Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training
| Autor: | Moon, Jong Hak, Lee, Hyungyung, Shin, Woncheol, Kim, Young-Hak, Choi, Edward |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | IEEE Journal of Biomedical and Health Informatics 2022 |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1109/JBHI.2022.3207502 |
| Popis: | Recently a number of studies demonstrated impressive performance on diverse vision-language multi-modal tasks such as image captioning and visual question answering by extending the BERT architecture with multi-modal pre-training objectives. In this work we explore a broad set of multi-modal representation learning tasks in the medical domain, specifically using radiology images and the unstructured report. We propose Medical Vision Language Learner (MedViLL), which adopts a BERT-based architecture combined with a novel multi-modal attention masking scheme to maximize generalization performance for both vision-language understanding tasks (diagnosis classification, medical image-report retrieval, medical visual question answering) and vision-language generation task (radiology report generation). By statistically and rigorously evaluating the proposed model on four downstream tasks with three radiographic image-report datasets (MIMIC-CXR, Open-I, and VQA-RAD), we empirically demonstrate the superior downstream task performance of MedViLL against various baselines, including task-specific architectures. The source code is publicly available at: https://github.com/SuperSupermoon/MedViLL Comment: Accepted by IEEE Journal of Biomedical and Health Informatics |
| Databáze: | arXiv |
| Externí odkaz: |
|