Extremal Contours: Gradient-driven contours for compact visual attribution
Training-free method that uses gradient-driven smooth contours for compact visual attribution.
Reza Karimzadeh
•
•
1 min read
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
CARMA: Collocation-Aware Resource Manager with GPU Memory Estimator
Server-scale collocation-aware GPU resource manager with an ML-based GPU memory estimator for robust and efficient deep learning training.
Ehsan Yousefzadeh-Asl-Miandoab
Extremal Contours
Extremal Contours is an algorithmic explainable AI method for extracting compact, smooth, and interpretable visual explanations from deep vision models. The method represents …
•
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
Generating Synthetic Computed Tomography for Radiotherapy: SynthRAD2023 Challenge Report
SynthRAD2023 challenge report on benchmark evaluation of synthetic CT generation methods for radiotherapy planning.
Evi M. C. Huijben
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
Attention-based deep learning segmentation: Application to brain tumor delineation
Attention-based deep learning segmentation for brain tumor delineation.
Reza Karimzadeh