That’s the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data

Jered McInerney, Geoffrey Young, Jan-Willem van de Meent, Byron Wallace


Abstract
Pretraining multimodal models on Electronic Health Records (EHRs) provides a means of learning representations that can transfer to downstream tasks with minimal supervision. Recent multimodal models induce soft local alignments between image regions and sentences. This is of particular interest in the medical domain, where alignments might highlight regions in an image relevant to specific phenomena described in free-text. While past work has suggested that attention “heatmaps” can be interpreted in this manner, there has been little evaluation of such alignments. We compare alignments from a state-of-the-art multimodal (image and text) model for EHR with human annotations that link image regions to sentences. Our main finding is that the text has an often weak or unintuitive influence on attention; alignments do not consistently reflect basic anatomical information. Moreover, synthetic modifications — such as substituting “left” for “right” — do not substantially influence highlights. Simple techniques such as allowing the model to opt out of attending to the image and few-shot finetuning show promise in terms of their ability to improve alignments with very little or no supervision. We make our code and checkpoints open-source.
Anthology ID:
2022.emnlp-main.238
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3626–3648
Language:
URL:
https://aclanthology.org/2022.emnlp-main.238
DOI:
10.18653/v1/2022.emnlp-main.238
Bibkey:
Cite (ACL):
Jered McInerney, Geoffrey Young, Jan-Willem van de Meent, and Byron Wallace. 2022. That’s the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3626–3648, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
That’s the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data (McInerney et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.238.pdf