Search Results for author: Koji Fujimoto

Found 3 papers, 1 papers with code

Progressive Transformer-Based Generation of Radiology Reports

1 code implementation Findings (EMNLP) 2021 Farhad Nooralahzadeh, Nicolas Perez Gonzalez, Thomas Frauenfelder, Koji Fujimoto, Michael Krauthammer

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.

Text Generation

Lung segmentation on chest x-ray images in patients with severe abnormal findings using deep learning

no code implementations21 Aug 2019 Mizuho Nishio, Koji Fujimoto, Kaori Togashi

Results: Our results demonstrated that using baseline U-net yielded poorer lung segmentation results in our database than those in the JSRT and Montgomery databases, implying that robust segmentation of lungs may be difficult because of severe abnormalities.

Cannot find the paper you are looking for? You can Submit a new open access paper.