HalmosiL/nodule-segresnet-3d-small-sw

3D nodule segmentation — SegResNet (small), sliding-window recipe

Two-stage 3D nodule segmentation on lung-cropped CT at native 1 mm resolution. Trained on 128^3 nodule-biased patches (Focal Tversky + weighted CE, nodule CE weight 10), inference via 128^3 sliding windows (overlap 0.5, Gaussian blending).

Test (325 series): nodule Dice (micro) 0.5370, precision 0.4645, recall 0.6363; instance recall 0.868, instance precision 0.086.

Files: model.pth (weights-only state dict) + config.yaml (full training configuration). Training code, splits and reports: wernerp02/nodule-segmentation-demo.