer it.
>
> Jim
>
> On Mon, Mar 1, 2021 at 10:24 PM Richard O'Keefe <[hidden email]> wrote:
>>
>> "Body Mass Index" is a rather bizarre thing:
>> body.mass.in.kg / height.in.m^2
>> I have never been able to find any biological
>> or physical meaning for this.  Yet clinicians
>> are solemnly advised to measure the weight to
>> the nearest 0.1kg and the height to the
>> nearest 0.1cm.
>>
>> How do you propose to determine the weight from
>> a single image?  Even an R package cannot perform magic.
>>
>>
>> On Mon, 1 Mar 2021 at 05:39, Paul Bernal <[hidden email]> wrote:
>>
>>> Hello everyone,
>>>
>>> Does anyone know about any package for image processing, for example, to
>>> calculate body mass index pased on a picture, silouette or image.
>>>
>>> Any guidance will be greatly appreciated.
>>>
>>> Best regards,
>>>
>>> Paul
>>>

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.