2023 World Conference on Lung Cancer (Posters)-EP08.02. Lymphovascular Invasion Prediction with CT images in Patients with Non-Small Cell Lung Cancer (NSCLC)

EP08.02. Lymphovascular Invasion Prediction with CT images in Patients with Non-Small Cell Lung Cancer (NSCLC) - PDF(Slides)

Back to course

Pdf Summary

Lymphovascular invasion (LVI) is an important prognostic factor in patients with Non-Small Cell Lung Cancer (NSCLC). However, obtaining LVI information usually requires invasive procedures or is not available for some patients. This study aimed to predict LVI using pre-treatment Computed Tomography (CT) images in NSCLC patients. <br /><br />The researchers used CT scans, semantic annotations of the tumors, and surgically proven LVI information from the Cancer Imaging Archive (TCIA). A total of 64 NSCLC patients were randomly divided into training and validation cohorts. Radiomic features were extracted from the CT images using the PyRadiomics Python module. Univariate analysis was performed to select informative features, and a random forest tree model was built using the statistically significant features. <br /><br />The study found that out of 130 radiomics features, 30 showed statistically significant differences between the LVI absent and LVI present groups. A prediction model using these features achieved an area under the receiver operating characteristic curve (AUC) of 0.69 in the validation cohort. <br /><br />The study concluded that noninvasive CT image biomarkers can successfully predict LVI in NSCLC patients. This prediction model has the potential to provide valuable clinical insights and help in selecting individualized treatment options for NSCLC patients.

Asset Subtitle

Misuk Lee

Meta Tag

Speaker Misuk Lee

Topic Local-Regional NSCLC: Multimodality Therapy

Keywords

Lymphovascular invasion

Non-Small Cell Lung Cancer

Prognostic factor

Computed Tomography

CT images

Cancer Imaging Archive

Radiomic features

Random forest tree model

Receiver operating characteristic curve

Individualized treatment options