EUVIMEDEUVIMED entdecken
Open Access

Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer

Olivia Prior iD, Carlos Macarro iD, Víctor Navarro iD, Camilo Monreal iD, Marta Ligero iD, Alonso Garcia-Ruiz iD, Garazi Serna, Sara Simonetti, Irene Braña, Maria Vieito, Manuel Escobar iD, Jaume Capdevila und 8 weitere

Radiology: Artificial Intelligence · 01.03.2024 · 6 (2)

DOI: 10.1148/ryai.230118 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology: Artificial Intelligence, erschienen am 01.03.2024. Verfasst von Olivia Prior und 19 weiteren Autor:innen. Beteiligte Einrichtung: From the Radiomics Group, Vall d'Hebron Institute of Oncology, Carrer de Natzaret 115-117, Barcelona 08035, Spain (O.P., C. Macarro, C. Monreal, M.L.…. Hauptthemen laut MEDLINE: Lung Neoplasms, Liver Neoplasms. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: “la Caixa” Foundation, CRIS Foundation, FERO Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies.

Results

Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology.

Conclusion

Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsLiver NeoplasmsHumansMaleMiddle AgedRetrospective StudiesReproducibility of ResultsRadiomicsTomography, X-Ray ComputedMachine Learning

Stichwörter der Autor:innen

CTDiffusion-weighted ImagingDynamic Contrast-enhanced MRILiverLungMRIOncologyRadiomicsUnsupervised Learning

Autor:innen und Institutionen

  • From the Radiomics Group, Vall d'Hebron Institute of Oncology, Carrer de Natzaret 115-117, Barcelona 08035, Spain (O.P., C. Macarro, C. Monreal, M.L., A.G.R., F.G., K.B., R.P.L.); Oncology Data Science Group, Vall d'Heb…

ORCID-Profile: Olivia Prior, Carlos Macarro, Víctor Navarro, Camilo Monreal, Marta Ligero, Alonso Garcia-Ruiz, Manuel Escobar, Rodrigo Dienstmann, Rodrigo Toledo, Paolo Nuciforo, Elena Garralda, Francesco Grussu, Kinga Bernatowicz, Raquel Perez-Lopez

Förderung

  • “la Caixa” Foundation
  • CRIS Foundation
  • FERO Foundation
  • Instituto de Salud Carlos III-Investigación en Salud
  • EU Horizon 2020
  • AstraZeneca

Zitieren

APA

Prior, O., Macarro, C., Navarro, V., Monreal, C., Ligero, M., Garcia-Ruiz, A., Serna, G., Simonetti, S., Braña, I., Vieito, M., Escobar, M., Capdevila, J., Byrne, A. T., Dienstmann, R., Toledo, R., Nuciforo, P., Garralda, E., Grussu, F., Bernatowicz, K., & Perez-Lopez, R. (2024). Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer. Radiology: Artificial Intelligence, 6(2). https://doi.org/10.1148/ryai.230118

Vancouver

Prior O, Macarro C, Navarro V, Monreal C, Ligero M, Garcia-Ruiz A, et al. Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer. Radiology: Artificial Intelligence. 2024;6(2). doi:10.1148/ryai.230118

BibTeX
@article{Prior2024,
  author = {Prior, Olivia and Macarro, Carlos and Navarro, Víctor and Monreal, Camilo and Ligero, Marta and Garcia-Ruiz, Alonso and Serna, Garazi and Simonetti, Sara and Braña, Irene and Vieito, Maria and Escobar, Manuel and Capdevila, Jaume and Byrne, Annette T and Dienstmann, Rodrigo and Toledo, Rodrigo and Nuciforo, Paolo and Garralda, Elena and Grussu, Francesco and Bernatowicz, Kinga and Perez-Lopez, Raquel},
  title = {Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer},
  journal = {Radiology: Artificial Intelligence},
  year = {2024},
  volume = {6},
  number = {2},
  doi = {10.1148/ryai.230118}
}
Kostenlos starten →