Robust imaging habitat computation using voxel-wise radiomics features

Autor: Raquel Perez-Lopez, Eric Delgado, Marta Ligero, Francesco Grussu, Alonso Garcia, K. Bernatowicz
Přispěvatelé: Institut Català de la Salut, [Bernatowicz K, Grussu F, Ligero M, Garcia A, Delgado E] Radiomics Group, Vall d’Hebron Institute of Oncology (VHIO), Barcelona, Spain. [Perez-Lopez R] Radiomics Group, Vall d’Hebron Institute of Oncology (VHIO), Barcelona, Spain. Servei de Radiologia, Vall d’Hebron Hospital Universitari, Barcelona, Spain, Vall d'Hebron Barcelona Hospital Campus
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Image Interpretation
Computer-Assisted::Tomography
X-Ray Computed [ANALYTICAL
DIAGNOSTIC AND THERAPEUTIC TECHNIQUES
AND EQUIPMENT]
Neoplasms::Neoplasms by Site::Thoracic Neoplasms::Respiratory Tract Neoplasms::Lung Neoplasms [DISEASES]
Lung Neoplasms
Computer science
Science
Feature extraction
Tomografia computada per emissió de fotó simple
computer.software_genre
Tumor heterogeneity
Joint entropy
Article
neoplasias::neoplasias por localización::neoplasias torácicas::neoplasias del tracto respiratorio::neoplasias pulmonares [ENFERMEDADES]
Radiomics
Voxel
Investigative Techniques::Epidemiologic Methods::Epidemiologic Research Design::Reproducibility of Results [ANALYTICAL
DIAGNOSTIC AND THERAPEUTIC TECHNIQUES
AND EQUIPMENT]
Image Processing
Computer-Assisted
Medical imaging
Humans
Entropy (energy dispersal)
Treatment resistance
Other subheadings::Other subheadings::/diagnostic imaging [Other subheadings]
Pulmons - Càncer - Imatgeria
Multidisciplinary
Diagnostic Tests
Routine
business.industry
diagnóstico::técnicas y procedimientos diagnósticos::diagnóstico por imagen::interpretación de imágenes asistida por ordenador::tomografía computarizada por rayos X [TÉCNICAS Y EQUIPOS ANALÍTICOS
DIAGNÓSTICOS Y TERAPÉUTICOS]
Reproducibility of Results
Otros calificadores::Otros calificadores::/diagnóstico por imagen [Otros calificadores]
Pattern recognition
técnicas de investigación::métodos epidemiológicos::diseño de la investigación epidemiológica::reproducibilidad de los resultados [TÉCNICAS Y EQUIPOS ANALÍTICOS
DIAGNÓSTICOS Y TERAPÉUTICOS]
Avaluació de resultats (Assistència sanitària)
Medicine
Cancer imaging
Artificial intelligence
Tomography
X-Ray Computed
business
Biomedical engineering
computer
Zdroj: Scientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
Scientia
Scientific Reports
ISSN: 2045-2322
Popis: Enginyeria Biomèdica; Imatge del càncer Biomedical engineering; Cancer imaging Ingeniería Biomédica; Imágenes del cáncer Tumor heterogeneity has been postulated as a hallmark of treatment resistance and a cure constraint in cancer patients. Conventional quantitative medical imaging (radiomics) can be extended to computing voxel-wise features and aggregating tumor subregions with similar radiological phenotypes (imaging habitats) to elucidate the distribution of tumor heterogeneity within and among tumors. Despite the promising applications of imaging habitats, they may be affected by variability of radiomics features, preventing comparison and generalization of imaging habitats techniques. We performed a comprehensive repeatability and reproducibility analysis of voxel-wise radiomics features in more than 500 lung cancer patients with computed tomography (CT) images and demonstrated the effect of voxel-wise radiomics variability on imaging habitats computation in 30 lung cancer patients with test–retest images. Repeatable voxel-wise features characterized texture heterogeneity and were reproducible regardless of the applied feature extraction parameters. Imaging habitats computed using robust radiomics features were more stable than those computed using all features in test–retest CTs from the same patient. Nine voxel-wise radiomics features (joint energy, joint entropy, sum entropy, maximum probability, difference entropy, Imc1, Imc2, Idn and Idmn) were repeatable and reproducible. This supports their application for computing imaging habitats in lung tumors towards the discovery of previously unseen tumor heterogeneity and the development of novel non-invasive imaging biomarkers for precision medicine. This study was supported by the Banco Bilbao Vizcaya Argentaria and Fundacio La Caixa. R.P.L. is supported by the CRIS Foundation Talent Award (TALENT19-05), the Instituto de Salud Carlos III-Investigación en Salud (PI18/01395) and the Prostate Cancer Foundation Young Investigator Award. K.B. is supported by MSCA COFUND Beatriu de Pinós Grant (2019BP/00182). ML is supported by a PERIS Grant-PIS Program. We thank Sarah MacKenzie, PhD for editorial assistance.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje