6 papers
ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning
Nusrat Binta Nizam, Fengbei Liu, Sunwoo Kwak +3
Multimodal medical models often degrade when inputs are missing, a common scenario in real-world clinical workflows. Separately, even when all modalities are present, modality domi…
Knockout: A simple way to handle missing inputs
Minh Nguyen, Batuhan K. Karaman, Heejong Kim +3
Deep learning models benefit from rich (e.g., multi-modal) input features. However, multimodal models might be challenging to deploy, because some inputs may be missing at inferenc…
GLACIAL: Granger and Learning-based Causality Analysis for Longitudinal Imaging Studies
Minh Nguyen, Gia H. Ngo, Mert R. Sabuncu
The Granger framework is useful for discovering causal relations in time-varying signals. However, most Granger causality (GC) methods are developed for densely sampled timeseries…
Efficient Identification of Direct Causal Parents via Invariance and Minimum Error Testing
Minh Nguyen, Mert R. Sabuncu
Invariant causal prediction (ICP) is a popular technique for finding causal parents (direct causes) of a target via exploiting distribution shifts and invariance testing (Peters et…
Effective Segmentation of Post-Treatment Gliomas Using Simple Approaches: Artificial Sequence Generation and Ensemble Models
Heejong Kim, Leo Milecki, Mina C Moghadam +5
Segmentation is a crucial task in the medical imaging field and is often an important primary step or even a prerequisite to the analysis of medical volumes. Yet treatments such as…
Adapting to Shifting Correlations with Unlabeled Data Calibration
Minh Nguyen, Alan Q. Wang, Heejong Kim +1
Distribution shifts between sites can seriously degrade model performance since models are prone to exploiting unstable correlations. Thus, many methods try to find features that a…