$30 off During Our Annual Pro Sale. View Details »

Trained Model for Breast Cancer Screening

Avatar for Kira McLean Kira McLean
July 16, 2016
0
72

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
Tweet

More Decks by Kira McLean

See All by Kira McLean
Software for the internet
Avatar for Kira McLean kiramclean
0
28
Women in tech
Avatar for Kira McLean kiramclean
0
84

Featured

See All Featured
Building Applications with DynamoDB
Avatar for Matt Wood mza
96
6.8k
Understanding Cognitive Biases in Performance Measurement
Avatar for Philip Tellis bluesmoon
32
2.7k
Large-scale JavaScript Application Architecture
Avatar for Addy Osmani addyosmani
515
110k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
Avatar for Chris Coyier chriscoyier
508
140k
What’s in a name? Adding method to the madness
Avatar for Product Marketing Alliance productmarketing
PRO
24
3.8k
Being A Developer After 40
Avatar for Adrian Kosmaczewski akosma
91
590k
Building Flexible Design Systems
Avatar for Yesenia Perez-Cruz yeseniaperezcruz
330
39k
The World Runs on Bad Software
Avatar for Brandon Keepers bkeepers
PRO
72
12k
10 Git Anti Patterns You Should be Aware of
Avatar for Lemi Orhan Ergin lemiorhan
PRO
659
61k
Imperfection Machines: The Place of Print at Facebook
Avatar for Scott Boms scottboms
269
13k
GraphQLの誤解/rethinking-graphql
Avatar for sonatard sonatard
73
11k
The Hidden Cost of Media on the Web [PixelPalooza 2025]
Avatar for Tammy Everts tammyeverts
1
100

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