dwi-flair-mismatch-stroke

DWI-FLAIR Mismatch Classification — DenseNet121 3D

Pretrained models for automatic DWI-FLAIR mismatch classification in acute ischemic stroke. Trained on the SOOP dataset (OpenNeuro ds004889) using a 3D DenseNet121 architecture (MONAI). Labels generated via the rDWI-IQR method (Scheldeman et al., 2022).

---

Models

best_own_model.pth — OWN EDA Pipeline

Preprocessing: TRSAA registration, 2×2×2mm isotropic resampling, Z-score normalization, CropOrPad 80×112×96.
Config: AdamW · lr=1e-3 · wd=1e-5 · warmup cosine · online augmentation
Val AUC=0.849 | Test AUC=0.834 | External AUC (ISLES 2022)=0.813

best_kim_model.pth — KIM Pipeline

Preprocessing: resize 256×256×36, min-max normalization, TRSAA registration (Kim et al., 2025).
Config: AdamW · lr=1e-3 · wd=1e-5 · warmup cosine · online augmentation
Val AUC=0.790 | Test AUC=0.778 | External AUC (ISLES 2022)=0.802

---

Usage

import torch
from huggingface_hub import hf_hub_download
from monai.networks.nets import DenseNet121

model = DenseNet121(spatial_dims=3, in_channels=2, out_channels=2, dropout_prob=0.5)

path = hf_hub_download(repo_id="your_username/dwi-flair-mismatch", filename="best_own_model.pth")
model.load_state_dict(torch.load(path, map_location="cpu"))
model.eval()

---

References

• Scheldeman et al. (2022): https://doi.org/10.1161/STROKEAHA.121.036871
• Kim et al. (2025): https://doi.org/10.1038/s41598-025-89305-5
• SOOP dataset: https://openneuro.org/datasets/ds004889
• ISLES 2022: https://doi.org/10.1038/s41597-022-01875-5