Virtual Library

Start Your Search

German Corredor-Prada



Author of

  • +

    P1.13 - Targeted Therapy (Not CME Accredited Session) (ID 945)

    • Event: WCLC 2018
    • Type: Poster Viewing in the Exhibit Hall
    • Track:
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/24/2018, 16:45 - 18:00, Exhibit Hall
    • +

      P1.13-34 - Changes in Radiomic Features Between Baseline and Two Weeks Post-Nivolumab Treatment Are Predictive of Pathologic Complete Response (ID 14271)

      16:45 - 18:00  |  Author(s): German Corredor-Prada

      • Abstract
      • Slides

      Background

      Programmed cell death immune checkpoint inhibitors have been approved by the FDA to treat stage III unresectable NSCLC or Stage IV metastatic lung adenocarcinoma. However, the response rate to such therapy is limited to 19%. Currently, there are no clinical biomarkers to identify patients who are likely to derive benefit from Nivolumab. Our aim was to explore whether changes in intratumoral and peritumoral radiomic texture features between baseline and 2-week post-treatment CT scans could predict immunotherapy response.

      a9ded1e5ce5d75814730bb4caaf49419 Method

      Surgical biopsy specimens (pre-treatment) and CT scans from 73 NSCLC patients with pre- and 2-week post-Nivolumab treatment were acquired. Patients with an objective response (complete/partial) per RECIST after two cycles of Nivolumab were defined as “responders” and patients with progressive disease were defined as “non-responders”. 454 intra-tumoral texture, 24 shape features and 7426 features from annular rings (15 annular rings each, 2mm each) outside the expert-annotated nodules were extracted from the baseline and post-treatment scans. Besides, 76 features quantifying compactness of tumor infiltrating lymphocytes (TILs) were extracted from the surgical specimens. A linear discriminant analysis(LDA) classifier was trained using the most predictive features identified on the discovery set(n=29) and validated on the test set(n=44). To investigate the radio-pathomic associations, a pair­wise Spearman correlation was performed between each radiomic and TIL feature.

      4c3880bb027f159e801041b1021e88e8 Result

      A combination of 6 intra-tumoral, 3 peri-tumoral and 1 shape delta radiomic feature yielded an AUC of 0.93 ± 0.085 within the discovery set and a corresponding AUC = 0.91 within the validation set. Lymphocyte density was found to be negatively(r=-0.5) correlated with a peritumoral Gabor feature from the first annular ring.

      8eea62084ca7e541d918e823422bd82e Conclusion

      Change in texture features extracted from baseline and post-Nivolumab treated CT scans were predictive of pathological response. Association of these texture features with TIL compactness may provide a deeper understanding of immune response and corresponding imaging phenotypes.

      untitled.png

      6f8b794f3246b0c1e1780bb4d4d5dc53

      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.