SAM with bounding-box prompts and transfer learning is reported to segment lung nodules with 97.08% Dice and classify malignancy with 96.71% accuracy, but the ground truth masks are generated by a geometric algorithm, not expert delineations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Advanced Lung Nodule Segmentation and Classification for Early Detection of Lung Cancer using SAM and Transfer Learning
SAM with bounding-box prompts and transfer learning is reported to segment lung nodules with 97.08% Dice and classify malignancy with 96.71% accuracy, but the ground truth masks are generated by a geometric algorithm, not expert delineations.