Lung texture in serial thoracic computed tomography scans: Correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development

Alexandra Cunliffe, Samuel G. Armato, Richard Castillo, Ngoc Pham, Thomas Guerrero, Hania A. Al-Hallaq

    Research output: Contribution to journalArticle

    84 Citations (Scopus)

    Abstract

    Purpose To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP). Methods and Materials A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each feature's ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction. Results For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84). Conclusions A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.

    Original languageEnglish (US)
    Pages (from-to)1048-1056
    Number of pages9
    JournalInternational Journal of Radiation Oncology Biology Physics
    Volume91
    Issue number5
    DOIs
    StatePublished - Apr 1 2015

    Fingerprint

    Radiation Pneumonitis
    lungs
    radiation therapy
    Radiotherapy
    Thorax
    textures
    tomography
    Tomography
    dosage
    Lung
    radiation
    Area Under Curve
    classifiers
    planning
    Radiation
    Research Ethics Committees
    Esophageal Neoplasms
    analysis of variance
    ROC Curve
    Analysis of Variance

    ASJC Scopus subject areas

    • Oncology
    • Radiology Nuclear Medicine and imaging
    • Radiation
    • Cancer Research

    Cite this

    Lung texture in serial thoracic computed tomography scans : Correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. / Cunliffe, Alexandra; Armato, Samuel G.; Castillo, Richard; Pham, Ngoc; Guerrero, Thomas; Al-Hallaq, Hania A.

    In: International Journal of Radiation Oncology Biology Physics, Vol. 91, No. 5, 01.04.2015, p. 1048-1056.

    Research output: Contribution to journalArticle

    Cunliffe, Alexandra ; Armato, Samuel G. ; Castillo, Richard ; Pham, Ngoc ; Guerrero, Thomas ; Al-Hallaq, Hania A. / Lung texture in serial thoracic computed tomography scans : Correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. In: International Journal of Radiation Oncology Biology Physics. 2015 ; Vol. 91, No. 5. pp. 1048-1056.
    @article{959c02b6262446f4afb4c98bfd126d43,
    title = "Lung texture in serial thoracic computed tomography scans: Correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development",
    abstract = "Purpose To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP). Methods and Materials A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each feature's ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction. Results For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84). Conclusions A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.",
    author = "Alexandra Cunliffe and Armato, {Samuel G.} and Richard Castillo and Ngoc Pham and Thomas Guerrero and Al-Hallaq, {Hania A.}",
    year = "2015",
    month = "4",
    day = "1",
    doi = "10.1016/j.ijrobp.2014.11.030",
    language = "English (US)",
    volume = "91",
    pages = "1048--1056",
    journal = "International Journal of Radiation Oncology Biology Physics",
    issn = "0360-3016",
    publisher = "Elsevier Inc.",
    number = "5",

    }

    TY - JOUR

    T1 - Lung texture in serial thoracic computed tomography scans

    T2 - Correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development

    AU - Cunliffe, Alexandra

    AU - Armato, Samuel G.

    AU - Castillo, Richard

    AU - Pham, Ngoc

    AU - Guerrero, Thomas

    AU - Al-Hallaq, Hania A.

    PY - 2015/4/1

    Y1 - 2015/4/1

    N2 - Purpose To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP). Methods and Materials A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each feature's ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction. Results For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84). Conclusions A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.

    AB - Purpose To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP). Methods and Materials A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each feature's ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction. Results For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84). Conclusions A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.

    UR - http://www.scopus.com/inward/record.url?scp=84925348152&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84925348152&partnerID=8YFLogxK

    U2 - 10.1016/j.ijrobp.2014.11.030

    DO - 10.1016/j.ijrobp.2014.11.030

    M3 - Article

    C2 - 25670540

    AN - SCOPUS:84925348152

    VL - 91

    SP - 1048

    EP - 1056

    JO - International Journal of Radiation Oncology Biology Physics

    JF - International Journal of Radiation Oncology Biology Physics

    SN - 0360-3016

    IS - 5

    ER -