Advertisement

Perinodular Parenchymal Features Improve Indeterminate Lung Nodule Classification

Published:August 03, 2022DOI:https://doi.org/10.1016/j.acra.2022.07.001

      Background

      : Radiomics, defined as quantitative features extracted from images, provide a non-invasive means of assessing malignant versus benign pulmonary nodules. In this study, we evaluate the consistency with which perinodular radiomics extracted from low-dose computed tomography images serve to identify malignant pulmonary nodules.

      Materials and Methods

      : Using the National Lung Screening Trial (NLST), we selected individuals with pulmonary nodules between 4mm to 20mm in diameter. Nodules were segmented to generate four distinct datasets; 1) a Tumor dataset containing tumor-specific features, 2) a 10 mm Band dataset containing parenchymal features between the segmented nodule boundary and 10mm out from the boundary, 3) a 15mm Band dataset, and 4) a Tumor Size dataset containing the maximum nodule diameter. Models to predict malignancy were constructed using support-vector machine (SVM), random forest (RF), and least absolute shrinkage and selection operator (LASSO) approaches. Ten-fold cross validation with 10 repetitions per fold was used to evaluate the performance of each approach applied to each dataset.

      Results

      : With respect to the RF, the Tumor, 10mm Band, and 15mm Band datasets achieved areas under the receiver-operator curve (AUC) of 84.44%, 84.09%, and 81.57%, respectively. Significant differences in performance were observed between the Tumor and 15mm Band datasets (adj. p-value <0.001). However, when combining tumor-specific features with perinodular features, the 10mm Band + Tumor and 15mm Band + Tumor datasets (AUC 87.87% and 86.75%, respectively) performed significantly better than the Tumor Size dataset (66.76%) or the Tumor dataset. Similarly, the AUCs from the SVM and LASSO were 84.71% and 88.91%, respectively, for the 10mm Band + Tumor.

      Conclusions

      : The combined 10mm Band + Tumor dataset improved the differentiation between benign and malignant lung nodules compared to the Tumor datasets across all methodologies. This demonstrates that parenchymal features capture novel diagnostic information beyond that present in the nodule itself. (data agreement: NLST-163)

      Key Words

      Abbreviation:

