PiMPiC: An Overlap-Aware Contrastive Learning Framework for 3D Patch-Based Medical Image Segmentation
Contrastive learning framework with overlap-aware modules for improved 3D medical image segmentation.
Reza Karimzadeh
•
•
1 min read
Self-Supervised Learning for 3D Patch-Based Medical Image Segmentation
A self-supervised contrastive learning framework for 3D medical image segmentation using overlap-aware patch sampling. The framework improves representation learning by explicitly …
•
1 min read
A Novel Shape-Based Loss Function for Machine Learning-Based Seminal Organ Segmentation in Medical Imaging
A novel shape-aware loss function for anatomical segmentation that leverages PCA to enforce realistic segment morphology.
Reza Karimzadeh