An end-to-end DL pipeline automates DCE-MRI analysis for brain tumors, introduces a cubic vascular input function model that lowers fitting error, and processes scans in under 3 minutes on one GPU while claiming state-of-the-art accuracy on BraTS and QIBA benchmarks plus 44 clinical cases.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fully-automated deep learning-powered system for DCE-MRI analysis of brain tumors
An end-to-end DL pipeline automates DCE-MRI analysis for brain tumors, introduces a cubic vascular input function model that lowers fitting error, and processes scans in under 3 minutes on one GPU while claiming state-of-the-art accuracy on BraTS and QIBA benchmarks plus 44 clinical cases.