Artificial Intelligence Measured Tumor Burden and Pre-Treatment Circulating Tumor DNA in Human Papilloma Virus-Associated Oropharynx Cancer.

Abstract

Artificial intelligence (AI)-based imaging analysis and circulating tumor-associated DNA (ctDNA) are both being used diagnostically in HPV-driven oropharynx squamous cell carcinoma (HPV-OPSCC). We evaluated associations between AI-measured tumor burden and ctDNA. We analyzed 170 patients treated definitively for HPV-OPSCC. All had pre-treatment serum tumor-tissue modified viral (TTMV) ctDNA levels. An AI algorithm measured tumor and lymph nodes on CT scans. Linear regressions detected associations between ctDNA (fragments/mL) and automated volumes, clinical tumor (T) and nodal (N) stage, and disease factors. Automated tumor volume (coeff = 39.43, p < 0.001), nodal volume (coeff = 39.54, p < 0.001), T stage (coeff = 1031.09, p = 0.009), and N stage (coeff = 1840, p = 0.018) were associated with ctDNA. On multivariable analysis, tumor (coeff = 34.79, p = 0.001) and nodal volumes (coeff = 24.68, p = 0.022) were associated with ctDNA; T and N stage were not. Automated volumetrics are independently and more strongly associated with ctDNA, compared with clinical stage. Automated volumetrics provide a practical correlate to ctDNA.