Cross-window knowledge distillation raises per-window AUC by 10-16 points in pulmonary CT by transferring latent pathological signatures from a teacher encoder on the most informative window to students on other windows.
PE-Ynet: a novel attention-based multi-task model for pulmonary embolism detection using CT pulmonary angiography (CTPA) scan images.Phys Eng Sci Med, 47(3):863–880
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncovering Latent Pathological Signatures in Pulmonary CT via Cross-Window Knowledge Distillation
Cross-window knowledge distillation raises per-window AUC by 10-16 points in pulmonary CT by transferring latent pathological signatures from a teacher encoder on the most informative window to students on other windows.