Progressive Transformer-Based Generation of Radiology Reports
Farhad Nooralahzadeh | Nicolas Perez Gonzalez | Thomas Frauenfelder | Koji Fujimoto | Michael Krauthammer
Findings of the Association for Computational Linguistics: EMNLP 2021
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 transformer-based 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.