Contrastive Learning with Counterfactual Explanations for Radiology Report Generation

TL;DR

This paper introduces CoFE, a novel framework for radiology report generation that uses counterfactual explanations to learn non-spurious visual features, improving report quality and clinical relevance.

Contribution

The paper proposes a counterfactual explanations-based approach combined with a learnable prompt for fine-tuning large language models in radiology report generation, enhancing robustness and accuracy.

Findings

Outperforms existing methods on two benchmarks.

Generates more semantically coherent reports.

Improves clinical efficacy metrics.

Abstract

Due to the common content of anatomy, radiology images with their corresponding reports exhibit high similarity. Such inherent data bias can predispose automatic report generation models to learn entangled and spurious representations resulting in misdiagnostic reports. To tackle these, we propose a novel \textbf{Co}unter\textbf{F}actual \textbf{E}xplanations-based framework (CoFE) for radiology report generation. Counterfactual explanations serve as a potent tool for understanding how decisions made by algorithms can be changed by asking ``what if'' scenarios. By leveraging this concept, CoFE can learn non-spurious visual representations by contrasting the representations between factual and counterfactual images. Specifically, we derive counterfactual images by swapping a patch between positive and negative samples until a predicted diagnosis shift occurs. Here, positive and negative samples are the most semantically similar but have different diagnosis labels. Additionally, CoFE employs a learnable prompt to efficiently fine-tune the pre-trained large language model, encapsulating both factual and counterfactual content to provide a more generalizable prompt representation. Extensive experiments on two benchmarks demonstrate that leveraging the counterfactual explanations enables CoFE to generate semantically coherent and factually complete reports and outperform in terms of language generation and clinical efficacy metrics.