Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers

Abstract

Introduction: 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.

Patients and methods: 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.

Results: 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.

Conclusions: 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.

Keywords: artificial intelligence; immunotherapy; machine learning; medical imaging; radiomics; response prediction.

Figure 1.

(A) Baseline contrast-enhanced CT scan of melanoma patient presenting with metastases in the liver and lymph nodes in the axilla and subclavicular area. (B) Follow-up scan of the same patient showing complete response in the axillary region and partial response of the lesions in the liver and neck. (C) Baseline CT scan of an NSCLC patient presenting lesion in the left lung, that showed progression at a later FU CT (data not shown). (D) Baseline CT scan of a melanoma patient presenting lesions in the right lung that showed response at a later FU CT (data not shown). (E) Schematic representation of the radiomics feature extraction process. (F) Schematic of the machine learning process.

Figure 2.

(A) Response kinetics curve depicting individual lesion responses (as dots) on a patient-to-patient basis. (B) One-year survival plot for all analyzed patients (C) for melanoma patients only, (D) for NSCLC patients only.

Figure 3.

Performance of the selected classifier on the independent test set for NSCLC lesions (A) and melanoma lesions (B). (C) Patient level response at first follow-up and (D) prognostic performance of the imaging biomarker on a patient level.