A radiomic-guided, lesion-aware ensemble with per-cluster post-processing yields strong segmentation across pediatric, meningioma, and metastasis MRI cohorts, though 'top-ranked' parity is asserted rather than shown.
arXiv preprint arXiv:2412.04094 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2025 3representative citing papers
Ensembling inpainting models with median filtering, histogram matching, pixel averaging, and lightweight U-Net refinement yields more anatomically plausible and accurate inpainted MRI regions than individual baseline models.
Radiomics-guided thresholds that delete small components and relabel swapped tissue classes improved the BraTS 2025 ranking metric by 14.9% (SSA) and 0.9% (GLI) with zero GPU hours.
citing papers explorer
-
Adaptable Segmentation Pipeline for Diverse Brain Tumors with Radiomic-Guided Subtyping and Lesion-Wise Model Ensemble
A radiomic-guided, lesion-aware ensemble with per-cluster post-processing yields strong segmentation across pediatric, meningioma, and metastasis MRI cohorts, though 'top-ranked' parity is asserted rather than shown.
-
Post-Processing Methods for Improving Accuracy in MRI Inpainting
Ensembling inpainting models with median filtering, histogram matching, pixel averaging, and lightweight U-Net refinement yields more anatomically plausible and accurate inpainted MRI regions than individual baseline models.
-
Improving Pre-trained Adult Glioma Segmentation Models Using only Post-processing Techniques
Radiomics-guided thresholds that delete small components and relabel swapped tissue classes improved the BraTS 2025 ranking metric by 14.9% (SSA) and 0.9% (GLI) with zero GPU hours.