Inspired by Curriculum Learning, we propose a consecutive (i.e., image-to-text-to-text) generation framework where we divide the problem of radiology report generation into two steps. Contrary to generating the full radiology report from the image at once, the model generates global concepts from the image in the first step and then reforms them into finer and coherent texts using a transformer architecture. We follow the transformer-based sequence-to-sequence paradigm at each step. We improve upon the state-of-the-art on two benchmark datasets.
@article{arxiv.2102.09777,
title = {Progressive Transformer-Based Generation of Radiology Reports},
author = {Farhad Nooralahzadeh and Nicolas Perez Gonzalez and Thomas Frauenfelder and Koji Fujimoto and Michael Krauthammer},
journal= {arXiv preprint arXiv:2102.09777},
year = {2021}
}