A hybrid CNN-transformer U-Net with structured convolutions, spatial-shift MLP links, and a superpixel transformer reports a Dice score of 89.04% on LIDC-IDRI lung nodule segmentation, about 4.5 points above compared methods.
Modality- specific segmentation network for lung tumor segmenta- tion in pet-ct images,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
S3TU-Net: Structured Convolution and Superpixel Transformer for Lung Nodule Segmentation
A hybrid CNN-transformer U-Net with structured convolutions, spatial-shift MLP links, and a superpixel transformer reports a Dice score of 89.04% on LIDC-IDRI lung nodule segmentation, about 4.5 points above compared methods.