Emerging text-to-image (T2I) models perpetuate biases, creating stereotypical portrayals of disability. This study investigates whether an agent-based, human-in-loop, AI workflow, that iteratively refines user-provided queries, can produce fairer representations of disability compared to standard models like Stable Diffusion, DALL·E-3, and MidJourney. Sixteen raters (eight with disabilities and eight without) evaluated images generated from models, prompted with textual inputs that targeted professional, medical, or social contexts. In an initial survey, raters were asked if an image depicted a disability, the type of disability if present, and if the setting aligned with the given text prompt to the model. Qualitative comments were collected. A post-survey asked raters to choose which image of a pair (standard vs. agent-based workflow) more accurately represented disability. Results revealed that standard models disproportionately produced images featuring physical disabilities or wheelchairs (p < 0.001), consistent with broader dataset biases. In contrast, the agent-based model’s images were deemed more representative in approximately two-thirds of comparisons (p < 0.0001), especially among raters with disabilities. Qualitative analyses underscored the need for nuanced, contextually rich portrayals.These findings suggest disability bias and that targeted debiasing can help mitigate stereotypes in generative AI, fostering more equitable outputs.

Radiology reports are critical for clinical decision-making but often lack a standardized format, limiting both human interpretability and machine learning (ML) applications. While large language models (LLMs) have shown strong capabilities in reformatting clinical text, their high computational requirements, lack of transparency, and data privacy concerns hinder practical deployment. To address these challenges, we explore lightweight encoder-decoder models (<300M parameters)—specifically T5 and BERT2BERT—for structuring radiology reports from the MIMIC-CXR and CheXpert Plus datasets. We benchmark these models against eight open-source LLMs (1B–70B parameters), adapted using prefix prompting, in-context learning (ICL), and low-rank adaptation (LoRA) finetuning. Our best-performing lightweight model outperforms all LLMs adapted using prompt-based techniques on a human-annotated test set. While some LoRA-finetuned LLMs achieve modest gains over the lightweight model on the Findings section (BLEU 6.4%, ROUGE-L 4.8%, BERTScore 3.6%, F1-RadGraph 1.1%, GREEN 3.6%, and F1-SRR-BERT 4.3%), these improvements come at the cost of substantially greater computational resources. For example, LLaMA-3-70B incurred more than 400 times the inference time, cost, and carbon emissions compared to the lightweight model. These results underscore the potential of lightweight, task-specific models as sustainable and privacy-preserving solutions for structuring clinical text in resource-constrained healthcare settings.

Automated radiology report generation from chest X-ray (CXR) images has the potential to improve clinical efficiency and reduce radiologists’ workload. However, most datasets, including the publicly available MIMIC-CXR and CheXpert Plus, consist entirely of free-form reports, which are inherently variable and unstructured. This variability poses challenges for both generation and evaluation: existing models struggle to produce consistent, clinically meaningful reports, and standard evaluation metrics fail to capture the nuances of radiological interpretation. To address this, we introduce Structured Radiology Report Generation (SRRG), a new task that reformulates free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. We create a novel dataset by restructuring reports using large language models (LLMs) following strict structured reporting desiderata. Additionally, we introduce SRR-BERT, a fine-grained disease classification model trained on 55 labels, enabling more precise and clinically informed evaluation of structured reports. To assess report quality, we propose F1-SRR-BERT, a metric that leverages SRR-BERT’s hierarchical disease taxonomy to bridge the gap between free-text variability and structured clinical reporting. We validate our dataset through a reader study conducted by five board-certified radiologists and extensive benchmarking experiments.