Skip to content

Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures

License

Notifications You must be signed in to change notification settings

VCG/FFD4DenSpineEM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures

Experiments on DenSpineEM Benchmark

Average Results (Mean ± Standard Deviation)

Model Dataset Spine Dice Spine IoU Trunk Dice Trunk IoU Spine Accuracy
PointNet++ M50 0.7784 ± 0.0553 0.7099 ± 0.0465 0.9713 ± 0.0088 0.9453 ± 0.0157 0.8464 ± 0.0649
PointNet++ w. FFD M50 0.8651 ± 0.0275 0.8108 ± 0.0367 0.9853 ± 0.0099 0.9718 ± 0.0169 0.8880 ± 0.0601
PointNet++ M10 0.8132 ± 0.0166 0.7310 ± 0.0182 0.9347 ± 0.0056 0.8807 ± 0.0095 0.7720 ± 0.0429
PointNet++ w. FFD M10 0.8737 ± 0.0133 0.8123 ± 0.0125 0.9705 ± 0.0043 0.9435 ± 0.0076 0.8560 ± 0.0260
PointNet++ H9 0.7465 ± 0.0232 0.6451 ± 0.0269 0.9383 ± 0.0100 0.8861 ± 0.0172 0.7048 ± 0.0561
PointNet++ w. FFD H9 0.8224 ± 0.0178 0.7482 ± 0.0181 0.9711 ± 0.0032 0.9445 ± 0.0055 0.7680 ± 0.0618

Fold 0

Model Dataset Spine Dice Spine IoU Trunk Dice Trunk IoU Spine Accuracy
PointNet++ M50 0.8011 0.7209 0.9564 0.9189 0.8766
PointNet++ w. FFD M50 0.8958 0.8488 0.9879 0.9763 0.9146
PointNet++ M10 0.8159 0.7343 0.9385 0.8863 0.8089
PointNet++ w. FFD M10 0.8859 0.8233 0.9724 0.9466 0.8917
PointNet++ H9 0.7073 0.6006 0.9207 0.8552 0.7891
PointNet++ w. FFD H9 0.8419 0.7655 0.9734 0.9485 0.8275

Fold 1

Model Dataset Spine Dice Spine IoU Trunk Dice Trunk IoU Spine Accuracy
PointNet++ M50 0.7755 0.7075 0.9744 0.9508 0.8857
PointNet++ w. FFD M50 0.8622 0.8063 0.9895 0.9793 0.9132
PointNet++ M10 0.8064 0.7170 0.9257 0.8656 0.8153
PointNet++ w. FFD M10 0.8751 0.8155 0.9736 0.9490 0.8694
PointNet++ H9 0.7550 0.6557 0.9462 0.8999 0.6901
PointNet++ w. FFD H9 0.8373 0.7681 0.9760 0.9536 0.8051

Fold 2

Model Dataset Spine Dice Spine IoU Trunk Dice Trunk IoU Spine Accuracy
PointNet++ M50 0.6935 0.6369 0.9738 0.9498 0.7294
PointNet++ w. FFD M50 0.8234 0.7515 0.9684 0.9418 0.7792
PointNet++ M10 0.8372 0.7624 0.9413 0.8923 0.7803
PointNet++ w. FFD M10 0.8845 0.8221 0.9626 0.9297 0.8567
PointNet++ H9 0.7610 0.6618 0.9436 0.8944 0.7252
PointNet++ w. FFD H9 0.8226 0.7475 0.9698 0.9424 0.7923

Fold 3

Model Dataset Spine Dice Spine IoU Trunk Dice Trunk IoU Spine Accuracy
PointNet++ M50 0.7928 0.7182 0.9711 0.9449 0.8486
PointNet++ w. FFD M50 0.8698 0.8209 0.9920 0.9842 0.9167
PointNet++ M10 0.8036 0.7185 0.9341 0.8794 0.7325
PointNet++ w. FFD M10 0.8641 0.8016 0.9719 0.9459 0.8312
PointNet++ H9 0.7407 0.6354 0.9385 0.8868 0.6486
PointNet++ w. FFD H9 0.8024 0.7272 0.9674 0.9376 0.7412

Fold 4

Model Dataset Spine Dice Spine IoU Trunk Dice Trunk IoU Spine Accuracy
PointNet++ M50 0.8290 0.7660 0.9806 0.9623 0.8919
PointNet++ w. FFD M50 0.8745 0.8264 0.9885 0.9776 0.9162
PointNet++ M10 0.8030 0.7227 0.9341 0.8799 0.7229
PointNet++ w. FFD M10 0.8587 0.7989 0.9721 0.9463 0.8312
PointNet++ H9 0.7684 0.6718 0.9427 0.8943 0.6709
PointNet++ w. FFD H9 0.8077 0.7328 0.9691 0.9406 0.6741

About

Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published