Radiomics to predict response to immunotherapy: an imminent reality?

Emerging Technologies for Non-invasive Monitoring of Treatment Response to Immunotherapy for Brain Tumors

Glioblastoma is the most common primary malignant brain tumor and one of the most aggressive tumors across all cancer types with remarkable resistance to any treatment. While immunotherapy has shown a robust clinical benefit in systemic cancers, its benefit is still under investigation in brain cancers. The broader use of immunotherapy in clinical trials for glioblastoma has highlighted the challenges of traditional methods of monitoring progression via imaging. Development of new guidelines, advanced imaging techniques, and immune profiling have emerged to counter premature diagnoses of progressive disease. However, these approaches do not provide a timely diagnosis and are costly and time consuming. Surgery is currently the standard of care for diagnosis of pseudoprogression in cases where MRI is equivocal. However, it is invasive, risky, and disruptive to patient's lives and their oncological treatment. With its increased vascularity, glioblastoma is continually shedding tumor components into the vasculature including tumor cells, genetic material, and extracellular vesicles. These elements can be isolated from routine blood draws and provide a real-time non-invasive indicator of tumor progression. Liquid biopsy therefore presents as an attractive alternative to current methods to guide treatment. While the initial evaluation of liquid biopsy for brain tumors via identification of mutations in the plasma was disappointing, novel technologies and use of alternatives to plasma cell-free DNA analytes provide promise for an effective liquid biopsy approach in brain tumors. This review aims to summarize developments in the use of liquid biopsy to monitor glioblastoma, especially in the context of immunotherapy.

The Role of Radiomics in Lung Cancer: From Screening to Treatment and Follow-Up

Purpose

Lung cancer represents the first cause of cancer-related death in the world. Radiomics studies arise rapidly in this late decade. The aim of this review is to identify important recent publications to be synthesized into a comprehensive review of the current status of radiomics in lung cancer at each step of the patients’ care.

Methods

A literature review was conducted using PubMed/Medline for search of relevant peer-reviewed publications from January 2012 to June 2020

Results

We identified several studies at each point of patient’s care: detection and classification of lung nodules (n=16), determination of histology and genomic (n=10) and finally treatment outcomes predictions (=23). We reported the methodology of those studies and their results and discuss the limitations and the progress to be made for clinical routine applications.

Conclusion

Promising perspectives arise from machine learning applications and radiomics based models in lung cancers, yet further data are necessary for their implementation in daily care. Multicentric collaboration and attention to quality and reproductivity of radiomics studies should be further consider.