A Survey on Biomedical Image Captioning
It addresses the need for automated assistance in medical diagnosis by summarizing advancements in biomedical image captioning, but is incremental as a survey with baseline improvements.
This paper presents the first survey on biomedical image captioning, covering datasets, evaluation measures, and state-of-the-art methods, and introduces a baseline that outperforms existing systems on one dataset.
Image captioning applied to biomedical images can assist and accelerate the diagnosis process followed by clinicians. This article is the first survey of biomedical image captioning, discussing datasets, evaluation measures, and state of the art methods. Additionally, we suggest two baselines, a weak and a stronger one; the latter outperforms all current state of the art systems on one of the datasets.