@inproceedings{kaliosis-etal-2024-data,
title = "A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning",
author = "Kaliosis, Panagiotis and
Pavlopoulos, John and
Charalampakos, Foivos and
Moschovis, Georgios and
Androutsopoulos, Ion",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.444",
pages = "7450--7466",
abstract = "Diagnostic Captioning (DC) automatically generates a diagnostic text from one or more medical images (e.g., X-rays, MRIs) of a patient. Treated as a draft, the generated text may assist clinicians, by providing an initial estimation of the patient{'}s condition, speeding up and helping safeguard the diagnostic process. The accuracy of a diagnostic text, however, strongly depends on how well the key medical conditions depicted in the images are expressed. We propose a new $\textit{data-driven}$ guided decoding method that incorporates medical information, in the form of existing tags capturing key conditions of the image(s), into the beam search of the diagnostic text generation process. We evaluate the proposed method on two medical datasets using four DC systems that range from generic image-to-text systems with CNN encoders and RNN decoders to pre-trained Large Language Models. The latter can also be used in few- and zero-shot learning scenarios. In most cases, the proposed mechanism improves performance with respect to all evaluation measures. We provide an open-source implementation of the proposed method at https://github.com/nlpaueb/dmmcs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaliosis-etal-2024-data">
<titleInfo>
<title>A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Panagiotis</namePart>
<namePart type="family">Kaliosis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Foivos</namePart>
<namePart type="family">Charalampakos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Moschovis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ion</namePart>
<namePart type="family">Androutsopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Diagnostic Captioning (DC) automatically generates a diagnostic text from one or more medical images (e.g., X-rays, MRIs) of a patient. Treated as a draft, the generated text may assist clinicians, by providing an initial estimation of the patient’s condition, speeding up and helping safeguard the diagnostic process. The accuracy of a diagnostic text, however, strongly depends on how well the key medical conditions depicted in the images are expressed. We propose a new data-driven guided decoding method that incorporates medical information, in the form of existing tags capturing key conditions of the image(s), into the beam search of the diagnostic text generation process. We evaluate the proposed method on two medical datasets using four DC systems that range from generic image-to-text systems with CNN encoders and RNN decoders to pre-trained Large Language Models. The latter can also be used in few- and zero-shot learning scenarios. In most cases, the proposed mechanism improves performance with respect to all evaluation measures. We provide an open-source implementation of the proposed method at https://github.com/nlpaueb/dmmcs.</abstract>
<identifier type="citekey">kaliosis-etal-2024-data</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.444</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7450</start>
<end>7466</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning
%A Kaliosis, Panagiotis
%A Pavlopoulos, John
%A Charalampakos, Foivos
%A Moschovis, Georgios
%A Androutsopoulos, Ion
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F kaliosis-etal-2024-data
%X Diagnostic Captioning (DC) automatically generates a diagnostic text from one or more medical images (e.g., X-rays, MRIs) of a patient. Treated as a draft, the generated text may assist clinicians, by providing an initial estimation of the patient’s condition, speeding up and helping safeguard the diagnostic process. The accuracy of a diagnostic text, however, strongly depends on how well the key medical conditions depicted in the images are expressed. We propose a new data-driven guided decoding method that incorporates medical information, in the form of existing tags capturing key conditions of the image(s), into the beam search of the diagnostic text generation process. We evaluate the proposed method on two medical datasets using four DC systems that range from generic image-to-text systems with CNN encoders and RNN decoders to pre-trained Large Language Models. The latter can also be used in few- and zero-shot learning scenarios. In most cases, the proposed mechanism improves performance with respect to all evaluation measures. We provide an open-source implementation of the proposed method at https://github.com/nlpaueb/dmmcs.
%U https://aclanthology.org/2024.findings-acl.444
%P 7450-7466
Markdown (Informal)
[A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning](https://aclanthology.org/2024.findings-acl.444) (Kaliosis et al., Findings 2024)
ACL
- Panagiotis Kaliosis, John Pavlopoulos, Foivos Charalampakos, Georgios Moschovis, and Ion Androutsopoulos. 2024. A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning. In Findings of the Association for Computational Linguistics ACL 2024, pages 7450–7466, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.