CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation

2026-01-21

AI Summary

This work addresses the misalignment between generated radiology reports and medical images—commonly caused by inaccurate visual grounding and factual inconsistencies—by proposing CURE, a novel framework that integrates error-aware dynamic curriculum learning with multi-task training. Without requiring additional data, CURE jointly optimizes phrase-level visual grounding, localized report generation, and anatomy-guided report synthesis. The approach significantly enhances vision–language alignment, achieving a +0.37 improvement in grounding accuracy (measured by IoU), a +0.188 gain in report quality (CXRFEScore), and an 18.6% reduction in hallucinations. These advances collectively strengthen anatomical consistency and clinical reliability in automated radiology reporting.

Technology Category

• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Medical vision-language models can automate the generation of radiology reports but struggle with accurate visual grounding and factual consistency. Existing models often misalign textual findings with visual evidence, leading to unreliable or weakly grounded predictions. We present CURE, an error-aware curriculum learning framework that improves grounding and report quality without any additional data. CURE fine-tunes a multimodal instructional model on phrase grounding, grounded report generation, and anatomy-grounded report generation using public datasets. The method dynamically adjusts sampling based on model performance, emphasizing harder samples to improve spatial and textual alignment. CURE improves grounding accuracy by +0.37 IoU, boosts report quality by +0.188 CXRFEScore, and reduces hallucinations by 18.6%. CURE is a data-efficient framework that enhances both grounding accuracy and report reliability. Code is available at https://github.com/PabloMessina/CURE and model weights at https://huggingface.co/pamessina/medgemma-4b-it-cure

Problem

• visual grounding
• factual consistency
• radiology report generation
• medical vision-language models
• hallucination

Innovation

• curriculum learning
• visual grounding
• medical report generation
• multimodal instruction tuning
• hallucination reduction