This is the first framework that successfully combines 3 tasks: ranking, tagging, and diagnostic captioning with focus on radiography exams that contain abnormalities.
The study sought to assist practitioners in identifying and prioritizing radiography exams that are more likely to contain abnormalities, and provide them with a diagnosis in order to manage heavy workload more efficiently (eg, during a pandemic) or avoid mistakes due to tiredness. With this article we introduced RTEx, a novel framework for (1) ranking radiography exams based on their probability to be abnormal, (2) generating abnormality tags for abnormal exams, and (3) providing a diagnostic explanation in natural language for each abnormal exam. Our framework consists of deep learning and retrieval methods and is assessed on 2 publicly available datasets.
@article{10.1093/jamia/ocab046,
author = {Kougia, Vasiliki and Pavlopoulos, John and Papapetrou, Panagiotis and Gordon, Max},
title = "{RTEX: A novel framework for ranking, tagging, and explanatory diagnostic captioning of radiography exams}",
journal = {Journal of the American Medical Informatics Association},
volume = {28},
number = {8},
pages = {1651-1659},
year = {2021},
month = {04},
issn = {1527-974X},
doi = {10.1093/jamia/ocab046},
url = {https://doi.org/10.1093/jamia/ocab046},
eprint = {https://academic.oup.com/jamia/article-pdf/28/8/1651/39502314/ocab046.pdf},
}