# Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models

arXiv: https://arxiv.org/abs/2512.13144 · HTML: https://mlsanity.com/paper/2512.13144/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Builds on (most cited first, 15 of 15)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Reading Race: AI Recognises Patient's Racial Identity In Medical Images](https://mlsanity.com/paper/2107.10356/) (2021)
- [SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound](https://mlsanity.com/paper/1612.05601/) (2016)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts](https://mlsanity.com/paper/2009.10132/) (2020)
- [Shortcut Learning in Medical Image Segmentation](https://mlsanity.com/paper/2403.06748/) (2024)
- [Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries](https://mlsanity.com/paper/2209.09610/) (2022)
- [Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessment](https://mlsanity.com/paper/2403.08700/) (2024)
- [DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation](https://mlsanity.com/paper/2205.11115/) (2022)
- [Debiasing Counterfactuals In the Presence of Spurious Correlations](https://mlsanity.com/paper/2308.10984/) (2023)
- [DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanations](https://mlsanity.com/paper/2405.09288/) (2024)
- [Learning semantic image quality for fetal ultrasound from noisy ranking annotation](https://mlsanity.com/paper/2402.08294/) (2024)
- [Removing confounding information from fetal ultrasound images](https://mlsanity.com/paper/2303.13918/) (2023)
- [Determining Fetal Orientations From Blind Sweep Ultrasound Video](https://mlsanity.com/paper/2504.06836/) (2025)

## Abstract (arXiv)

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.