Radiologic text correction for better machine understanding

Abstract Radiologic reports often contain misspellings that compromise report quality and pose challenges for machine understanding methods, which require syntactical correctness. General automatic misspell correction solutions are less effective in specialized documents, such as spinal radiologic r...

Full description

Saved in:
Bibliographic Details
Main Authors: András Kicsi, Klaudia Szabó Ledenyi, László Vidács
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Engineering Reports
Subjects:
Online Access:https://doi.org/10.1002/eng2.12891
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850256014049280000
author András Kicsi
Klaudia Szabó Ledenyi
László Vidács
author_facet András Kicsi
Klaudia Szabó Ledenyi
László Vidács
author_sort András Kicsi
collection DOAJ
description Abstract Radiologic reports often contain misspellings that compromise report quality and pose challenges for machine understanding methods, which require syntactical correctness. General automatic misspell correction solutions are less effective in specialized documents, such as spinal radiologic reports, particularly in morphologically rich languages like Hungarian. Issues arise from complex conjugations and the modification of Latin terms per the rules of the native language. This study introduces a method for the automatic correction of these misspellings, utilizing the Hunspell software and field‐specific dictionaries. This approach, enhanced by linguistic analysis and statistical data, improves information retrieval, as demonstrated in machine‐learning‐based classification and rule‐based identification tasks. Notably, our method identified over 30% more valid errors than human annotators, highlighting its efficiency. We offer a primarily dictionary‐based solution for correcting highly specialized texts and explore the impact of nonword correction on machine understanding. This work underscores the significance of tailored spelling correction in enhancing text processing algorithms' accuracy.
format Article
id doaj-art-2b1f37bf303e4634b716ffce63ee2221
institution OA Journals
issn 2577-8196
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Engineering Reports
spelling doaj-art-2b1f37bf303e4634b716ffce63ee22212025-08-20T01:56:45ZengWileyEngineering Reports2577-81962024-12-01612n/an/a10.1002/eng2.12891Radiologic text correction for better machine understandingAndrás Kicsi0Klaudia Szabó Ledenyi1László Vidács2Department of Software Engineering University of Szeged Szeged HungaryDepartment of Software Engineering University of Szeged Szeged HungaryDepartment of Software Engineering University of Szeged Szeged HungaryAbstract Radiologic reports often contain misspellings that compromise report quality and pose challenges for machine understanding methods, which require syntactical correctness. General automatic misspell correction solutions are less effective in specialized documents, such as spinal radiologic reports, particularly in morphologically rich languages like Hungarian. Issues arise from complex conjugations and the modification of Latin terms per the rules of the native language. This study introduces a method for the automatic correction of these misspellings, utilizing the Hunspell software and field‐specific dictionaries. This approach, enhanced by linguistic analysis and statistical data, improves information retrieval, as demonstrated in machine‐learning‐based classification and rule‐based identification tasks. Notably, our method identified over 30% more valid errors than human annotators, highlighting its efficiency. We offer a primarily dictionary‐based solution for correcting highly specialized texts and explore the impact of nonword correction on machine understanding. This work underscores the significance of tailored spelling correction in enhancing text processing algorithms' accuracy.https://doi.org/10.1002/eng2.12891information retrievalmedical reportsmisspell correctionnatural language processing
spellingShingle András Kicsi
Klaudia Szabó Ledenyi
László Vidács
Radiologic text correction for better machine understanding
Engineering Reports
information retrieval
medical reports
misspell correction
natural language processing
title Radiologic text correction for better machine understanding
title_full Radiologic text correction for better machine understanding
title_fullStr Radiologic text correction for better machine understanding
title_full_unstemmed Radiologic text correction for better machine understanding
title_short Radiologic text correction for better machine understanding
title_sort radiologic text correction for better machine understanding
topic information retrieval
medical reports
misspell correction
natural language processing
url https://doi.org/10.1002/eng2.12891
work_keys_str_mv AT andraskicsi radiologictextcorrectionforbettermachineunderstanding
AT klaudiaszaboledenyi radiologictextcorrectionforbettermachineunderstanding
AT laszlovidacs radiologictextcorrectionforbettermachineunderstanding