Imaging-based PRediction of Eligibility for ChemoImmunotherapy in reSEctable NSCLC, iPRECISE

Condition(s) studied

Investigational drug(s) / intervention(s)

High-resolution deep learning-based CT reconstruction: High-resolution deep learning-based computed tomography reconstruction will be applied after computed tomography image acquisition to generate additional reconstructed images. These images will be compared with conventional computed tomography reconstruction images to evaluate their usefulness for imaging biomarker development and assessment of extranodal extension.

Study summary

This study is for adults with resectable non-small cell lung cancer who are scheduled to receive neoadjuvant chemoimmunotherapy before surgery.

Neoadjuvant chemoimmunotherapy can help shrink lung cancer before surgery and may improve treatment outcomes. However, not all patients benefit from this treatment in the same way, and it can sometimes cause side effects, such as immune-related pneumonitis. At present, it is still difficult to predict before or during treatment which patients will have a strong response.

The purpose of this study is to find imaging features on chest computed tomography scans that may help predict how well a patient's cancer responds to neoadjuvant chemoimmunotherapy. The study will compare computed tomography findings before treatment and before surgery with pathologic findings from surgery, including pathologic complete response and major pathologic response. The study will also evaluate whether computed tomography-based imaging features are associated with treatment-related side effects and long-term outcomes such as disease progression and survival.

This is an observational study. The investigators will not assign participants to a specific cancer treatment. Participants will receive neoadjuvant chemoimmunotherapy and surgery according to standard clinical practice. Chest computed tomography scans will be obtained before treatment and before surgery as part of the study protocol. These computed tomography images will also be reconstructed using a high-resolution deep learning-based computed tomography reconstruction technique to explore whether this approach can improve the development of imaging biomarkers.

The results of this study may help develop a noninvasive imaging-based model to identify patients who are more likely to benefit from neoadjuvant chemoimmunotherapy and to better guide treatment planning for resectable non-small cell lung cancer.

Eligibility

Primary outcome measure(s)

• Predictive performance of computed tomography-based imaging biomarkers for pathologic complete response — From baseline computed tomography before neoadjuvant chemoimmunotherapy to surgical pathology assessment after surgery, up to 6 months after enrollment.
  The predictive performance of imaging biomarkers derived from contrast-enhanced chest computed tomography scans obtained before and after neoadjuvant chemoimmunotherapy will be evaluated for pathologic complete response. Pathologic complete response will be assessed using surgical pathology findings after resection. Predictive performance will be measured using model discrimination, including the area under the receiver operating characteristic curve.

Trial sites (1)

More Samsung Medical Center trials in South Korea

Other trials for the same condition