Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models
This provides a tool for verifying model trustworthiness in medical imaging, addressing concerns about shortcut learning for clinicians and researchers, though it is incremental as it builds on existing interpretability methods.
The paper tackled the problem of shortcut learning in deep medical imaging models by introducing Weight Space Correlation Analysis to quantify feature utilization, showing that an SA-SonoNet model for preterm birth prediction selectively used clinically relevant features while ignoring irrelevant metadata like scanner type.
Deep learning models in medical imaging are susceptible to shortcut learning, relying on confounding metadata (e.g., scanner model) that is often encoded in image embeddings. The crucial question is whether the model actively utilizes this encoded information for its final prediction. We introduce Weight Space Correlation Analysis, an interpretable methodology that quantifies feature utilization by measuring the alignment between the classification heads of a primary clinical task and auxiliary metadata tasks. We first validate our method by successfully detecting artificially induced shortcut learning. We then apply it to probe the feature utilization of an SA-SonoNet model trained for Spontaneous Preterm Birth (sPTB) prediction. Our analysis confirmed that while the embeddings contain substantial metadata, the sPTB classifier's weight vectors were highly correlated with clinically relevant factors (e.g., birth weight) but decoupled from clinically irrelevant acquisition factors (e.g. scanner). Our methodology provides a tool to verify model trustworthiness, demonstrating that, in the absence of induced bias, the clinical model selectively utilizes features related to the genuine clinical signal.