Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Trained Model for Breast Cancer Screening

Avatar for Kira McLean Kira McLean
July 16, 2016
73
0

Trained Model for Breast Cancer Screening

Work we did for the dream challenge hackathon in July 2016.

Avatar for Kira McLean

Kira McLean

July 16, 2016

More Decks by Kira McLean

See All by Kira McLean
Software for the internet
Avatar for Kira McLean kiramclean
0
30
Women in tech
Avatar for Kira McLean kiramclean
0
86

Featured

See All Featured
AI: The stuff that nobody shows you
Avatar for John Nunemaker jnunemaker
PRO
4
500
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
Avatar for Beat Signer signer
PRO
0
3.3k
The Power of CSS Pseudo Elements
Avatar for Geoffrey Crofte geoffreycrofte
82
6.2k
Un-Boring Meetings
Avatar for Sebastian Deterding codingconduct
0
250
Reality Check: Gamification 10 Years Later
Avatar for Sebastian Deterding codingconduct
0
2.1k
VelocityConf: Rendering Performance Case Studies
Avatar for Addy Osmani addyosmani
333
25k
Unlocking the hidden potential of vector embeddings in international SEO
Avatar for Frank van Dijk frankvandijk
0
230
Leadership Guide Workshop - DevTernity 2021
Avatar for David Neal reverentgeek
1
260
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
Avatar for Aleyda Solis aleyda
2
10k
Primal Persuasion: How to Engage the Brain for Learning That Lasts
Avatar for Mike Taylor tmiket
0
300
The Hidden Cost of Media on the Web [PixelPalooza 2025]
Avatar for Tammy Everts tammyeverts
2
260
Have SEOs Ruined the Internet? - User Awareness of SEO in 2025
Avatar for Akash Hashmi akashhashmi
0
300

Transcript

  1. Trained Model for Breast Cancer Screening @kiraemclean @rebagliatte @tahirinadia @alexisblanchetcohen

  2. DREAM Challenge http://bit.ly/290GBre

  3. The Dataset image meta data exam meta data DICOM images

    image filename, image view results for each view images and embedded patient meta data

  4. DICOM Format Standard for medical images

  5. Image Views

  6. Machine Learning To the rescue

  7. None

  8. Neural Networks Train a model by providing it with input

    and its desired output
  9. None

  10. Tools in Ruby?

  11. ruby-dicom

  12. ruby-fann

  13. Let’s see some code!

  14. Train

  15. Test

  16. Output Sample

  17. Made friends + Learned a whole bunch of stuff

  18. Made friends + Learned a whole bunch of stuff

  19. Made friends + Learned a whole bunch of stuff

  20. Thanks! @kiraemclean @rebagliatte @tahirinadia @alexisblanchetcohen