Adding click prompts encoded as Euclidean distance transforms to an nnU-Net improves interactive whole-body PET/CT lesion segmentation over Gaussian encodings and baseline autoPET III models.
In: Inter- national Conference on Medical Image Computing and Computer-Assisted Inter- vention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Interactive Lesion Segmentation in Whole-Body PET/CT with Promptable Models
Adding click prompts encoded as Euclidean distance transforms to an nnU-Net improves interactive whole-body PET/CT lesion segmentation over Gaussian encodings and baseline autoPET III models.