Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers

TLDR

Immunotherapy is a major breakthrough in cancer treatment, yet only a subset of patients respond, highlighting the need for predictive biomarkers. The study tests whether AI can automatically quantify radiographic features that serve as noninvasive radiomic biomarkers for predicting immunotherapy response. Using contrast‑enhanced CT, the authors applied AI to 1,055 lesions from 203 melanoma and NSCLC patients on anti‑PD1 therapy, developing a machine‑learning biomarker and validating it, while gene‑set enrichment analysis on an independent NSCLC cohort explored its biological basis. The biomarker achieved AUCs of 0.83 in NSCLC lesions and 0.64 in melanoma lymph nodes, and patient‑level predictions reached AUC 0.76 with a 24% 1‑year survival advantage, linking increased proliferative pathways to response and supporting radiographic features as useful noninvasive biomarkers for patient stratification.

Abstract

Immunotherapy is regarded as one of the major breakthroughs in cancer treatment. Despite its success, only a subset of patients responds-urging the quest for predictive biomarkers. We hypothesize that artificial intelligence (AI) algorithms can automatically quantify radiographic characteristics that are related to and may therefore act as noninvasive radiomic biomarkers for immunotherapy response. In this study, we analyzed 1055 primary and metastatic lesions from 203 patients with advanced melanoma and non-small-cell lung cancer (NSCLC) undergoing anti-PD1 therapy. We carried out an AI-based characterization of each lesion on the pretreatment contrast-enhanced CT imaging data to develop and validate a noninvasive machine learning biomarker capable of distinguishing between immunotherapy responding and nonresponding. To define the biological basis of the radiographic biomarker, we carried out gene set enrichment analysis in an independent dataset of 262 NSCLC patients. The biomarker reached significant performance on NSCLC lesions (up to 0.83 AUC, P < 0.001) and borderline significant for melanoma lymph nodes (0.64 AUC, P = 0.05). Combining these lesion-wide predictions on a patient level, immunotherapy response could be predicted with an AUC of up to 0.76 for both cancer types (P < 0.001), resulting in a 1-year survival difference of 24% (P = 0.02). We found highly significant associations with pathways involved in mitosis, indicating a relationship between increased proliferative potential and preferential response to immunotherapy. These results indicate that radiographic characteristics of lesions on standard-of-care imaging may function as noninvasive biomarkers for response to immunotherapy, and may show utility for improved patient stratification in both neoadjuvant and palliative settings.