A dual cross-attention Siamese Swin Transformer model trained on image pairs from 135 patients achieves 81.76% balanced accuracy, 90.07% sensitivity, and 72.86% specificity on a held-out set of 62 patients for distinguishing clinical complete response from local regrowth in rectal cancer endoscopy.
Mldrl: Multi-loss disentangled representation learning for predicting esophageal cancer response to neoadju- vant chemoradiotherapy using longitudinal ct images,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dual Cross-Attention Siamese Transformer for Rectal Tumor Regrowth Assessment in Watch-and-Wait Endoscopy
A dual cross-attention Siamese Swin Transformer model trained on image pairs from 135 patients achieves 81.76% balanced accuracy, 90.07% sensitivity, and 72.86% specificity on a held-out set of 62 patients for distinguishing clinical complete response from local regrowth in rectal cancer endoscopy.