Clinically Accurate Chest X-Ray Report Generation

Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew McDermott, Willie Boag, Wei-Hung Weng, Peter Szolovits, Marzyeh Ghassemi
; Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:249-269, 2019.

Abstract

The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from computer vision and natural language generation to produce readable reports. However, these works often fail to account for the particular nuances of the radiology domain, and, in particular, the critical importance of clinical accuracy in the resulting generated reports. In this work, we present a domain-aware automatic chest X-ray radiology report generation system which first predicts what topics will be discussed in the report, then conditionally generates sentences corresponding to these topics. The resulting system is fine-tuned using reinforcement learning, considering both readability and clinical accuracy, as assessed by the proposed Clinically Coherent Reward. We verify this system on two datasets, Open-I and MIMICCXR, and demonstrate that our model offers marked improvements on both language generation metrics and CheXpert assessed accuracy over a variety of competitive baselines.

Cite this Paper


BibTeX
@InProceedings{pmlr-v106-liu19a, title = {Clinically Accurate Chest X-Ray Report Generation}, author = {Liu, Guanxiong and Hsu, Tzu-Ming Harry and McDermott, Matthew and Boag, Willie and Weng, Wei-Hung and Szolovits, Peter and Ghassemi, Marzyeh}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {249--269}, year = {2019}, editor = {Finale Doshi-Velez and Jim Fackler and Ken Jung and David Kale and Rajesh Ranganath and Byron Wallace and Jenna Wiens}, volume = {106}, series = {Proceedings of Machine Learning Research}, address = {Ann Arbor, Michigan}, month = {09--10 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v106/liu19a/liu19a.pdf}, url = {http://proceedings.mlr.press/v106/liu19a.html}, abstract = {The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from computer vision and natural language generation to produce readable reports. However, these works often fail to account for the particular nuances of the radiology domain, and, in particular, the critical importance of clinical accuracy in the resulting generated reports. In this work, we present a domain-aware automatic chest X-ray radiology report generation system which first predicts what topics will be discussed in the report, then conditionally generates sentences corresponding to these topics. The resulting system is fine-tuned using reinforcement learning, considering both readability and clinical accuracy, as assessed by the proposed Clinically Coherent Reward. We verify this system on two datasets, Open-I and MIMICCXR, and demonstrate that our model offers marked improvements on both language generation metrics and CheXpert assessed accuracy over a variety of competitive baselines.} }
Endnote
%0 Conference Paper %T Clinically Accurate Chest X-Ray Report Generation %A Guanxiong Liu %A Tzu-Ming Harry Hsu %A Matthew McDermott %A Willie Boag %A Wei-Hung Weng %A Peter Szolovits %A Marzyeh Ghassemi %B Proceedings of the 4th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2019 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v106-liu19a %I PMLR %J Proceedings of Machine Learning Research %P 249--269 %U http://proceedings.mlr.press %V 106 %W PMLR %X The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from computer vision and natural language generation to produce readable reports. However, these works often fail to account for the particular nuances of the radiology domain, and, in particular, the critical importance of clinical accuracy in the resulting generated reports. In this work, we present a domain-aware automatic chest X-ray radiology report generation system which first predicts what topics will be discussed in the report, then conditionally generates sentences corresponding to these topics. The resulting system is fine-tuned using reinforcement learning, considering both readability and clinical accuracy, as assessed by the proposed Clinically Coherent Reward. We verify this system on two datasets, Open-I and MIMICCXR, and demonstrate that our model offers marked improvements on both language generation metrics and CheXpert assessed accuracy over a variety of competitive baselines.
APA
Liu, G., Hsu, T.H., McDermott, M., Boag, W., Weng, W., Szolovits, P. & Ghassemi, M.. (2019). Clinically Accurate Chest X-Ray Report Generation. Proceedings of the 4th Machine Learning for Healthcare Conference, in PMLR 106:249-269

Related Material