Vision-Language Models for Automated Chest X-ray Interpretation: Leveraging ViT and GPT-2
This addresses the bottleneck of manual, error-prone radiology report generation for clinical workflows, but it is incremental as it tests existing model combinations on a known dataset.
The study tackled automated chest X-ray report generation by evaluating multimodal models combining vision transformers (ViT-B16 and SWIN) with language models (BART and GPT-2), finding that the SWIN-BART model achieved the best results on metrics like ROUGE, BLEU, and BERTScore.
Radiology plays a pivotal role in modern medicine due to its non-invasive diagnostic capabilities. However, the manual generation of unstructured medical reports is time consuming and prone to errors. It creates a significant bottleneck in clinical workflows. Despite advancements in AI-generated radiology reports, challenges remain in achieving detailed and accurate report generation. In this study we have evaluated different combinations of multimodal models that integrate Computer Vision and Natural Language Processing to generate comprehensive radiology reports. We employed a pretrained Vision Transformer (ViT-B16) and a SWIN Transformer as the image encoders. The BART and GPT-2 models serve as the textual decoders. We used Chest X-ray images and reports from the IU-Xray dataset to evaluate the usability of the SWIN Transformer-BART, SWIN Transformer-GPT-2, ViT-B16-BART and ViT-B16-GPT-2 models for report generation. We aimed at finding the best combination among the models. The SWIN-BART model performs as the best-performing model among the four models achieving remarkable results in almost all the evaluation metrics like ROUGE, BLEU and BERTScore.