Automatic Caption Generation for Chest X-Ray Using CNN Algorithm
Simaran Singh, Pandey, Pallavi, Atul Kumar, Srivastava, Vibha · Zenodo (CERN European Organization for Nuclear Research) · 2023
The automatic caption generation of chest X-ray report is a hot research topic at present. Image captioning aims to automatically describe the relationship of an image with a sentence, and this work has attracted research from both computer vision and natural language processing research communities. This research paper proposes a novel approach to automatically generating captions for medical images using Convolutional Neural Network (CNN) algorithm. The system was trained on a large dataset of medical images and their corresponding captions, and was evaluated using a variety of metrics including BLEU score and human evaluation. The results indicate that the proposed approach outperforms existing captioning systems in terms of caption accuracy and fluency. The proposed system has potential applications in the healthcare domain, where accurate and timely description of medical images can be critical for diagnosis and treatment.