Optical imaging of treatment-naïve human NSCLC reveals changes associated with metastatic recurrence

Lung cancer remains the leading cause of cancer deaths, comprising nearly 25% of all cancer deaths [1]. The five-year survival rate of patients with non-small cell lung carcinoma (NSCLC) remains significantly low given that over half present with locally advanced or metastatic disease at time of diagnosis, and experience tumor recurrence following therapeutic intervention [2,3]. Current evaluation techniques to assess treatment response are lacking, given they are implemented several weeks after treatment completion and are solely based on anatomical changes in tumor size, forgoing other criteria such as functional or metabolic changes. There is a critical need to identify surrogate markers early on following diagnosis, that aid in distinguishing patients based on their long-term outcome. Two photon microscopy (TPM) techniques provide non-invasive high-resolution information on cell metabolism within tissue by utilizing an optical redox ratio (ORR) of FAD/[NADH+FAD] autofluorescence. The goal of this study is to use the ORR and NADH fluorescence lifetime decay to identify measurable differences in optical endpoints of human NSCLC that are indicative of their long-term outcome. Twenty-nine treatment-naïve NSCLC specimens were classified into metastatic and non-metastatic groups according to subject-detail reports. The ORR and mean NADH lifetime were determined for each sample, revealing a significant increase in the ORR for the metastatic group. Given that KEAP1 expression has previously been associated with poor patient outcomes, we stained our samples for KEAP1 and found low KEAP1 expression regions to be associated with higher ORR. A deep learning network base on Inception-ResNet-v2 trained on imaging endpoints (AUC = 0.68) outperformed a model built with only clinicopathologic features (AUC = 0.45), when classifying tumors based on their metastatic status. These results demonstrate the feasibility of using optical imaging of autofluorescence of metabolic cofactors to identify differences indicative of long-term patient outcome.