SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models

arXiv:2404.17912v1 Announce Type: cross
Abstract: Radiology Report Generation (R2Gen) demonstrates how Multi-modal Large Language Models (MLLMs) can automate the creation of accurate and coherent radiological reports. Existing methods often hallucinate details in text-based reports that don't accurately reflect the image content. To mitigate this, we introduce a novel strategy, SERPENT-VLM (SElf Refining Radiology RePort GENeraTion using Vision Language Models), which improves the R2Gen task by integrating a self-refining mechanism into the MLLM framework. We employ a unique self-supervised loss that …

abstract arxiv automate cs.ai cs.cl cs.lg image language language models large language large language models mllms modal multi-modal novel radiology report reports strategy text type vision vlm