-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Investigate invalid use of ground truth which leads to improved performances #23
Comments
But the spine-generic dataset should not be used as an absolute representation of scans around the world. Some hospitals acquire only 4-5 vertebrae, others acquire 10-15. There is no general rule about the number of discs to expect in one MRI scan unfortunately. |
Yes I agree, but I still need to choose a relevant number of class for the training to limit false detections caused by under-represented discs. Moreover, I might need to rewrite some functions to handle images with a different FOV. |
I just noticed that the loss was only computed on non-empty GT masks resulting to a lot of false positive prediction. disc-labeling-hourglass/src/dlh/models/jointsmseloss.py Lines 31 to 37 in 1c8ff28
This feature should be removed, however, for now I will just set the variable disc-labeling-hourglass/src/dlh/models/jointsmseloss.py Lines 15 to 19 in 1c8ff28
|
Description
Recently, I noticed that the post processing function applied during testing: extract_skeleton, used some information from the labels to know how many intervertebral discs were present in the image. Therefore, by doing this the performances of the hourglass are biased and less subject to false detection.
INVALID step: Images with a discs number higher than the number of discs the hourglass was trained to find were also removed from the testing and the training.
Conclusion
Further investigation need to be done in the function extract_skeleton and in create_skeleton to see how this post processing function could be improved/fixed to increase fairly the hourglass performances.
The text was updated successfully, but these errors were encountered: