Conference item icon

Conference item

Weakly supervised captioning of ultrasound images

Abstract:
Medical image captioning models generate text to describe the semantic contents of an image, aiding the non-experts in understanding and interpretation. We propose a weakly-supervised approach to improve the performance of image captioning models on small image-text datasets by leveraging a large anatomically-labelled image classification dataset. Our method generates pseudo-captions (weak labels) for caption-less but anatomically-labelled (class-labelled) images using an encoder-decoder sequence-to-sequence model. The augmented dataset is used to train an image-captioning model in a weakly supervised learning manner. For fetal ultrasound, we demonstrate that the proposed augmentation approach outperforms the baseline on semantics and syntax-based metrics, with nearly twice as much improvement in value on BLEU-1 and ROUGE-L. Moreover, we observe that superior models are trained with the proposed data augmentation, when compared with the existing regularization techniques. This work allows seamless automatic annotation of images that lack human-prepared descriptive captions for training image-captioning models. Using pseudo-captions in the training data is particularly useful for medical image captioning when significant time and effort of medical experts is required to obtain real image captions.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Publisher copy:
10.1007/978-3-031-12053-4_14

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
St Hilda's College
Role:
Author
ORCID:
0000-0002-3060-3772


Publisher:
Springer
Pages:
187-198
Series:
Lecture Notes in Computer Science
Series number:
13413
Publication date:
2022-07-25
Event title:
26th Medical Image Understanding and Analysis (MUIA 2022)
Event location:
Cambridge, UK
Event website:
https://www.miua2022.com/
Event start date:
2022-07-27
Event end date:
2022-07-29
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
ISBN:
9783031120527


Language:
English
Keywords:
Pubs id:
1278280
Local pid:
pubs:1278280
Deposit date:
2023-02-21
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP