Virtual Library

Start Your Search

Si Sun



Author of

  • +

    JCSE01 - Joint IASLC-CSCO-CAALC Session (ID 63)

    • Event: WCLC 2019
    • Type: Joint IASLC-CSCO-CAALC Session
    • Track:
    • Presentations: 1
    • +

      JCSE01.18 - A CT-Based Radiomics Approach to Predict PD1 Inhibitor Response in Non-Small-Cell Lung Cancer (ID 3432)

      07:00 - 11:15  |  Author(s): Si Sun

      • Abstract
      • Slides

      Abstract
      Background
      The purpose of this study was to investigate the use of radiomics features as predictive parameters of clinical outcomes of non-small-cell lung cancer (NSCLC) patients treated with PD1 inhibitor.

      Methods
      Forty-three stage IIIB/IV NSCLC patients without EGFR mutation or ALK rearrangement who received nivolumab were enrolled between Apr 2016 and Jan 2019. High-dimensional quantitative feature analysis via Pyradiomics was applied to extract 852 radiomics features of pre-anti-PD1 treatment CT. A radiomic score model was constructed from these features with the use of least absolute shrinkage and selection operator (LASSO) Cox regression. The radiomic score for each patient was computed using an equation in which the coefficients were derived from the LASSO Cox model to subgroup patients by progression-free survival (PFS). The median value of radiomic score was used as the cut-off value to cluster patients into high or low score groups.

      Results
      We developed a radiomic signature for PFS that included seven variables. The median value of radiomic score was 0.23. The objective response rate (ORR) was 16.3% (7/43), the median PFS was 2 months and median overall survival (OS) was 3.2 months of all 43 patients. A low radiomic score was associated with a higher ORR (33.7% vs 0%, p= 0.0036), improved PFS (median: 3 months vs 2 months; HR 0.14, 95% CI   0.053-0.39, P < 0.0001) and longer OS (median: 11.2 months vs 7.0 months; HR 0.12, 95%CI 0.04-0.31, p < 0.0001). Multivariate analysis also showed that a low radiomic score was related to better PFS (HR 0.12, 95% CI   0.041-0.32, P < 0.0001) and OS (HR 0.11, 95%CI 0.03-0.28, p < 0.0001).



      Conclusion
      The radiomic signature as an imaging predictor provided a promising way to predict clinical outcomes for NSCLC patients treated with PD-1 inhibitor.

      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.

  • +

    P1.01 - Advanced NSCLC (ID 158)

    • Event: WCLC 2019
    • Type: Poster Viewing in the Exhibit Hall
    • Track: Advanced NSCLC
    • Presentations: 1
    • Now Available
    • Moderators:
    • Coordinates: 9/08/2019, 09:45 - 18:00, Exhibit Hall
    • +

      P1.01-66 - A CT-Based Radiomics Approach to Predict PD1 Inhibitor Response in Non-Small-Cell Lung Cancer (Now Available) (ID 565)

      09:45 - 18:00  |  Author(s): Si Sun

      • Abstract
      • Slides

      Background

      The purpose of this study was to investigate the use of radiomics features as predictive parameters of clinical outcomes of non-small-cell lung cancer (NSCLC) patients treated with PD1 inhibitor.

      Method

      Forty-three stage IIIB/IV NSCLC patients without EGFR mutation or ALK rearrangement who received nivolumab were enrolled between Apr 2016 and Jan 2019. High-dimensional quantitative feature analysis via Pyradiomics was applied to extract 852 radiomics features of pre-anti-PD1 treatment CT. A radiomic score model was constructed from these features with the use of least absolute shrinkage and selection operator (LASSO) Cox regression. The radiomic score for each patient was computed using an equation in which the coefficients were derived from the LASSO Cox model to subgroup patients by progression-free survival (PFS). The median value of radiomic score was used as the cut-off value to cluster patients into high or low score groups.

      Result

      We developed a radiomic signature for PFS that included seven variables. The median value of radiomic score was 0.23. The objective response rate (ORR) was 16.3% (7/43), the median PFS was 2 months and median overall survival (OS) was 3.2 months of all 43 patients. A low radiomic score was associated with a higher ORR (33.7% vs 0%, p= 0.0036), improved PFS (median: 3 months vs 2 months; HR 0.14, 95% CI   0.053-0.39, P < 0.0001) and longer OS (median: 11.2 months vs 7.0 months; HR 0.12, 95%CI 0.04-0.31, p < 0.0001). Multivariate analysis also showed that a low radiomic score was related to better PFS (HR 0.12, 95% CI   0.041-0.32, P < 0.0001) and OS (HR 0.11, 95%CI 0.03-0.28, p < 0.0001).

      8.pic_hd.jpg

      Conclusion

      The radiomic signature as an imaging predictor provided a promising way to predict clinical outcomes for NSCLC patients treated with PD-1 inhibitor.

      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.