Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916133884395520 |
|---|---|
| author | Bannur, Shruthi Hyland, Stephanie Liu, Qianchu Pérez-García, Fernando Ilse, Maximilian Castro, Daniel C. Boecking, Benedikt Sharma, Harshita Bouzid, Kenza Thieme, Anja Schwaighofer, Anton Wetscherek, Maria Lungren, Matthew P. Nori, Aditya Alvarez-Valle, Javier Oktay, Ozan |
| author_facet | Bannur, Shruthi Hyland, Stephanie Liu, Qianchu Pérez-García, Fernando Ilse, Maximilian Castro, Daniel C. Boecking, Benedikt Sharma, Harshita Bouzid, Kenza Thieme, Anja Schwaighofer, Anton Wetscherek, Maria Lungren, Matthew P. Nori, Aditya Alvarez-Valle, Javier Oktay, Ozan |
| contents | Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not only introduce poor alignment between the modalities but also a missed opportunity to exploit rich self-supervision through existing temporal content in the data. In this work, we explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model. It is designed to be versatile to arising challenges such as pose variations and missing input images across time. The resulting model excels on downstream tasks both in single- and multi-image setups, achieving state-of-the-art performance on (I) progression classification, (II) phrase grounding, and (III) report generation, whilst offering consistent improvements on disease classification and sentence-similarity tasks. We release a novel multi-modal temporal benchmark dataset, MS-CXR-T, to quantify the quality of vision-language representations in terms of temporal semantics. Our experimental results show the advantages of incorporating prior images and reports to make most use of the data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_04558 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing Bannur, Shruthi Hyland, Stephanie Liu, Qianchu Pérez-García, Fernando Ilse, Maximilian Castro, Daniel C. Boecking, Benedikt Sharma, Harshita Bouzid, Kenza Thieme, Anja Schwaighofer, Anton Wetscherek, Maria Lungren, Matthew P. Nori, Aditya Alvarez-Valle, Javier Oktay, Ozan Computer Vision and Pattern Recognition Computation and Language Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not only introduce poor alignment between the modalities but also a missed opportunity to exploit rich self-supervision through existing temporal content in the data. In this work, we explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model. It is designed to be versatile to arising challenges such as pose variations and missing input images across time. The resulting model excels on downstream tasks both in single- and multi-image setups, achieving state-of-the-art performance on (I) progression classification, (II) phrase grounding, and (III) report generation, whilst offering consistent improvements on disease classification and sentence-similarity tasks. We release a novel multi-modal temporal benchmark dataset, MS-CXR-T, to quantify the quality of vision-language representations in terms of temporal semantics. Our experimental results show the advantages of incorporating prior images and reports to make most use of the data. |
| title | Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2301.04558 |