Memory-based Cross-modal Semantic Alignment Network for Radiology Report Generation

arXiv:2404.00588v1 Announce Type: new
Abstract: Generating radiology reports automatically reduces the workload of radiologists and helps the diagnoses of specific diseases. Many existing methods take this task as modality transfer process. However, since the key information related to disease accounts for a small proportion in both image and report, it is hard for the model to learn the latent relation between the radiology image and its report, thus failing to generate fluent and accurate radiology reports. To tackle this problem, …

abstract alignment arxiv cs.ai cs.cv disease diseases however image information key memory modal network process radiology report reports semantic small the key transfer type