Papers for

radiology ai developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

NnU-Net shows varied accuracy on different brain tumor types

Assessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026

Abstract: BraTS-GoAT evaluates tumor segmentation across heterogeneous populations. We trained a conventional 3D nnU-Net on 1,351 labeled cases using five-fold cross-validation and 1,000 epochs per fold. The final predictor averaged all folds and applied test-time mirroring. On pooled official validation, global DSC values were 0.7805, 0.8288, and 0.8854 for enhancing tumor (ET), tumor core (TC), and whole tumor (WT). Under matched fold-0 inference, mean regional Dice decreased from 0.9058 on source out-of-fold (OOF) cases to 0.8310 on pooled validation (difference--0.0747). Mirroring gave small single-fold gains but no clear ensemble benefit; a residual-encoder alternative reached 0.8282 mean Dice. In labeled OOF predictions, failure cases had substantially smaller reference ET volumes; after adjustment for ET and WT volume, lower Dice remained associated with more disconnected ET components and a smaller fraction of ET contained in the largest component.

Mon 14 SeptComputer Vision and Pattern Recognition

The gist

Segmenting brain tumors accurately in medical images is important but challenging because tumors vary a lot. The authors trained a popular deep learning model called nnU-Net on many brain tumor cases and tested how well it works on different tumor types. They found the model did best for whole tumors and less well on parts like enhancing or core tumors, especially if these parts are small or broken into many pieces. Their study helps understand the strengths and limits of this model on diverse tumor data.

Open → 2609.15524v1