Spatial Prior-Guided Boundary and Region-Aware 2D Lesion Segmentation in Neonatal Hypoxic Ischemic Encephalopathy
Rao, A.; Shukla, A.; Bhargava, J.; Bao, R.; Ou, Y.
Show abstract
Segmenting acute and hyper-acute brain lesions in neona-tal hypoxic-ischemic encephalopathy (HIE) from diffusion-weighted MRI (DWI) is critical for prognosis and treatment planning but remains challenging due to severe class imbalance and lesion variability. We propose a computationally efficient 2D segmentation framework leveraging ADC and ZADC maps as a three-channel input to UNet++ with an Inception-v4 encoder and scSE attention for enhanced spatial-channel recalibration. To address class critical imbalance and lack of volumetric context in 2D methods, we introduce a novel boundary-and-region-aware weighted loss integrating Tversky, Log-Hausdorff, and Focal losses. Our method surpasses state-of-the-art 2D approaches and achieves competitive performance against computationally intensive 3D architectures, securing a Dice Similarity Coefficient (DSC) of 0.6060, Mean Average Surface Distance (MASD) of 2.6484, and Normalized Surface Distance (NSD) of 0.7477. These results establish a new benchmark for neonatal HIE lesion segmentation, demonstrating superior detection of both acute and hyper-acute lesions while mitigating the challenge of loss collapse. The code is available at Neonatal-HIE-SPARSeg.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Deep Learning Based Cardiac Cine Segmentation – Transfer Learning Application to 7T Ultrahigh-Field MRI 95%
- Prospective Motion Correction and Automatic Segmentation of Penetrating Arteries in Phase Contrast MRI at 7 T 94%
- SC-GAN: 3D self-attention conditional GAN with spectral normalization for multi-modal neuroimaging synthesis 94%
Similar papers in this journal
- Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images 96%
- Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images 96%
- STAMP: Simultaneous Training and Model Pruning for Low Data Regimes in Medical Image Segmentation 95%
Similar papers in this journal
Similar papers in this journal
- Anatomy-guided, modality-agnostic segmentation of neuroimaging abnormalities 96%
- Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation 96%
- OpenMAP-T1: A Rapid Deep Learning Approach to Parcellate 280 Anatomical Regions to Cover the Whole Brain 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.