A Unified Pipeline for Consistent Multi-Label Mask Generation in Pediatric Cardiac Segmentation
Creators
- 1. Marmara Univ, Bioengn, Istanbul, Turkiye
- 2. Istinye Univ, Dept Mech Engn, Istanbul, Turkiye
- 3. Istanbul Medipol Univ, Dept Biomed Engn, Istanbul, Turkiye
- 4. Istanbul Medipol Univ, Biomed Engn & Bioinformat, Istanbul, Turkiye
- 5. Anadolu Med Ctr, Dept Radiol, Istanbul, Turkiye
- 6. Istinye Univ, Dept Comp Engn, Istanbul, Turkiye
- 7. Istinye Univ, Comp Engn, Istanbul, Turkiye
- 8. Istinye Univ, Software Engn, Istanbul, Turkiye
- 9. Istinye Univ, Artificial Intelligence, Istanbul, Turkiye
- 10. Yildiz Tech Univ, Biomed Engn, Istanbul, Turkiye
- 11. Zuhtu Kurtulmus Anatolian High Sch, Istanbul, Turkiye
- 12. Cemberlitas Anatolian High Sch, Istanbul, Turkiye
Description
Artificial Intelligence based cardiac image segmentation requires consistent labels, harmonized volumes, and computationally efficient dataset. The present study proposes a reproducible pipeline that (i) merges segmented cardiac structures into a single multi-label mask (0: background, 1: aorta, 2: chambers, 3: pulmonary structures), (ii) resamples masks to perfectly match scan dimensions using 3D Slicer's "Resample Image (BRAINS)" module (nearest-neighbor interpolation), and (iii) performs automatic region-of-interest (ROI) cropping by adding 10-pixel margin around mask-derived bounds. On our internal dataset, the workflow standardizes inputs, reduces data volume substantially, and preserves full cardiac anatomy. The resulting data enabled stable multi-class and task-specific training and contribution to a better Dice score in downstream models. The ROI script operate on a simple folder structure and can be executed batch-wise, supporting anonymity, interoperability, and rapid experimentation.
Files
bib-05231630-41b9-44af-b4f0-011c3ad3cd5a.txt
Files
(319 Bytes)
| Name | Size | Download all |
|---|---|---|
|
md5:6c817706e0582784d2a3801d939e5d47
|
319 Bytes | Preview Download |