2 citations · 8 across the 15 of their papers we have counts for
3 papers · 1 filter
Radiology-Aware Model-Based Evaluation Metric for Report Generation
Amos Calamida, Farhad Nooralahzadeh, Morteza Rohanian +3
We propose a new automated evaluation metric for machine-generated radiology reports using the successful COMET architecture adapted for the radiology domain. We train and publish…
Boosting Radiology Report Generation by Infusing Comparison Prior
Sanghwan Kim, Farhad Nooralahzadeh, Morteza Rohanian +5
Recent transformer-based models have made significant strides in generating radiology reports from chest X-ray images. However, a prominent challenge remains: these models often la…
Exploratory Analysis of Federated Learning Methods with Differential Privacy on MIMIC-III
Aron N. Horvath, Matteo Berchier, Farhad Nooralahzadeh +2
Background: Federated learning methods offer the possibility of training machine learning models on privacy-sensitive data sets, which cannot be easily shared. Multiple regulations…