Virtual Library

Start Your Search

Stefano Tomatis



Author of

  • +

    P2.17 - Treatment of Early Stage/Localized Disease (ID 189)

    • Event: WCLC 2019
    • Type: Poster Viewing in the Exhibit Hall
    • Track: Treatment of Early Stage/Localized Disease
    • Presentations: 1
    • Now Available
    • Moderators:
    • Coordinates: 9/09/2019, 10:15 - 18:15, Exhibit Hall
    • +

      P2.17-20 - A Radiomic Approach to Predict Nodal and Distant Relapse in Patients Treated with Stereotactic Body Radiation Therapy for Early Stage NSCLC (Now Available) (ID 2178)

      10:15 - 18:15  |  Author(s): Stefano Tomatis

      • Abstract
      • Slides

      Background

      Regional and distant relapse remain a significant issue in the treatment of early stage non small cell lung cancer with Stereotactic Body Radiation Therapy (SBRT). There is a need for predictive biomarkers able to identify patients that are at higher risk of relapse. In this work we present a radiomic approach using features extracted by routine planning CT, to predict the risk of nodal and distant recurrence.

      Method

      A cohort of 102 patients was retrospectively investigated. All patients were affected by early stage (T1-T2) lung cancer and received the same radiation treatment with 48Gy delivered in 4 fractions. For all patients, a set of 45 radiomics textural features was computed for the tumor volumes segmented on the treatment planning CT images. Patients were split into two independent cohorts used for training (70% of cases) and validation (30% of cases). A stepwise backward linear discriminant analysis (LDA) was applied as a classifier to identify patients at risk of lymph-nodal progression. The performance of the model was assessed by means of standard metrics derived from the confusion matrix. Furthermore, all textural features were correlated to survival data to build predictive models: the features/predictors found significant at univariate analysis and to elastic net regularization, were included in a multivariate model to predict disease specific progression free survival (PFS) and disease specific survival (DS OS). Low and high risk groups were identified by maximizing the separation by means of the Youden method.

      Result

      In the total cohort (77 (75.5%) males and 25 (24.5%) females, median age 76.6 years), 15 patients presented nodal progression at the time of analysis (11 in the training and 4 in the validation sets); 19 patients (18.6%) died because of disease specific causes, 25 (24.5%) died for other reasons, 28 (27.5%) were alive without disease and 30 (29.4%) with either local or distant progression. The mean tumor volume was 5.6±6.4cm3. Figure 1 illustrates the actuarial curves for PFS and DS OS over the entire training and test cohorts (in both cases the difference was not significant) and the same data stratified in low and high risk groups identified. In all case highly significant differences were identified.

      curves.jpg

      Conclusion

      Radiomics features extracted from treatment planning CT images can distinguish patients with low and high risk of tumor progression and disease specific death in early stage lung cancer treated with SBRT.

      Only Active Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login or select "Add to Cart" and proceed to checkout.