A VAE-based multiple instance learning model predicts rectal cancer lymph node metastasis from MRI with cross-validated AUC 0.858 on 168 patients, but the state-of-the-art and radiologist-exceeding claims are weakly supported.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpretable Prediction of Lymph Node Metastasis in Rectal Cancer MRI Using Variational Autoencoders
A VAE-based multiple instance learning model predicts rectal cancer lymph node metastasis from MRI with cross-validated AUC 0.858 on 168 patients, but the state-of-the-art and radiologist-exceeding claims are weakly supported.