Natural language processing in the classification of radiology reports in benign gallbladder diseases O processamento de língua natural permite a classificação correta de laudos radiológicos em doenças benignas da vesícula biliar

Página do item simplificado
dc.contributor.authorSantina L.G.
dc.contributor.authorLeeb H.M.H.
dc.contributor.authorda Silvac V.M.
dc.contributor.authorCardosod E.F.
dc.contributor.authorGazzolae M.G.
dc.date.accessioned2025-05-01T06:28:25Z
dc.date.available2025-05-01T06:28:25Z
dc.date.issued2024
dc.description.abstract© 2024, Colegio Brasileiro de Radiologia. All rights reserved.Objective: To develop a natural language processing application capable of automatically identifying benign gallbladder diseases that require surgery, from radiology reports. Materials and Methods: We developed a text classifier to classify reports as describing benign diseases of the gallbladder that do or do not require surgery. We randomly selected 1,200 reports describing the gallbladder from our database, including different modalities. Four radiologists classified the reports as describing benign disease that should or should not be treated surgically. Two deep learning architectures were trained for classification: a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network. In order to represent words in vector form, the models included a Word2Vec representation, with dimensions of 300 or 1,000. The models were trained and evaluated by dividing the dataset into training, validation, and subsets (80/10/10). Results: The CNN and BiLSTM performed well in both dimensional spaces. For the 300- and 1,000-dimensional spaces, respectively, the F1-scores were 0.95945 and 0.95302 for the CNN model, compared with 0.96732 and 0.96732 for the BiLSTM model. Conclusion: Our models achieved high performance, regardless of the architecture and dimensional space employed.
dc.description.volume57
dc.identifier.doi10.1590/0100-3984.2023.0096-en
dc.identifier.issnNone
dc.identifier.urihttps://dspace.mackenzie.br/handle/10899/40625
dc.relation.ispartofRadiologia Brasileira
dc.rightsAcesso Aberto
dc.subject.otherlanguageArtificial intelligence
dc.subject.otherlanguagecomputer
dc.subject.otherlanguageDeep learning
dc.subject.otherlanguageNatural language processing
dc.subject.otherlanguageNeural networks
dc.subject.otherlanguageSupport vector machine
dc.titleNatural language processing in the classification of radiology reports in benign gallbladder diseases O processamento de língua natural permite a classificação correta de laudos radiológicos em doenças benignas da vesícula biliar
dc.typeArtigo
local.scopus.citations0
local.scopus.eid2-s2.0-105002160442
local.scopus.updated2025-05-01
local.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105002160442&origin=inward
Arquivos
Coleções
Artigos de periódico