An anatomy-informed U-Net using TotalSegmentator-derived organ exclusion masks reduces false positives and improves boundary accuracy for abdominal aortic aneurysm segmentation compared to a standard U-Net on limited data.
Ahmedt-Aristizabal, M
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
citing papers explorer
-
Anatomy-Informed Deep Learning for Abdominal Aortic Aneurysm Segmentation
An anatomy-informed U-Net using TotalSegmentator-derived organ exclusion masks reduces false positives and improves boundary accuracy for abdominal aortic aneurysm segmentation compared to a standard U-Net on limited data.
-
Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.