11
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          The Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule (SPN) remains unclear. 240 patients with SPNs (malignant, n = 180; benign, n = 60) underwent non-contrast CT (NECT) and contrast-enhanced CT (CECT) which were reconstructed with different slice thickness and convolution kernel. 150 radiomics features were extracted separately from each set of CT and diagnostic performance of each feature were assessed. After feature selection and radiomics signature construction, diagnostic performance of radiomics signature for discriminating benign and malignant SPN was also assessed with respect to the discrimination and classification and compared with net reclassification improvement (NRI). Our results showed NECT-based radiomics signature demonstrated better discrimination and classification capability than CECT in both primary (AUC: 0.862 vs. 0.829, p = 0.032; NRI = 0.578) and validation cohort (AUC: 0.750 vs. 0.735, p = 0.014; NRI = 0.023). Thin-slice (1.25 mm) CT-based radiomics signature had better diagnostic performance than thick-slice CT (5 mm) in both primary (AUC: 0.862 vs. 0.785, p = 0.015; NRI = 0.867) and validation cohort (AUC: 0.750 vs. 0.725, p = 0.025; NRI = 0.467). Standard convolution kernel-based radiomics signature had better diagnostic performance than lung convolution kernel-based CT in both primary (AUC: 0.785 vs. 0.770, p = 0.015; NRI = 0.156) and validation cohort (AUC: 0.725 vs.0.686, p = 0.039; NRI = 0.467). Therefore, this study indicates that the contrast-enhancement, reconstruction slice thickness and convolution kernel can affect the diagnostic performance of radiomics signature in SPN, of which non-contrast, thin-slice and standard convolution kernel-based CT is more informative.

          Related collections

          Most cited references 18

          • Record: found
          • Abstract: found
          • Article: not found

          Measuring Computed Tomography Scanner Variability of Radiomics Features.

          The purpose of this study was to determine the significance of interscanner variability in CT image radiomics studies.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Net reclassification improvement: computation, interpretation, and controversies: a literature review and clinician's guide.

            The net reclassification improvement (NRI) is an increasingly popular measure for evaluating improvements in risk predictions. This article details a review of 67 publications in high-impact general clinical journals that considered the NRI. Incomplete reporting of NRI methods, incorrect calculation, and common misinterpretations were found. To aid improved applications of the NRI, the article elaborates on several aspects of the computation and interpretation in various settings. Limitations and controversies are discussed, including the effect of miscalibration of prediction models, the use of the continuous NRI and “clinical NRI,” and the relation with decision analytic measures. A systematic approach toward presenting NRI analysis is proposed: Detail and motivate the methods used for computation of the NRI, use clinically meaningful risk cutoffs for the category-based NRI, report both NRI components, address issues of calibration, and do not interpret the overall NRI as a percentage of the study population reclassified. Promising NRI findings need to be followed with decision analytic or formal cost-effectiveness evaluations.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Accuracy of PET/CT in characterization of solitary pulmonary lesions.

              Characterization of a pulmonary lesion is a well-established indication for metabolic imaging with 18F-FDG. There is extensive literature on the use of PET and CT in the characterization of a solitary pulmonary nodule (SPN). The performance of dual-modality imaging with PET/CT for characterizing SPNs was investigated in a clinical referral setting. We performed a retrospective study involving patients referred for SPN characterization with PET/CT between September 2002 and June 2004, for whom a pathologic diagnosis was available. The group consisted of 12 men and 30 women whose age ranged from 35 to 84 y (mean age +/- SD, 67 +/- 11 y). A dual-slice CT/lutetium oxyorthosilicate PET system was used for imaging. CT images were acquired without intravenous contrast. Blinded interpretation was performed by 1 chest radiologist for CT and 2 nuclear medicine physicians for PET. PET/CT images were read in consensus. Lesions were analyzed by location, texture, axial dimension, and metabolic activity and visually scored on a 5-point scale from benign to malignant; the maximum standardized uptake value (SUVmax) was measured. Lesion diameter varied from 7 to 30 mm (mean +/- SD, 15 +/- 6 mm). The SUVmax ranged from 0.5 to 17.2 (mean +/- SD, 3.0 +/- 3.0). SUVmax corrected for lean body mass was 0.4-12.1 (mean +/- SD, 2.1 +/- 2.0). Comparison of CT versus PET versus PET/CT yielded accuracies of 74%, 74%, and 93%, respectively. PET and CT correctly characterized 31 and PET/CT correctly characterized 39 of the 42 lesions as malignant or benign. The sensitivity and specificity for CT, PET, and PET/CT was 93%/31%, 69%/85%, and 97%/85%, respectively. There were significant differences (P < 0.05) between PET/CT and PET for accuracy, sensitivity, and specificity. Accuracy did not improve by quantitative analysis using an SUVmax cutoff of 2.0 for malignancy. Lean body mass correction of the SUVmax did not change accuracy. PET/CT demonstrates an excellent performance in classifying SPNs as benign or malignant. The combination of anatomic and metabolic imaging is synergistic by maintaining the sensitivity of CT and the specificity of PET, resulting in an overall significantly improved accuracy. Visual interpretation is sufficient for characterizing an SPN. Quantitative analysis does not improve accuracy of PET/CT for SPN characterization.
                Bookmark

                Author and article information

                Journal
                Sci Rep
                Sci Rep
                Scientific Reports
                Nature Publishing Group
                2045-2322
                10 October 2016
                2016
                : 6
                Affiliations
                [1 ]Department of Radiology, Guangdong General Hospital, Guangdong Academy of Medical Sciences , Guangzhou, Guangdong, 510080, China
                [2 ]School of Medicine, South China University of Technology, Guangzhou , Guangdong, 510006, China
                Author notes
                [*]

                These authors contributed equally to this work.

                Article
                srep34921
                10.1038/srep34921
                5056507
                27721474
                Copyright © 2016, The Author(s)

                This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

                Categories
                Article

                Uncategorized

                Comments

                Comment on this article