Role of radiomics in predicting immunotherapy response

Abstract

Summary Immunotherapies have revolutionised cancer management. Despite their success, durable responses are limited to a subset of patients. Prediction of immunotherapy response in patients has proven to be difficult due to a lack of robust biomarkers. Routinely collected imaging may offer an additional information source to personalise patient treatment, with advantages over tissue‐based biomarkers. Quantitative image analysis or radiomics, which involves the high‐throughput extraction of imaging features, has the potential to non‐invasively predict cancer histology, outcomes and prognosis. This review evaluates the value of radiomics in patients undergoing immunotherapy, with a summary provided of the performance of radiomics models in predicting immunotherapy response and toxicity, as well as immune correlates. Much of the literature focussed on clinical endpoints and correlates to tissue biomarkers, particularly in lung cancer, while few studies investigated association with immune‐related adverse events. Strengths of the studies included more frequent use of clinical trial datasets, homogenous patient cohorts and high‐quality diagnostic scans. Limitations of the studies include heterogeneity in study methodology, lack of well‐defined homogenous imaging datasets, limited open publishing of imaging datasets, coding and parameters used for radiomics signature development and limited use of external validation datasets. Future research should address the above limitations, as well as further explore the relationship between radiomics and immune‐related adverse effects and less well‐studied biological correlates such tumour mutational burden, and incorporate known clinical prognostic scores into radiomics models.

Radiomics, a Promising New Discipline: Example of Hepatocellular Carcinoma

“…Nevertheless, a response to immunotherapy, which is highly effective when it occurs, cannot be obtained in all patients. There is, therefore, a challenge to predict which patients will respond and, thus, avoid potential side effects in others [ 31 ]. These equivocal results of immunotherapy could be explained by inter-individual variability in tumor lymphocyte infiltration, which implies that characterization of the tumor environment is an essential activity in the management of these systemic therapies [ 32 ].…”

Nonoperative Management of dMMR/MSI-H Colorectal Cancer following Neoadjuvant Immunotherapy: A Narrative Review

“…41 In the case of immunotherapy, radiomics has also shown potential of predicting and diagnosing CR. 42 PET-CT is another important evaluating tool for colon cancer. An excellent review by Borm et al have summarized the advantage of this technique, including being able to discern early response and providing more features on residual disease that can facilitate cCR identification.…”

The impact of inter-observer variation in delineation on robustness of radiomics features in non-small cell lung cancer

“…cance rimag ingar chive. net) 4,6 . Additional data used and analysed during the current study are available from the corresponding author on reasonable request.…”

“…The de-identified imaging and clinical datasets analysed during the current study are available from an openly accessible online centralised repository, The Cancer Imaging Archive (TCIA) ( https://www.cancerimagingarchive.net ) 4 , 6 . Additional data used and analysed during the current study are available from the corresponding author on reasonable request.…”

“…There are several published studies assessing the value of a radiomics based approach in predicting outcomes for oncology patients. These studies found radiomic features to be associated with oncological outcomes including local control and overall survival [1][2][3] , risk of lymph node metastases 4 , rates of pathological complete response 5 , and tissue biomarkers 6 . Aerts et al 2014 published a radiomics signature (then reproduced in distributed learning fashion by Shi et al 2019) that incorporated four radiomics features found to be prognostic in non-small cell lung cancer (NSCLC) 7,8 .…”