      : SVM (Support Vector Machine), LASSO (Least Absolute Shrinkage Selection Operator), RF (Random Forest), LDCT (Low-Dose Computed Tomography)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Marshall HM
        • Bowman RV
        • Yang IA
        • Fong KM
        • Berg CD.
        Screening for lung cancer with low-dose computed tomography: a review of current status.
        J Thorac Dis. AME Publishing Company;. 2013; 5https://doi.org/10.3978/j.issn.2072-1439.2013.09.06
      1. The National Lung Screening Trial Research Team. Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening.
        N Engl J Med. 2011; 365: 395-409https://doi.org/10.1056/NEJMoa1102873
        • Pinsky PF
        • Bellinger CR
        • Miller DP.
        False-positive screens and lung cancer risk in the National Lung Screening Trial: Implications for shared decision-making.
        J Med Screen. 2018; 25: 110-112https://doi.org/10.1177/0969141317727771
        • Raghu VK
        • Zhao W
        • Pu J
        • et al.
        Feasibility of lung cancer prediction from low-dose CT scan and smoking factors using causal models.
        Thorax. 2019; 74: 643-649https://doi.org/10.1136/thoraxjnl-2018-212638
        • Patz EF
        • Pinsky P
        • Gatsonis C
        • et al.
        Overdiagnosis in Low-Dose Computed Tomography Screening for Lung Cancer.
        JAMA Intern Med. 2014; 174: 269-274https://doi.org/10.1001/jamainternmed.2013.12738
        • Pinsky PF.
        Assessing the benefits and harms of low-dose computed tomography screening for lung cancer.
        Lung Cancer Manag. 2014; 3: 491-498https://doi.org/10.2217/LMT.14.41
        • Preventive Services Task Force US
        • Krist AH
        • Davidson KW
        • et al.
        Screening for Lung Cancer: US Preventive Services Task Force Recommendation Statement.
        JAMA. 2021; 325: 962https://doi.org/10.1001/jama.2021.1117
        • Pinsky PF
        • Gierada DS
        • Black W
        • et al.
        Performance of Lung-RADS in the National Lung Screening Trial.
        Ann Intern Med. 2015; 162: 485-491https://doi.org/10.7326/M14-2086
        • Kalpathy-Cramer J
        • Mamomov A
        • Zhao B
        • et al.
        Radiomics of Lung Nodules: A Multi-Institutional Study of Robustness and Agreement of Quantitative Imaging Features.
        Tomography. 2016; 2: 430-437https://doi.org/10.18383/j.tom.2016.00235
        • Hammer MM
        • Byrne SC
        • Kong CY.
        Factors Influencing the False Positive Rate in CT Lung Cancer Screening.
        Acad Radiol. 2022; 29: S18-S22https://doi.org/10.1016/j.acra.2020.07.040
        • de Torres JP
        • Bastarrika G
        • Wisnivesky JP
        • et al.
        Assessing the Relationship Between Lung Cancer Risk and Emphysema Detected on Low-Dose CT of the Chest.
        Chest. 2007; 132: 1932-1938https://doi.org/10.1378/chest.07-1490
        • Smith BM
        • Schwartzman K
        • Kovacina B
        • et al.
        Lung cancer histologies associated with emphysema on computed tomography.
        Lung Cancer. 76. Elsevier, 2012: 61-66https://doi.org/10.1016/j.lungcan.2011.09.003
        • Kinsey CM
        • San José Estépar R
        • Wei Y
        • Washko GR
        • Christiani DC
        Regional Emphysema of a Non-Small Cell Tumor Is Associated with Larger Tumors and Decreased Survival.
        Ann Am Thorac Soc. 2015; 150603140911000https://doi.org/10.1513/AnnalsATS.201411-539OC
        • Moon SW
        • Park MS
        • Kim YS
        • et al.
        Combined pulmonary fibrosis and emphysema and idiopathic pulmonary fibrosis in non-small cell lung cancer: impact on survival and acute exacerbation.
        BMC Pulm Med. 2019; 19: 177https://doi.org/10.1186/s12890-019-0951-2
        • Gillies RJ
        • Kinahan PE
        • Hricak H.
        Radiomics: Images Are More than Pictures, They Are Data.
        Radiology. Radiological Society of North America;. 2015; 278: 563-577https://doi.org/10.1148/radiol.2015151169
        • Dilger SKN
        • Uthoff J
        • Judisch A
        • et al.
        Improved pulmonary nodule classification utilizing quantitative lung parenchyma features.
        J Med Imaging Bellingham Wash. 2015; 2041004https://doi.org/10.1117/1.JMI.2.4.041004
        • Uthoff J
        • Stephens MJ
        • Newell JD
        • et al.
        Machine learning approach for distinguishing malignant and benign lung nodules utilizing standardized perinodular parenchymal features from CT.
        Med Phys. 2019; 46: 3207-3216https://doi.org/10.1002/mp.13592
        • Wu S
        • Zhang N
        • Wu Z
        • Ren J
        • E L
        Can Peritumoral Radiomics Improve the Prediction of Malignancy of Solid Pulmonary Nodule Smaller Than 2 cm?.
        Acad Radiol. 2022; 29: S47-S52https://doi.org/10.1016/j.acra.2020.10.029
        • Gupta S
        • Jacobson FL
        • Kong CY
        • Hammer MM.
        Performance of Lung Nodule Management Algorithms for Lung-RADS Category 4 Lesions.
        Acad Radiol. 2021; 28: 1037-1042https://doi.org/10.1016/j.acra.2020.04.041
        • San Jose Estepar R
        • Ross JC
        • Harmouche R
        • Onieva J
        • Diaz AA
        • Washko GR.
        Chest Imaging Platform: An Open-Source Library and Workstation for Quantitative Chest Imaging. C66 LUNG IMAGING II NEW PROBES Emerg Technol.
        American Thoracic Society. 2015; (A4975–A4975)https://doi.org/10.1164/ajrccm-conference.2015.191.1_MeetingAbstracts.A4975
        • Yip SSF
        • Parmar C
        • Blezek D
        • et al.
        Application of the 3D slicer chest imaging platform segmentation algorithm for large lung nodule delineation.
        PLOS ONE. 2017; 12e0178944https://doi.org/10.1371/journal.pone.0178944
        • Pedregosa F
        • Varoquaux G
        • Gramfort A
        • et al.
        Scikit-learn: Machine Learning in Python.
        Scikit-Learn Mach Learn Python. 2011; 12: 2825-2830
        • Li Q
        • Balagurunathan Y
        • Liu Y
        • et al.
        Comparison between semantic features and lung-RADS in predicting malignancy of screening lung nodule.
        Clin Lung Cancer. 2018; 19 (e3): 148-156https://doi.org/10.1016/j.cllc.2017.10.002
        • King PT.
        Inflammation in chronic obstructive pulmonary disease and its role in cardiovascular disease and lung cancer.
        Clin Transl Med. 2015; 4https://doi.org/10.1186/s40169-015-0068-z
        • Parris BA
        • O'Farrell HE
        • Fong KM
        • Yang IA
        Chronic obstructive pulmonary disease (COPD) and lung cancer: common pathways for pathogenesis.
        J Thorac Dis. 2019; 11: S2155-S2172https://doi.org/10.21037/jtd.2019.10.54
        • Yoo H
        • Jeong B-H
        • Chung MJ
        • Lee KS
        • Kwon OJ
        • Chung MP.
        Risk factors and clinical characteristics of lung cancer in idiopathic pulmonary fibrosis: a retrospective cohort study.
        BMC Pulm Med. 2019; 19: 149https://doi.org/10.1186/s12890-019-0905-8
        • Webb WR.
        Thin-section CT of the secondary pulmonary lobule: anatomy and the image–the 2004 Fleischner lecture.
        Radiology. 2006; 239: 322-338https://doi.org/10.1148/radiol.2392041968
        • Nishino M
        • Itoh H
        • Hatabu H.
        A Practical Approach to High-Resolution CT of Diffuse Lung Disease.
        Eur J Radiol. 2014; 83: 6-19https://doi.org/10.1016/j.ejrad.2012.12.028
        • Chen B
        • Yang L
        • Zhang R
        • Luo W
        • Li W.
        Radiomics: an overview in lung cancer management—a narrative review.
        Ann Transl Med. 2020; 8: 1191https://doi.org/10.21037/atm-20-4589