# Have Computer programs (Pattern Recognition) Ever Been Used to Evaluate Skin Cancer?

**URL:** <https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786>\
**Category:** Factual Questions\
**Created:** [April 15, 2015, 10:37pm UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786 "2015-04-15T22:37:45Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![ralph124c](https://avatars.discourse-cdn.com/v4/letter/r/8797f3/32.png) [@ralph124c](https://boards.straightdope.com/u/ralph124c)\
**Post date:** [April 15, 2015, 10:37pm UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786/1 "2015-04-15T22:37:45Z")

</div>

I just returned from the dermatologist-thankfully, he saw nothing suspicious . My question: a screening by a dermatologist is utilizing the doctor’s experience in evaluation the size and shape of moles, pimples, birthmarks, etc. Could a computer program do was well? also, the computer scan could store the past images and show any changes.  
It would seem (to me) that computerized screenings might be faster and more accurate-has anyone tried it?

---

<div class="post-metadata">

**Author:** ![lisiate](https://avatars.discourse-cdn.com/v4/letter/l/f05b48/32.png) [@lisiate](https://boards.straightdope.com/u/lisiate)\
**Post date:** [April 15, 2015, 10:59pm UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786/2 "2015-04-15T22:59:31Z")

</div>

Here in New Zealand, [digitized mole mapping](http://www.dermnetnz.org/procedures/mole-mapping.html)is a pretty big thing. While the analysis of the images is still done by humans, the ability to store and compare images of lesions over time is a big help in detecting areas of concern, and reducing false positives.

I really should get one done actually.

---

<div class="post-metadata">

**Author:** ![Melbourne](https://avatars.discourse-cdn.com/v4/letter/m/b5e925/32.png) [@Melbourne](https://boards.straightdope.com/u/Melbourne)\
**Post date:** [April 16, 2015, 2:33am UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786/3 "2015-04-16T02:33:05Z")

</div>

There was a recent study of 3 or 4 iOS / Android skin cancer detection apps, which determined that the 2-3 which used pattern recognition weren’t any good, and the one which was ok was sending the pictures off for analysis by a team of actual doctors.

It was an active area of research a couple of years ago, so I think that the reason the research has gone quiet is either that they were looking at commercialisation, or they decided it wasn’t working well enough.

---

<div class="post-metadata">

**Author:** ![Francis\_Vaughan](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/francis_vaughan/32/3093_2.png) [@Francis\_Vaughan](https://boards.straightdope.com/u/Francis_Vaughan)\
**Post date:** [April 16, 2015, 2:36am UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786/4 "2015-04-16T02:36:38Z")

</div>

[They don’t seem to please the FTC either](http://www.theregister.co.uk/2015/04/13/ftc_cancer_app_settlement/).

---

<div class="post-metadata">

**Author:** ![Lance\_Turbo](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/lance_turbo/32/6156_2.png) [@Lance\_Turbo](https://boards.straightdope.com/u/Lance_Turbo)\
**Post date:** [April 16, 2015, 9:19pm UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786/5 "2015-04-16T21:19:51Z")

</div>

Sounds like a job for a [support vector machine](http://en.wikipedia.org/wiki/Support_vector_machine).

---

<div class="post-metadata">

**Author:** ![Sage\_Rat](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/sage_rat/32/399_2.png) [@Sage\_Rat](https://boards.straightdope.com/u/Sage_Rat)\
**Post date:** [April 16, 2015, 10:40pm UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786/6 "2015-04-16T22:40:28Z")

</div>

Given that you need a full-body check in order to perform this sort of evaluation, regardless of software, you would still need a human-sized booth that took a 360 shot of your naked body. That sort of equipment would be housed at a doctor’s office and there probably wouldn’t be a significantly great time saving between having the doctor look you over versus having all the technicians operate the equipment.

So overall, I don’t know that it’s something which is liable to have a great calling (outside of Australia/NZ).

---

<div class="post-metadata">

**Author:** ![Digital\_is\_the\_new\_Analog](https://avatars.discourse-cdn.com/v4/letter/d/a88e4f/32.png) [@Digital\_is\_the\_new\_Analog](https://boards.straightdope.com/u/Digital_is_the_new_Analog)\
**Post date:** [April 17, 2015, 2:01am UTC](https://boards.straightdope.com/t/have-computer-programs-pattern-recognition-ever-been-used-to-evaluate-skin-cancer/717786/7 "2015-04-17T02:01:55Z")

</div>

A few years ago, I was part of a clinical trial at my dermatologists’ office for digital imaging and recognizing displastic nevi. I never heard the results, but they don’t take pictures of my nevi any more, so I assume it didn’t go all that well. If I remember next time I’m there (in about 5 months), I’ll ask.
