Radiomics-based features for pattern recognition of lung cancer histopathology and metastases. (June 2018)

• Record Type: Journal Article
• Authors: Ferreira Junior, José Raniery; Koenigkam-Santos, Marcel; Cipriano, Federico Enrique Garcia; Fabro, Alexandre Todorovic; Azevedo-Marques, Paulo Mazzoncini de
• Is Part Of: Computer methods and programs in biomedicine. Volume 159(2018)
• Page Start: 23
• Page End: 30
• Publication Date: 2018-06
• Subjects: Lung cancer -- Metastasis prediction -- Pattern recognition -- Quantitative image analysis -- Radiomics; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2018.02.015
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Shape features presented greatest potential on nodal metastasis pattern recognition. Gray-level cooccurrence matrix texture features presented greatest potential on distant metastasis and histopathological pattern recognition. Our radiomics model may provide additional information for therapy decision support based on metastases prediction and aid the histopathological subtype diagnosis. Abstract: Background and Objectives: lung cancer is the leading cause of cancer-related deaths in the world, and its poor prognosis varies markedly according to tumor staging. Computed tomography (CT) is the imaging modality of choice for lung cancer evaluation, being used for diagnosis and clinical staging. Besides tumor stage, other features, like histopathological subtype, can also add prognostic information. In this work, radiomics-based CT features were used to predict lung cancer histopathology and metastases using machine learning models. Methods: local image datasets of confirmed primary malignant pulmonary tumors were retrospectively evaluated for testing and validation. CT images acquired with same protocol were semiautomatically segmented. Tumors were characterized by clinical features and computer attributes of intensity, histogram, texture, shape, and volume. Three machine learning classifiers used up to 100 selected features to perform the analysis. Results: radiomics-based features yielded areas under the receiver operating characteristic curve of 0.89, 0.97, and 0.92 at testing and 0.75, 0.71, and 0.81 at validation for lymph nodal metastasis, distant metastasis, and histopathology pattern recognition, respectively. Conclusions: the radiomics characterization approach presented great potential to be used in a computational model to aid lung cancer histopathological subtype diagnosis as a "virtual biopsy" and metastatic prediction for therapy decision support without the necessity of a whole-body imaging scanning.