Skip to content

Latest commit

 

History

History
76 lines (67 loc) · 1.98 KB

LOGS.md

File metadata and controls

76 lines (67 loc) · 1.98 KB

Daily Logs

Data Preparation

09-04-2019 18:36:03

Anoushkrit Goel:

Exceptions in the “WBerg” dataset which contain multiple sub-cases and have different BI-RADS score for respective sub-case. For example: WB129A and WB129B are the two cases under WB129 which have different BI-RADS score.

Proposed Solution: Sort all the anomalies like this and classify them under test data for the model because model will eventually classify the BI-RADS score of those unknown sub-datasets. Anomalies:

  1. WB102
  2. WB114
  3. WB120
  4. WB129
  5. WB137
  6. WB163
  7. WB202
  8. WB208
  9. WB245
  10. WB249
  11. WB252
  12. WB253
  13. WB254
  14. WB268
  15. WB269
  16. WB271
  17. WB272
  18. WB281
  19. WB282
  20. WB286
  21. WB288
  22. WB290
  23. WB297
  24. WB302
  25. WB305
  26. WB312
  27. WB323
  28. WB327
  29. WB338
  30. WB344
  31. WB349
  32. WB361
  33. WB369
  34. WB372
  35. WB379
  36. WB384
  37. WB387
  38. WB388
  39. WB398
  40. WB405
  41. WB415
  42. WB424
  43. WB430

09-04-2019 18:36:03

Anoushkrit Goel:

  • Creating a massive dataset of Ultrasound images which contain callipers and leaving those which do not.
  • Palp8_31, Palp_8_6, PalpB9Clear226,
  • Philips Ultrasound Scanning device is not good in creating contrasting images to detect lesions perfectly.
  • Siemens cannot be used WB264 contains no callipers.

09-04-2019 18:36:03

Anoushkrit Goel:

Major Finding

The model was initially destined to be trained on un-callipered images by creating bounding box around them using imglab. Coordinates of these bounding boxes would have been written in an .xml file by the same software which would be eventually fed to the model. But, we are not certain as to what type of images will be provided to the deployed model while, hence, the model needs to be trained with both type of images. Technically, all the type of images regardless of callipers or metadata written on the image itself will be used to train the following.

09-10-2019

  1. Break His Dataset

15-11-2019

  1. Discovered the Attention Gated Networks using PyTorch.