DocumentCode :
583224
Title :
Extracting BI-RADS features from Portuguese clinical texts
Author :
Nassif, Houssam ; Cunha, F. ; Moreira, Ines C. ; Cruz-Correia, Ricardo ; Sousa, Emanuel ; Page, Douglas ; Burnside, Elizabeth ; Dutra, Ines
Author_Institution :
Univ. of Wisconsin, Madison, WI, USA
fYear :
2012
fDate :
4-7 Oct. 2012
Firstpage :
1
Lastpage :
4
Abstract :
In this work we build the first BI-RADS parser for Portuguese free texts, modeled after existing approaches to extract BI-RADS features from English medical records. Our concept finder uses a semantic grammar based on the BI-RADS lexicon and on iterative transferred expert knowledge. We compare the performance of our algorithm to manual annotation by a specialist in mammography. Our results show that our parser´s performance is comparable to the manual method.
Keywords :
biological organs; cancer; feature extraction; grammars; mammography; medical information systems; natural language processing; text analysis; BI-RADS feature extraction; BI-RADS lexicon; BI-RADS parser; English medical records; Portuguese clinical texts; Portuguese free texts; breast imaging reporting-and-data system; mammography; manual annotation; semantic grammar; Cancer; Data mining; Educational institutions; Feature extraction; Manuals; Medical diagnostic imaging; BI-RADS descriptors; breast cancer; feature extraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Bioinformatics and Biomedicine (BIBM), 2012 IEEE International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
978-1-4673-2559-2
Electronic_ISBN :
978-1-4673-2558-5
Type :
conf
DOI :
10.1109/BIBM.2012.6392613
Filename :
6392613
Link To Document :
بازگشت