Learning to ground medical text in a 3D human atlas

Dusan Grujicic, Gorjan Radevski, Tinne Tuytelaars, Matthew Blaschko


Abstract
In this paper, we develop a method for grounding medical text into a physically meaningful and interpretable space corresponding to a human atlas. We build on text embedding architectures such as Bert and introduce a loss function that allows us to reason about the semantic and spatial relatedness of medical texts by learning a projection of the embedding into a 3D space representing the human body. We quantitatively and qualitatively demonstrate that our proposed method learns a context sensitive and spatially aware mapping, in both the inter-organ and intra-organ sense, using a large scale medical text dataset from the “Large-scale online biomedical semantic indexing” track of the 2020 BioASQ challenge. We extend our approach to a self-supervised setting, and find it to be competitive with a classification based method, and a fully supervised variant of approach.
Anthology ID:
2020.conll-1.23
Volume:
Proceedings of the 24th Conference on Computational Natural Language Learning
Month:
November
Year:
2020
Address:
Online
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
302–312
Language:
URL:
https://aclanthology.org/2020.conll-1.23
DOI:
10.18653/v1/2020.conll-1.23
Bibkey:
Cite (ACL):
Dusan Grujicic, Gorjan Radevski, Tinne Tuytelaars, and Matthew Blaschko. 2020. Learning to ground medical text in a 3D human atlas. In Proceedings of the 24th Conference on Computational Natural Language Learning, pages 302–312, Online. Association for Computational Linguistics.
Cite (Informal):
Learning to ground medical text in a 3D human atlas (Grujicic et al., CoNLL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.conll-1.23.pdf
Optional supplementary material:
 2020.conll-1.23.OptionalSupplementaryMaterial.zip
Code
 gorjanradevski/text2atlas
Data
BioASQ