Wavelet features with elastic net achieve patient-level AUC 0.874 on CESM malignancy detection under patient-grouped CV, matching ResNet-50 performance while providing explicit physical interpretability per predictor.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Masked complex non-decimated wavelet features for patient-level classification of contrast-enhanced mammography
Wavelet features with elastic net achieve patient-level AUC 0.874 on CESM malignancy detection under patient-grouped CV, matching ResNet-50 performance while providing explicit physical interpretability per predictor.