@inproceedings{nishino-etal-2022-factual,
title = "Factual Accuracy is not Enough: Planning Consistent Description Order for Radiology Report Generation",
author = "Nishino, Toru and
Miura, Yasuhide and
Taniguchi, Tomoki and
Ohkuma, Tomoko and
Suzuki, Yuki and
Kido, Shoji and
Tomiyama, Noriyuki",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.480",
doi = "10.18653/v1/2022.emnlp-main.480",
pages = "7123--7138",
abstract = "Radiology report generation systems have the potential to reduce the workload of radiologists by automatically describing the findings in medical images. To broaden the application of the report generation system, the system should generate reports that are not only factually accurate but also chronologically consistent, describing images that are presented in time order, that is, the correct order. We employ a planning-based radiology report generation system that generates the overall structure of reports as {``}plans{'}{''} prior to generating reports that are accurate and consistent in order. Additionally, we propose a novel reinforcement learning and inference method, Coordinated Planning (CoPlan), that includes a content planner and a text generator to train and infer in a coordinated manner to alleviate the cascading of errors that are often inherent in planning-based models. We conducted experiments with single-phase diagnostic reports in which the factual accuracy is critical and multi-phase diagnostic reports in which the description order is critical. Our proposed CoPlan improves the content order score by 5.1 pt in time series critical scenarios and the clinical factual accuracy F-score by 9.1 pt in time series irrelevant scenarios, compared those of the baseline models without CoPlan.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishino-etal-2022-factual">
<titleInfo>
<title>Factual Accuracy is not Enough: Planning Consistent Description Order for Radiology Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toru</namePart>
<namePart type="family">Nishino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhide</namePart>
<namePart type="family">Miura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Taniguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoko</namePart>
<namePart type="family">Ohkuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoji</namePart>
<namePart type="family">Kido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noriyuki</namePart>
<namePart type="family">Tomiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Radiology report generation systems have the potential to reduce the workload of radiologists by automatically describing the findings in medical images. To broaden the application of the report generation system, the system should generate reports that are not only factually accurate but also chronologically consistent, describing images that are presented in time order, that is, the correct order. We employ a planning-based radiology report generation system that generates the overall structure of reports as “plans”’ prior to generating reports that are accurate and consistent in order. Additionally, we propose a novel reinforcement learning and inference method, Coordinated Planning (CoPlan), that includes a content planner and a text generator to train and infer in a coordinated manner to alleviate the cascading of errors that are often inherent in planning-based models. We conducted experiments with single-phase diagnostic reports in which the factual accuracy is critical and multi-phase diagnostic reports in which the description order is critical. Our proposed CoPlan improves the content order score by 5.1 pt in time series critical scenarios and the clinical factual accuracy F-score by 9.1 pt in time series irrelevant scenarios, compared those of the baseline models without CoPlan.</abstract>
<identifier type="citekey">nishino-etal-2022-factual</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.480</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.480</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7123</start>
<end>7138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Factual Accuracy is not Enough: Planning Consistent Description Order for Radiology Report Generation
%A Nishino, Toru
%A Miura, Yasuhide
%A Taniguchi, Tomoki
%A Ohkuma, Tomoko
%A Suzuki, Yuki
%A Kido, Shoji
%A Tomiyama, Noriyuki
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F nishino-etal-2022-factual
%X Radiology report generation systems have the potential to reduce the workload of radiologists by automatically describing the findings in medical images. To broaden the application of the report generation system, the system should generate reports that are not only factually accurate but also chronologically consistent, describing images that are presented in time order, that is, the correct order. We employ a planning-based radiology report generation system that generates the overall structure of reports as “plans”’ prior to generating reports that are accurate and consistent in order. Additionally, we propose a novel reinforcement learning and inference method, Coordinated Planning (CoPlan), that includes a content planner and a text generator to train and infer in a coordinated manner to alleviate the cascading of errors that are often inherent in planning-based models. We conducted experiments with single-phase diagnostic reports in which the factual accuracy is critical and multi-phase diagnostic reports in which the description order is critical. Our proposed CoPlan improves the content order score by 5.1 pt in time series critical scenarios and the clinical factual accuracy F-score by 9.1 pt in time series irrelevant scenarios, compared those of the baseline models without CoPlan.
%R 10.18653/v1/2022.emnlp-main.480
%U https://aclanthology.org/2022.emnlp-main.480
%U https://doi.org/10.18653/v1/2022.emnlp-main.480
%P 7123-7138
Markdown (Informal)
[Factual Accuracy is not Enough: Planning Consistent Description Order for Radiology Report Generation](https://aclanthology.org/2022.emnlp-main.480) (Nishino et al., EMNLP 2022)
ACL